Identification of Missed Pulmonary Nodules on Low Dose CT Lung Cancer Screening Studies Using an Automatic Detection System

Size: px
Start display at page:

Download "Identification of Missed Pulmonary Nodules on Low Dose CT Lung Cancer Screening Studies Using an Automatic Detection System"

Transcription

1 Identification of Missed Pulmonary Nodules on Low Dose CT Lung Cancer Screening Studies Using an Automatic Detection System Carol L. Novak *a, Li Fan a, Jianzhong Qian a, Guo-Qing Wei a, David P. Naidich b a Siemens Corporate Research; 755 College Road East, Princeton, NJ b New York University Medical Center, st Avenue, New York, NY ABSTRACT Multi-slice CT (MSCT) scanners allow nodules as small as 3mm to be identified during screening. However the associated large data sets make it challenging for radiologists to identify all small nodules in a reasonable amount of time. Computer-aided detection may play a critical role in identifying missed nodules. 13 MSCT screening studies, initially interpreted as non-actionable by a radiologist, were selected from participants in a lung cancer screening study. The study protocol defines actionable studies as those containing at least 1 solid non-calcified nodule larger than 3mm, for which follow-up studies are recommended to exclude interval growth. An automatic detection algorithm was applied to the 13 studies to determine whether it might detect missed nodules, and whether any of these were of sufficient size to be considered actionable. There were a total of 138 automatically detected candidate nodules, an average of 10.6 per patient. 83 candidates were characterized as true positives, yielding a positive predictive value of 60.1%. 10 automatically detected candidates were judged to be actionable nodules greater than 3mm in diameter. 6 of 13 (46%) patients had at least one actionable finding detected by the computer that had been overlooked in the initial exam. Keywords: CT lung cancer screening, automatic detection, computer-aided diagnosis 1. INTRODUCTION Lung cancer is the leading cause of cancer-related mortality in the United States and worldwide. The average five-year survival rate for all stages of lung cancer is only about 15% 1. However lung cancer diagnosed in the early stages has a much better prognosis, with reported five-year survival rates for stage I lung cancer of 60-70% 2-3. Therefore detection of lung cancer in the earliest stages may hold the key to improving cure rates. Low dose Computed Tomography (CT) imaging for screening of lung cancer is becoming increasingly popular, since it allows earlier detection of lung tumors than chest x-rays 4. Several studies are currently under way to determine whether CT screening will ultimately decrease disease specific mortality in patients with non-small cell lung cancer. Multi-slice CT (MSCT) scanners are capable of scanning the entire volume of the lungs in a single breath-hold, utilizing a slice collimation of 1mm or less, and at a low enough radiation dose to be acceptable for screening. With such high-resolution data, it is possible for radiologists to detect and examine very small, potentially malignant nodules. However, MSCT results in typical data sets of 300 to 600 images per patient. This presents a substantial clinical burden to examining physicians. Due to workflow constraints, many radiologists do not examine images reconstructed every 1mm, but instead look at a smaller set of images reconstructed at thicker intervals, such as 5mm thick images reconstructed every 4mm, or 7mm thick images reconstructed every 6mm. This reduces the number of images to examine to a more manageable 50 to 75 per study. Naturally, thicker sections make it more difficult for the reader to find small nodules, especially those less than 5mm in diameter. However even with the use of 1mm images, it is still quite possible for readers to miss nodules in the 3-5mm size range, principally due to obscuring structures such as vessels and airways. * carol.novak@scr.siemens.com Medical Imaging 2003: Image Perception, Observer Performance, and Technology Assessment, Dev P. Chakraborty, Elizabeth A. Krupinski, Editors, Proceedings of SPIE Vol (2003) 2003 SPIE /03/$

2 Due to the complexity of examination of MSCT data sets, some type of computerized assistance would be an extremely valuable asset to radiologists. Many research groups are currently developing and testing Computer Aided Diagnosis (CADx) systems for lung cancer screening with CT One of the goals of CADx is for the computer to automatically identify nodules that would otherwise have been missed by the examining physician. In this paper we present some preliminary data about the potential clinical impact of an automatic nodule detection system upon routine screening. 2. METHODS AND MATERIALS Thirteen low dose (40 mas) MSCT screening studies, initially interpreted as normal or non-actionable, were selected from participants evaluated at New York University Medical Center as part of the Early Detection Research Network (EDRN) study of lung cancer screening. The EDRN protocol calls for CT studies to be performed using 1 mm collimation, but with initial radiologic evaluation performed on 7mm reconstructed images, consistent with standard clinical care. According to the EDRN protocol, all solid nodules less than 3mm in diameter are interpreted as non-actionable. By contrast, actionable nodules are defined as solid non-calcified nodule greater than 3mm in diameter. Non-solid or pure ground glass nodules are considered actionable if they are greater than 5mm in diameter. Nodules with a homogeneous pattern of calcification are considered non-actionable regardless of size. An actionable nodule leads to the recommendation of some follow-up evaluation for the patient, typically a repeat MSCT scan in 3 months to exclude interval growth. In the case of very suspicious lesions, an immediate biopsy may be recommended rather than a repeat scan. Non-actionable nodules receive no follow-up other than a repeat yearly scan. These categories are shown in table 1. Non-actionable Solid nodules < 3mm in diameter Non-solid nodules < 5mm in diameter Calcified nodules Actionable Solid nodules > 3mm in diameter Non-solid nodules > 5mm in diameter Table 1: Description of actionable and non-actionable nodules according to the EDRN study protocol. Actionable nodules result in some recommendation for follow-up evaluation, typically a repeat scan in 3 months. A patient study is deemed non-actionable if it contained no actionable nodules detected during the radiologist screening on 7mm sections. An automatic detection algorithm developed at Siemens Corporate Research was applied to 1.25mm reconstructions from the non-actionable studies, to determine whether the algorithm might detect missed nodules, and whether any of these were of sufficient size to fall into the actionable category. The automatic detection system employed here is a knowledge-based automatic detection system with multiple modules developed for different nodule types 15. The system makes use of specialized algorithms to detect solitary nodules, nodules attached to vessels, and nodules attached to the chest wall. The modules are integrated to share processing information efficiently, to speed up processing and increase reliability. In addition the system contains specialized modules for removing false positives. The modular system is extensible to handle the inclusion of new detection systems, such as one for detecting sub-solid or ground glass nodules. The results of the automatic detection algorithm were validated by a thoracic radiologist experienced in interpreting low dose CT screening studies. For each computer-generated finding the radiologist determined whether the finding truly constituted a nodule, whether it was calcified, and whether it was above or below the size criteria established in the study protocol (see table 1). The sizes were initially determined by the placing a 3mm diameter circle on the axial slice where the nodule appeared largest, to determine whether the nodule fit completely within the circle. If the nodule extended outside the circle, it was considered to have diameter larger than 3mm in the axial plane, and thus actionable. 440 Proc. of SPIE Vol. 5034

3 The nodule sizes were also evaluated by a computer program that performs interactive segmentation. The segmentation program determines the greatest nodule diameter in any dimension, rather than the greatest diameter in the axial dimension 16. The greatest diameter in any direction will generally be slightly larger than the greatest axial diameter, and in no case smaller. As semi-automated or automated segmentation becomes increasingly available in the clinical workflow, radiologists will probably come to rely increasingly on measurements made in this way. For this paper, we report nodule sizes made both by appearance in the axial plane, and by computer measurement in all axes. Figure 1 shows one of the missed actionable nodules detected by the computer. Figure 1(b) shows a 3mm circle superimposed on the image, indicating that the nodule is larger than 3mm in diameter in the axial plane. The computer measured this nodule as 5.2mm in the largest diameter. (b) (a) Figure 1: Example of a missed actionable nodule detected by the computer. (a) shows the entire slice with a box around the detected nodule. (b) shows a magnification of the region inside the box in 1(a); the dark circle is exactly 3mm in diameter, indicating that the largest diameter of the nodule in this slice exceeds 3mm. (c) shows a shaded surface display of the segmented nodule in light gray. The darker gray structures are nearby vessels. (c) Figure 2 shows one of the missed non-actionable nodules detected by the computer. The nodule was judged to be nonactionable because it fit completely inside the 3mm circle, indicating that it was smaller than 3mm axially. However the computer measured the diameter as 4.1mm in the largest dimension. The radiologist also retrospectively examined the 7 mm images containing the missed nodules to estimate whether they could in principle have been seen during the initial examination of thick sections. Nodules that were visible on the thick sections, generally those that were peripherally located, were judged retrospectively visible. Nodules that could not be seen on the 7mm images, generally those obscured by vessels and centrally located, were judged to be retrospectively not visible. Proc. of SPIE Vol

4 (b) (a) Figure 2: Example of a missed non-actionable nodule detected by the computer. (a) shows the entire slice with a box around the detected nodule. (b) shows the boxed region in more detail; the circle is exactly 3mm in diameter, indicating that the largest diameter of the nodule in this slice is less than 3mm. (c) shows a shaded surface display of the segmented nodule in light gray. The darker gray structures are nearby vessels, the chest wall, and some artifacts due to noise. Figure 3 shows a computer detected actionable nodule that was judged to have been retrospectively visible on the 7mm thick sections. 3(a) shows the appearance on 1mm thick slices and 3(b) shows the appearance on 7mm thick slices. The nodule is located fairly close to the periphery of the lungs and is not obscured by surrounding vessels. (c) (a) Figure 3: Example of an actionable nodule that was judged retrospectively visible on thick sections. The nodule is centered within the box. (a) shows the appearance on 1mm sections and (b) shows the appearance on 7mm thick sections. (b) 442 Proc. of SPIE Vol. 5034

5 Figure 4 shows a computer detected actionable nodule that was judged not to have been retrospectively visible on the thick sections. The nodule is located centrally and thus not distinguishable from vessels of similar size in the vicinity. (a) Figure 4: Example of an actionable nodule that was not retrospectively visible on thick sections. (a) shows the nodule on 1mm sections and (b) shows the nodule on 7mm thick sections. (b) 3. RESULTS There were a total of 138 automatically detected candidate nodules in the 13 patients, an average of 10.6 per patient. The number of detections per patient ranged from 1 to 53. Each candidate nodule was classified into one of the following categories: false positive, an actionable non-calcified nodule with size above 3mm, a non-actionable noncalcified nodule with size below 3mm, a calcified nodule of any size, or a non-nodule abnormality such as scarring or atelectasis. Since the automatic detection system is not currently designed to detect pure ground glass nodules, there is no separate category for their detection. The categories are shown in table 2. Category Description 0 False positive 1 Actionable nodule 2 Non-calcified nodule < 3mm in diameter 3 Calcified nodule of any size 4 Non-nodule abnormality Table 2: Categories for classifying automatically detected nodule candidates. 55 of the automatically detected candidates were classified as false positives in category 0, an average of 4.2 per patient, with a range of 0 to 17 false positives per patient. The remaining 83 candidates were categorized as belonging to one of the four categories of true positives, yielding an average of 6.4 per patient, with a range of 0 to 47 per patient. 47 (34.1%) of the 138 candidates were calcified nodules in category 3, and 15 (10.9%) were interpreted as non-nodule abnormalities in category of the 138 candidates (15.2%) were interpreted as non-calcified nodules. Size alone was used to assign them to the actionable category 1 or non-actionable category 2. Using the apparent diameter on an axial slice to determine size, 10 of the nodules were judged large enough to be actionable, and 11 were judged below 3mm in diameter and thus nonactionable. These results are summarized in table 3. Proc. of SPIE Vol

6 Number of % of Per patient Category findings total Average Minimum Maximum 0 false positive % actionable % non-actionable % calcified % other abnormality % total % Table 3: Results of automatic detection by category However when measuring the greatest diameter in any dimension, all 21 non-calcified nodules were at least 3mm in diameter. This is not a coincidence; the fact is that the automatic detection system has been configured to only report nodules that are at least 3mm in their largest diameter. It is likely that the system could have detected additional nodules smaller than 3mm in diameter, but the algorithm is currently designed to ignore smaller findings. If clinical practice guidelines were to change to specify the detection of smaller nodules, of course it would be a simple matter to change the program to report smaller findings. These results are summarized in table 4. Since the current clinical practice is to judge actionability by the appearance of nodule size on axial slices, we will follow this guideline to classify only 10 of the 21 non-calcified nodules as actionable under the current clinical standard. Number of detected noncalcified nodules with given axial diameter Number of detected noncalcified nodules with given diameter in any direction > 3mm < 3mm 11 0 Table 4: Categorization of nodule sizes by maximum axial diameter, or by maximum diameter in any direction The 10 clearly actionable nodules that had been missed by the examining physician and detected by the computer were divided among 6 patients. In other words, 6 of the 13 patients, or 46%, had at least one actionable finding. If instead we consider all 21 non-calcified nodules that were at least 3mm in diameter in some axis, the 21 findings were divided among 10 patients (77%). Only 3 of the 13 patients (23%) had no computer-detected non-calcified nodules. These findings are shown in the graph in figure 5. The EDRN protocol for patients enrolled in the study specifies that non-calcified nodules above 3mm in diameter are actionable. However other studies may use different size thresholds. 62% of patients had at least one missed nodule larger than 4mm in diameter when measured in any direction. 31% of patients had at least one missed nodule larger than 5mm. In this sample of 13 patients, the computer did not find any missed non-calcified nodules larger than 8mm in diameter. Figure 6 shows the percentage of patients containing at least 1 missed nodule at various size thresholds. In retrospect, 28 (41.2%) of 68 true positive nodules in categories 1, 2 and 3 could be identified on the initial 7 mm images once their location was known. This includes 20 of 47 (42.6%) calcified nodules. 6 of 10 (60%) nodules larger than 3mm in diameter on axial slices could be retrospectively identified on the thick sections. By contrast, only 2 of 11 (18.2%) nodules with axial diameter <3mm could be retrospectively seen on thick sections. The rest of the nodules were not visible on corresponding thick sections, due to their central location or proximity to an adjacent vessel. These results are summarized in table Proc. of SPIE Vol. 5034

7 Percentage of patients with at least 1 actionable nodules missed by reader and detected by computer 23% Patients with >= 1 actionable nodule 46% Patients with >= 1 possibly actionable nodule Patients with 0 noncalcified nodules 31% Figure 5: Automatic detection of nodules not seen by examining radiologist, according to percentage of patients containing at least 1 finding. Definitely actionable nodules were >3 mm in diameter on an axial slice. Possibly actionable nodules were >3 mm in diameter in some other dimension, but less than 3mm axially. 100% Patients with at least one non-calcified nodule of given size % of patients 90% 80% 70% 60% 50% 40% 30% 20% 10% 0% 77% 62% 31% 23% 8% 0% >3 >4 >5 >6 >7 >8 largest diameter (mm) in any direction Figure 6: Percentage of patients where the computer detected at least one missed non-calcified nodule greater than various thresholds. Proc. of SPIE Vol

8 1 2 3 Nodule Retrospective examination on thick sections Category Visible Not visible Total Actionable nodule Nonactionable nodule Calcified nodule 6 (60.0%) 4 (40.0%) 10 2 (18.2%) 9 (81.8%) (42.6%) 27 (57.4%) 47 Table 5: Results of retrospective examination of computer-detected nodules, to determine whether they could have been seen during reader examination of thick sections. 5. DISCUSSION Studies of lung cancer screening with low-dose CT are finding that one-quarter to one-half of patients have an actionable finding at the first screening Our results suggest that with the use of automatic nodule detection software, this percentage could rise substantially. In this investigation we found that almost half of the screening patients who were deemed by the screening examiner to have no actionable nodules, actually had a nodule that if seen might have led to a recommendation for follow-up. If we expand the criteria from 3mm in diameter in the axial direction to 3mm in any direction, still more patients were found to have nodules large enough to warrant action. We have observed that fairly often nodules that are just over 3mm in their greatest diameter will have a cross-section slightly below 3mm in the axial plane. As software for automatically or semi-automatically measuring nodules becomes more widely available, radiologists may come to rely upon it to determine nodule sizes and thus actionability. We predict that changing the measurement criteria from 3mm in the axial plane to 3mm in any direction would inevitably lead to an increase in actionable nodules if the threshold for action were kept constant. Our automatic detection system is not yet able to detect all nodules found by physicians. In particular non-solid or pure ground glass nodules are not currently detected by the system. Although the computer did detect several nodules missed by the examining physicians, it should not be concluded that the computer is more skilled at detection than a radiologist, but rather that it is complementary. The lungs have a very complex structure of vessels and airways, and it is impractical for a reader to examine every millimeter in detail. We argue that this should be the job of the computer. 6. CONCLUSIONS In this investigation, we show that an automatic nodule detection system is frequently able to find nodules not reported by the examining physician, but which if seen might have led to the recommendation for further action. The computer found at least 1 non-calcified nodule larger than 3mm in axial diameter in 6 out of 13 or 46% of non-actionable studies. The computer program also detected non-calcified nodules that were less than 3mm in the axial diameter, although larger than 3mm in some other axis, in an additional 4 patients (31%). Although automatic lung nodule detection is still in the stages of development and testing, we conclude that the potential is clearly there to aid physicians in the detection of small, potentially malignant nodules that would have otherwise been overlooked during routine screening examinations. REFERENCES 1. J. H. Schiller, Current standards of care in small-cell and non-small-cell lung cancer, Oncology 61 Supp l, pp. 3-13, M. T. van Rens, A. B. de la Riviere, H. R. Elbers, J. M. van Den Bosch, Prognostic assessment of 2,361 patients who underwent pulmonary resection for non-small cell lung cancer, I, II, and IIIA, Chest 117(2), pp , Proc. of SPIE Vol. 5034

9 3. R. Shah, S. Sabanathan, J. Richardson, A.J. Mearns, C. Goulden, Results of surgical treatment of stage I and II lung cancer, The Journal of Cardiovascular Surgery, 37, pp , C. I. Henschke, D. I. McCauley, D. F. Yankelevitz, D. P. Naidich, G. McGuinness, O. S. Miettinen, D. M. Libby, M. W. Pasmantier, J. Koizumi, N. K. Altorki, J. P. Smith, Early lung cancer action project: overall design and findings from baseline screening, The Lancet, 354, pp , S. G. Armato III, F. Li, M. L. Giger, H. MacMahon, S. Sone, K. Doi, Lung Cancer: Performance of Automated Lung Nodule Detection Applied to Cancers Missed in a CT Screening Program, Radiology, 225(3), pp , M. S. Brown, M. F. McNitt-Gray, J. G. Goldin, R. D. Suh, D. R. Aberle, Patient-specific models for lung nodule detection and surveillance in CT images, Proceedings of the SPIE Conference on Medical Imaging, 4322, pp , P. Croisille, M. Souto, M. Cova, S. Wood, Y. Afework, J.E. Kuhlman, and E.A. Zerhouni, Pulmonary nodules: improved detection with vascular segmentation and extraction with spiral CT, Thoracic Radiology, vol. 197, pp , M. Fiebich, D. Wormanns, W. Heindel, Improvement of method for computer-assisted detection of pulmonary nodules in CT of the chest, Proceedings of the SPIE Conference on Medical Imaging, 4322, pp , M. N. Gurcan, N. Petrick, B. Sahiner, H-P. Chan, P. N. Cascade, E. A. Kazerooni, L. M. Hadjiiski, Computerized lung nodule detection on thoracic CT images: combined rule-based and statistical classifier for false positive reduction, Proceedings of the SPIE Conference on Medical Imaging, 4322, pp , W. J. Kostis, A. P. Reeves, D. F. Yankelevitz, and C. I. Henschke, Three-dimensional segmentation of solitary pulmonary nodules from helical CT scans, Computer Assisted Radiology and Surgery, pp , M. Kubo, T. Yamamoto, Y. Kawata, N. Niki, K. Eguchi, H. Ohmatsu, R. Kakinuma, M. Kaneko, M. Kusumoto, N. Moriyama, K. Mori, H. Nishiyama, CAD system to support comparative reading for lung cancer based on helical CT images, Computer Assisted Radiology and Surgery, ICS 1230, pp , C. L. Novak, L. Fan, J. Qian, G. Kohl, D. P. Naidich, An interactive system for CT lung nodule identification and examination, Computer Assisted Radiology and Surgery, ICS 1230, pp , H. Takizawa, S. Yamamoto, T. Matsumoto, Y. Tateno, T. Iinuma, M. Matsumoto, Recognition of lung nodules from x-ray CT images using 3D MRF models, Computer Assisted Radiology and Surgery, pp , R. Wiemker, P. Rogalla, A. Zwartkruis, T. Blaffert, Computer aided lung nodule detection on high resolution CT data, Proceedings of the SPIE Conference on Medical Imaging, J. Qian, L. Fan, G. Wei, C. L. Novak, B. Odry, H. Shen, L. Zhang, D. P. Naidich, J. P. Ko, A. N. Rubinowitz, G. Kohl, Knowledge-based Automatic Detection of Multi-type Lung Nodules from Multi-detector CT Studies, Proceedings of the SPIE Conference on Medical Imaging, 4684, L. Fan, J. Qian, B. Odry, H. Shen, D. P. Naidich, G. Kohl, E. Klotz; Automatic Segmentation of Pulmonary Nodules by Using Dynamic 3D Cross-correlation for Interactive CAD Systems ; Medical Imaging 2002: Image Processing; M. Sonka and M. J. Fitzpatrick, editors; Proceedings of SPIE Volume 4684, pp , C.I. Henschke, D.F. Yankelevitz, R. Mirtcheva, G. McGuinness, D. McCauley, O.S. Miettinen, CT screening for lung cancer: frequency and significance of part-solid and nonsolid nodules ; AJR Am J Roentgenol 178(5), pp , S. Diederich, D. Wormanns, M. Semik, M. Thomas, H. Lenzen, N. Roos, W. Heindel, Screening for early lung cancer with low-dose spiral CT: prevalence in 817 asymptomatic smokers ; Radiology 222(3), pp , Proc. of SPIE Vol

Copyright 2008 Society of Photo Optical Instrumentation Engineers. This paper was published in Proceedings of SPIE, vol. 6915, Medical Imaging 2008:

Copyright 2008 Society of Photo Optical Instrumentation Engineers. This paper was published in Proceedings of SPIE, vol. 6915, Medical Imaging 2008: Copyright 2008 Society of Photo Optical Instrumentation Engineers. This paper was published in Proceedings of SPIE, vol. 6915, Medical Imaging 2008: Computer Aided Diagnosis and is made available as an

More information

Segmentation of nodules on chest computed tomography for growth assessment

Segmentation of nodules on chest computed tomography for growth assessment Segmentation of nodules on chest computed tomography for growth assessment William Mullally, a) Margrit Betke, and Jingbin Wang Computer Science Department, Boston University, Boston, Massachusetts 02215

More information

Chapter 5. Pulmonary nodules detected at lung cancer screening: Interobserver variability of semiautomated volume measurements

Chapter 5. Pulmonary nodules detected at lung cancer screening: Interobserver variability of semiautomated volume measurements Chapter 5 Pulmonary nodules detected at lung cancer screening: Interobserver variability of semiautomated volume measurements Hester Gietema Ying Wang Dongming Xu Rob van Klaveren Harry de Koning Ernst

More information

Computer-Aided Detection in Screening CT for

Computer-Aided Detection in Screening CT for Yuan et al. Screening CT for Pulmonary Chest Imaging Original Research C M E D E N T U R I C L I M G I N G JR 2006; 186:1280 1287 0361 803X/06/1865 1280 merican Roentgen Ray Society Y O Ren Yuan 1 Patrick

More information

Small Pulmonary Nodules: Our Preliminary Experience in Volumetric Analysis of Doubling Times

Small Pulmonary Nodules: Our Preliminary Experience in Volumetric Analysis of Doubling Times Small Pulmonary Nodules: Our Preliminary Experience in Volumetric Analysis of Doubling Times Andrea Borghesi, MD Davide Farina, MD Roberto Maroldi, MD Department of Radiology University of Brescia Brescia,

More information

Copyright 2007 IEEE. Reprinted from 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, April 2007.

Copyright 2007 IEEE. Reprinted from 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, April 2007. Copyright 27 IEEE. Reprinted from 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, April 27. This material is posted here with permission of the IEEE. Such permission of the

More information

doi: /

doi: / Yiting Xie ; Matthew D. Cham ; Claudia Henschke ; David Yankelevitz ; Anthony P. Reeves; Automated coronary artery calcification detection on low-dose chest CT images. Proc. SPIE 9035, Medical Imaging

More information

Low-dose CT Lung Cancer Screening Guidelines for Pulmonary Nodules Management Version 2

Low-dose CT Lung Cancer Screening Guidelines for Pulmonary Nodules Management Version 2 Low-dose CT Lung Cancer Screening Guidelines for Pulmonary Nodules Management Version 2 The Committee for Management of CT-screening-detected Pulmonary Nodules 2009-2011 The Japanese Society of CT Screening

More information

Small solid noncalcified pulmonary nodules detected by screening chest computed tomography

Small solid noncalcified pulmonary nodules detected by screening chest computed tomography Respiratory Medicine (2007) 101, 1880 1884 Small solid noncalcified pulmonary nodules detected by screening chest computed tomography Sang-Man Jin a,b, Seung-Ho Choi c, Chul-Gyu Yoo a,b, Young-Whan Kim

More information

Copyright 2008 Society of Photo Optical Instrumentation Engineers. This paper was published in Proceedings of SPIE, vol. 6915, Medical Imaging 2008:

Copyright 2008 Society of Photo Optical Instrumentation Engineers. This paper was published in Proceedings of SPIE, vol. 6915, Medical Imaging 2008: Copyright 28 Society of Photo Optical Instrumentation Engineers. This paper was published in Proceedings of SPIE, vol. 695, Medical Imaging 28: Computer Aided Diagnosis and is made available as an electronic

More information

Computer-aided Detection of Peripheral Lung Cancers Missed at CT: ROC Analyses without and with Localization 1

Computer-aided Detection of Peripheral Lung Cancers Missed at CT: ROC Analyses without and with Localization 1 Feng Li, MD, PhD Hidetaka Arimura, PhD Kenji Suzuki, PhD Junji Shiraishi, PhD Qiang Li, PhD Hiroyuki Abe, MD, PhD Roger Engelmann, MS Shusuke Sone, MD, PhD Heber MacMahon, MD Kunio Doi, PhD Published online

More information

Copyright 2007 Society of Photo Optical Instrumentation Engineers. This paper was published in Proceedings of SPIE, volume 6514, Medical Imaging

Copyright 2007 Society of Photo Optical Instrumentation Engineers. This paper was published in Proceedings of SPIE, volume 6514, Medical Imaging Copyright 2007 Society of Photo Optical Instrumentation Engineers. This paper was published in Proceedings of SPIE, volume 6514, Medical Imaging 2007: Computer Aided Diagnosis and is made available as

More information

Computer Assisted Radiology and Surgery

Computer Assisted Radiology and Surgery Computer Assisted Radiology and Surgery How Can a Massive Training Artificial Neural Network (MTANN) Be Trained With a Small Number of Cases in the Distinction Between Nodules and Vessels in Thoracic CT?

More information

May-Lin Wilgus. A. Study Purpose and Rationale

May-Lin Wilgus. A. Study Purpose and Rationale Utility of a Computer-Aided Diagnosis Program in the Evaluation of Solitary Pulmonary Nodules Detected on Computed Tomography Scans: A Prospective Observational Study May-Lin Wilgus A. Study Purpose and

More information

Copyright 2009 Society of Photo Optical Instrumentation Engineers. This paper was published in Proceedings of SPIE, vol. 7260, Medical Imaging 2009:

Copyright 2009 Society of Photo Optical Instrumentation Engineers. This paper was published in Proceedings of SPIE, vol. 7260, Medical Imaging 2009: Copyright 2009 Society of Photo Optical Instrumentation Engineers. This paper was published in Proceedings of SPIE, vol. 7260, Medical Imaging 2009: Computer Aided Diagnosis and is made available as an

More information

CT Screening for Lung Cancer for High Risk Patients

CT Screening for Lung Cancer for High Risk Patients CT Screening for Lung Cancer for High Risk Patients The recently published National Lung Cancer Screening Trial (NLST) showed that low-dose CT screening for lung cancer reduces mortality in high-risk patients

More information

Chapter 11. Summary and general discussion

Chapter 11. Summary and general discussion Chapter 11 Summary and general discussion Low Dose Computed Tomography of the Chest: Applications and Limitations INTRODUCTION The introduction of spiral, multidetector-row computed tomography (CT) has

More information

Guidelines for the Management of Pulmonary Nodules Detected by Low-dose CT Lung Cancer Screening

Guidelines for the Management of Pulmonary Nodules Detected by Low-dose CT Lung Cancer Screening Guidelines for the Management of Pulmonary Nodules Detected by Low-dose CT Lung Cancer Screening 1. Introduction In January 2005, the Committee for Preparation of Clinical Practice Guidelines for the Management

More information

doi: /

doi: / Yiting Xie ; Yu Maw Htwe ; Jennifer Padgett ; Claudia Henschke ; David Yankelevitz ; Anthony P. Reeves; Automated aortic calcification detection in low-dose chest CT images. Proc. SPIE 9035, Medical Imaging

More information

LOW DOSE SPIRAL COMPUTERIZED TOMOGRAPHY (LDCT) SCREENING FOR LUNG CANCER

LOW DOSE SPIRAL COMPUTERIZED TOMOGRAPHY (LDCT) SCREENING FOR LUNG CANCER LOW DOSE SPIRAL COMPUTERIZED TOMOGRAPHY (LDCT) SCREENING FOR LUNG CANCER A Technology Assessment INTRODUCTION The California Technology Assessment Forum is requested to review the scientific evidence for

More information

ORIGINAL PAPER APPLICATION OF SUBSECOND ROTATION SCAN TO HELICAL CT FOR LUNG CANCER SCREENING

ORIGINAL PAPER APPLICATION OF SUBSECOND ROTATION SCAN TO HELICAL CT FOR LUNG CANCER SCREENING Nagoya J. Med. Sci. 68. 139 ~ 145, 2006 ORIGINAL PAPER APPLICATION OF SUBSECOND ROTATION SCAN TO HELICAL CT FOR LUNG CANCER SCREENING YOSHINE MORI, 1 SHIGEKI ITOH, 2 MITSURU IKEDA, 2 AKIKO SAWAKI, 1 KOUJIRO

More information

IEEE TRANSACTIONS ON MEDICAL IMAGING, VOL. 25, NO. 4, APRIL

IEEE TRANSACTIONS ON MEDICAL IMAGING, VOL. 25, NO. 4, APRIL IEEE TRANSACTIONS ON MEDICAL IMAGING, VOL. 25, NO. 4, APRIL 2006 435 On Measuring the Change in Size of Pulmonary Nodules Anthony P. Reeves*, Senior Member, IEEE, Antoni B. Chan, David F. Yankelevitz,

More information

CT Screening for Lung Cancer: Frequency and Significance of Part-Solid and Nonsolid Nodules

CT Screening for Lung Cancer: Frequency and Significance of Part-Solid and Nonsolid Nodules Claudia I. Henschke 1 David F. Yankelevitz 1 Rosna Mirtcheva 1 Georgeann McGuinness 2 Dorothy McCauley 1 0lli S. Miettinen 3 for the ELCAP Group Received June 19, 2001; accepted after revision November

More information

Ultralow Dose Chest CT with MBIR

Ultralow Dose Chest CT with MBIR Ultralow Dose Chest CT with MBIR Ella A. Kazerooni, M.D. Professor & Director Cardiothoracic Radiology Associate Chair for Clinical Affairs University of Michigan Disclosures Consultant: GE Healthcare

More information

Loren Ketai, MD; Mathurn Malby, BS; Kirk Jordan, MD; Andrew Meholic, MD; and Julie Locken, MD

Loren Ketai, MD; Mathurn Malby, BS; Kirk Jordan, MD; Andrew Meholic, MD; and Julie Locken, MD Small Nodules Detected on Chest Radiography* Does Size Predict Calcification? Loren Ketai, MD; Mathurn Malby, BS; Kirk Jordan, MD; Andrew Meholic, MD; and Julie Locken, MD Study objectives: To determine

More information

Mayo Clinic College of Medicine, Rochester, Minnesota, USA

Mayo Clinic College of Medicine, Rochester, Minnesota, USA The Oncologist Lung Cancer Commentary: CT Screening for Lung Cancer Caveat Emptor JAMES R. JETT,DAVID E. MIDTHUN Mayo Clinic College of Medicine, Rochester, Minnesota, USA Key Words. CT screening Early

More information

Original Article Thoracic Imaging

Original Article Thoracic Imaging Original Article Thoracic Imaging https://doi.org/10.3348/kjr.2018.19.4.803 pissn 1229-6929 eissn 2005-8330 Korean J Radiol 2018;19(4):803-808 Radiological Report of Pilot Study for the Korean Lung Cancer

More information

Results of three-year mass screening programme for lung cancer using mobile low-dose spiral computed tomography scanner

Results of three-year mass screening programme for lung cancer using mobile low-dose spiral computed tomography scanner doi: 10.1054/ bjoc.2000.1531 available online at http://www.idealibrary.com on http://www.bjcancer.com Results of three-year mass screening programme for lung cancer using mobile low-dose spiral computed

More information

A VIRTUAL TRAINING SYSTEM FOR CHEST RADIOGRAM INTERPRETATIONS USING ANATOMICAL HUMAN STRUCTURES IN HIGH-RESOLUTION CT IMAGES

A VIRTUAL TRAINING SYSTEM FOR CHEST RADIOGRAM INTERPRETATIONS USING ANATOMICAL HUMAN STRUCTURES IN HIGH-RESOLUTION CT IMAGES A VIRTUAL TRAINING SYSTEM FOR CHEST RADIOGRAM INTERPRETATIONS USING ANATOMICAL HUMAN STRUCTURES IN HIGH-RESOLUTION CT IMAGES T. Hara*, X. Zhou*, H. Fujita*, I. Kurimoto*, T. Kiryu**, R. Yokoyama**, H.

More information

Early Lung Cancer Action Project: A Summary of the Findings on Baseline Screening

Early Lung Cancer Action Project: A Summary of the Findings on Baseline Screening Early Lung Cancer Action Project: A Summary of the Findings on Baseline Screening CLAUDIA I. HENSCHKE, a DOROTHY I. MCCAULEY, b DAVID F. YANKELEVITZ, a DAVID P. NAIDICH, b GEORGEANN MCGUINNESS, b OLLI

More information

Christine Argento, MD Interventional Pulmonology Emory University

Christine Argento, MD Interventional Pulmonology Emory University Christine Argento, MD Interventional Pulmonology Emory University Outline Lung Cancer Statistics Prior Studies for Lung Cancer Screening NLST Studies Following NLST Future Directions Lung Cancer American

More information

THE BENEFITS OF BIG DATA

THE BENEFITS OF BIG DATA THE BENEFITS OF BIG DATA Disclosures I am a named inventor on a number of patents and patent applications relating to the evaluation of pulmonary nodules on CT scans of the chest which are owned by Cornell

More information

Multidisciplinary Symposium Screening for Cancer. Proposals for lung cancer screening in the UK

Multidisciplinary Symposium Screening for Cancer. Proposals for lung cancer screening in the UK Cancer Imaging (2001) 2, 6 16 Multidisciplinary Symposium Screening for Cancer Monday 15 October 2001, 10.20 12.45 Proposals for lung cancer screening in the UK Janet E Husband Academic Department of Diagnostic

More information

Pulmonary nodule detection in PET/CT images: Improved approach using combined nodule detection and hybrid FP reduction

Pulmonary nodule detection in PET/CT images: Improved approach using combined nodule detection and hybrid FP reduction Pulmonary nodule detection in PET/CT images: Improved approach using combined nodule detection and hybrid FP reduction Atsushi Teramoto* a, Hiroshi Fujita b, Yoya Tomita c, Katsuaki Takahashi c, Osamu

More information

Small Pulmonary Nodules: Volume Measurement at Chest CT Phantom Study 1

Small Pulmonary Nodules: Volume Measurement at Chest CT Phantom Study 1 Jane P. Ko, MD Henry Rusinek, PhD Erika L. Jacobs, MD James S. Babb, PhD Margrit Betke, PhD Georgeann McGuinness, MD David P. Naidich, MD Index terms: Computed tomography (CT), image processing, 60.12117

More information

Computer-Aided Volumetry of Pulmonary Nodules Exhibiting Ground-Glass Opacity at MDCT

Computer-Aided Volumetry of Pulmonary Nodules Exhibiting Ground-Glass Opacity at MDCT Cardiopulmonary Imaging Original Research Oda et al. MDCT and Volumetry of Pulmonary Nodules Cardiopulmonary Imaging Original Research Computer-Aided Volumetry of Pulmonary Nodules Exhibiting Ground-Glass

More information

C2 COMPLETION INSTRUCTIONS

C2 COMPLETION INSTRUCTIONS The C2 Form is completed for each screening exam at T0, T1, and T2. The C2 Form is to be completed by each of the following ACRIN-NLST study staff: the research associate (study coordinator), CT technologist,

More information

VA PARTNERSHIP Increase ACCESS to LUNG SCREENING

VA PARTNERSHIP Increase ACCESS to LUNG SCREENING VA PARTNERSHIP Increase ACCESS to LUNG SCREENING Project PI: Drew Moghanaki, MD, MPH Clinical Co-PI: Claudia Henschke, PhD, MD Technical Co-PI: Rick Avila, MS Sponsored by the Bristol-Myers Squibb Foundation

More information

I9 COMPLETION INSTRUCTIONS

I9 COMPLETION INSTRUCTIONS The I9 Form is completed for each screening exam at T0, T1, and T2. At T0 (baseline), the I9 documents comparison review of the baseline screen (C2 Form) with any historical images available. At T1 and

More information

Pulmonary Nodule Volumetric Measurement Variability as a Function of CT Slice Thickness and Nodule Morphology

Pulmonary Nodule Volumetric Measurement Variability as a Function of CT Slice Thickness and Nodule Morphology CT of Pulmonary Nodules Chest Imaging Original Research Myria Petrou 1 Leslie E. Quint 1 in Nan 2 Laurence H. aker 3 Petrou M, Quint LE, Nan, aker LH Keywords: chest, lung disease, MDCT, oncologic imaging,

More information

LUNG NODULE SEGMENTATION FOR COMPUTER AIDED DIAGNOSIS

LUNG NODULE SEGMENTATION FOR COMPUTER AIDED DIAGNOSIS LUNG NODULE SEGMENTATION FOR COMPUTER AIDED DIAGNOSIS Manjula.T 1 Sheela.S 2 Shanthala.C.P 3 1 Fourth Sem M.Tech (CSE), CIT Gubbi, Tumkur. Email: manjula.t44@gmail.com 2 Asst. Professor, Dept of CSE, CIT

More information

COMPUTER AIDED DIAGNOSIS SYSTEM FOR THE IDENTIFICATION AND CLASSIFICATION OF LESSIONS IN LUNGS

COMPUTER AIDED DIAGNOSIS SYSTEM FOR THE IDENTIFICATION AND CLASSIFICATION OF LESSIONS IN LUNGS COMPUTER AIDED DIAGNOSIS SYSTEM FOR THE IDENTIFICATION AND CLASSIFICATION OF LESSIONS IN LUNGS B.MAGESH, PG Scholar, Mrs.P.VIJAYALAKSHMI, Faculty, Ms. M. ABIRAMI, Faculty, Abstract --The Computer Aided

More information

Measurement error of spiral CT Volumetry:

Measurement error of spiral CT Volumetry: Measurement error of spiral CT Volumetry: Influence of Low Dose CT Technique 1 Tae Gyu Lee, M.D. 2, Myung Jin Chung, M.D., Sung Bum Cho, M.D. 2, Jae Min Cho, M.D., Seog Joon Kim, M.D. 2, Sang Hyun Baik,

More information

Chapter 6. Hester Gietema Cornelia Schaefer-Prokop Willem Mali Gerard Groenewegen Mathias Prokop. Accepted for publication in Radiology

Chapter 6. Hester Gietema Cornelia Schaefer-Prokop Willem Mali Gerard Groenewegen Mathias Prokop. Accepted for publication in Radiology Chapter 6 Interscan variability of semiautomated volume measurements in intraparenchymal pulmonary nodules using multidetector-row computed tomography: Influence of inspirational level, nodule size and

More information

OBJECTIVES. Solitary Solid Spiculated Nodule. What would you do next? Case Based Discussion: State of the Art Management of Lung Nodules.

OBJECTIVES. Solitary Solid Spiculated Nodule. What would you do next? Case Based Discussion: State of the Art Management of Lung Nodules. Organ Imaging : September 25 2015 OBJECTIVES Case Based Discussion: State of the Art Management of Lung Nodules Dr. Elsie T. Nguyen Dr. Kazuhiro Yasufuku 1. To review guidelines for follow up and management

More information

LUNG CANCER continues to rank as the leading cause

LUNG CANCER continues to rank as the leading cause 1138 IEEE TRANSACTIONS ON MEDICAL IMAGING, VOL. 24, NO. 9, SEPTEMBER 2005 Computer-Aided Diagnostic Scheme for Distinction Between Benign and Malignant Nodules in Thoracic Low-Dose CT by Use of Massive

More information

Acknowledgments. A Specific Diagnostic Task: Lung Nodule Detection. A Specific Diagnostic Task: Chest CT Protocols. Chest CT Protocols

Acknowledgments. A Specific Diagnostic Task: Lung Nodule Detection. A Specific Diagnostic Task: Chest CT Protocols. Chest CT Protocols Personalization of Pediatric Imaging in Terms of Needed Indication-Based Quality Per Dose Acknowledgments Duke University Medical Center Ehsan Samei, PhD Donald Frush, MD Xiang Li PhD DABR Cleveland Clinic

More information

A real-time interactive pulmonary nodule analysis system

A real-time interactive pulmonary nodule analysis system Clinical applications A real-time interactive pulmonary nodule analysis system E.J.R. van Beek B.F. Mullan B.H.Thomson Department of Radiology, Carver College of Medicine, University of Iowa, Iowa City,

More information

Detection of Pulmonary Nodules on CT and Volumetric Assessment of Change over Time

Detection of Pulmonary Nodules on CT and Volumetric Assessment of Change over Time Detection of Pulmonary Nodules on CT and Volumetric Assessment of Change over Time Margrit Betke 1 and Jane P. Ko 2 1 Computer Science Department Boston College, Chestnut Hill MA 02167, USA betke@oak.bc.edu

More information

I8 COMPLETION INSTRUCTIONS

I8 COMPLETION INSTRUCTIONS The I8 Form is completed for each screening exam at T0, T1, and T2. At T0 (baseline), the I8 Form documents comparison review of the baseline screen (DR Form) with any historical images available. At T1

More information

Effect of CT Image Compression on Computer-assisted Lung Nodule Volume Measurement 1

Effect of CT Image Compression on Computer-assisted Lung Nodule Volume Measurement 1 Computer Applications Radiology Jane P. Ko, MD Jeffrey Chang, MD Elan Bomsztyk, BS James S. Babb, PhD David P. Naidich, MD Henry Rusinek, PhD Published online before print 10.1148/radiol.2371041079 Radiology

More information

Proportion and characteristics of transient nodules in a retrospective analysis of pulmonary nodules

Proportion and characteristics of transient nodules in a retrospective analysis of pulmonary nodules Thoracic Cancer ISSN 1759-7706 ORIGINAL ARTICLE Proportion and characteristics of transient nodules in a retrospective analysis of pulmonary nodules Jin-Yeong Yu 1, Boram Lee 1, Sunmi Ju 1, Eun-Young Kim

More information

By choosing to view this document, you agree to all provisions of the copyright laws protecting it.

By choosing to view this document, you agree to all provisions of the copyright laws protecting it. Copyright 2009 IEEE. Reprinted from 31 st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2009. EMBC 2009. Sept. 2009. This material is posted here with permission

More information

Ryutaro Kakinuma 1,2,3, Yukio Muramatsu 1,4, Junta Yamamichi 1,5, Shiho Gomi 1,6, Estanislao Oubel 7, Noriyuki Moriyama 1,8.

Ryutaro Kakinuma 1,2,3, Yukio Muramatsu 1,4, Junta Yamamichi 1,5, Shiho Gomi 1,6, Estanislao Oubel 7, Noriyuki Moriyama 1,8. Original Article Evaluation of the 95% limits of agreement of the volumes of 5-year clinically stable solid nodules for the development of a follow-up system for indeterminate solid nodules in CT lung

More information

LUNG NODULES: MODERN MANAGEMENT STRATEGIES

LUNG NODULES: MODERN MANAGEMENT STRATEGIES Department of Radiology LUNG NODULES: MODERN MANAGEMENT STRATEGIES Christian J. Herold M.D. Department of Biomedical Imaging and Image-guided Therapy Medical University of Vienna Vienna, Austria Pulmonary

More information

Performance of computer-aided detection of pulmonary nodules in low-dose CT: comparison with double reading by nodule volume

Performance of computer-aided detection of pulmonary nodules in low-dose CT: comparison with double reading by nodule volume Eur Radiol (2012) 22:2076 2084 DOI 10.1007/s00330-012-2437-y CHEST Performance of computer-aided detection of pulmonary nodules in low-dose CT: comparison with double reading by nodule volume Yingru Zhao

More information

Predictive Data Mining for Lung Nodule Interpretation

Predictive Data Mining for Lung Nodule Interpretation Predictive Data Mining for Lung Nodule Interpretation William Horsthemke, Ekarin Varutbangkul, Daniela Raicu, Jacob Furst DePaul University, Chicago, IL USA {whorsthe,evarutba}@students.depaul.edu, {draicu,

More information

Projected Outcomes Using Different Nodule Sizes to Define a Positive CT Lung Cancer Screening Examination

Projected Outcomes Using Different Nodule Sizes to Define a Positive CT Lung Cancer Screening Examination DOI:10.1093/jnci/dju284 First published online October 20, 2014 The Author 2014. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com.

More information

Automated Detection System for Pulmonary Emphysema on 3D Chest Images

Automated Detection System for Pulmonary Emphysema on 3D Chest Images Automated Detection System for Pulmonary Emphysema on 3D Chest Images Takeshi Hara, Akira Yamamoto, Xiangrong Zhou, Shingo Iwano*, Shigeki Itoh*, Hiroshi Fujita, and Takeo Ishigaki* Department of Intelligent

More information

Lung Cancer Risk Associated With New Solid Nodules in the National Lung Screening Trial

Lung Cancer Risk Associated With New Solid Nodules in the National Lung Screening Trial Cardiopulmonary Imaging Original Research Pinsky et al. Lung Cancer Risk Associated With New Nodules Cardiopulmonary Imaging Original Research Paul F. Pinsky 1 David S. Gierada 2 P. Hrudaya Nath 3 Reginald

More information

Lung structure recognition: a further study of thoracic organ recognitions based on CT images

Lung structure recognition: a further study of thoracic organ recognitions based on CT images Lung structure recognition: a further study of thoracic organ recognitions based on CT images X. Zhou a, S. Kobayashi a, T. Hayashi a, N. Murata a, T. Hara a, H. Fujita a, R. Yokoyama b, T. Kiryu b, H.

More information

Clinical significance of noncalcified lung nodules in patients with breast cancer

Clinical significance of noncalcified lung nodules in patients with breast cancer Breast Cancer Res Treat (2016) 159:265 271 DOI 10.1007/s10549-016-3937-2 CLINICAL TRIAL Clinical significance of noncalcified lung nodules in patients with breast cancer Feng Li 1 Samuel G. Armato 1 Maryellen

More information

Adaptive Enhancement Technique for Cancerous Lung Nodule in Computed Tomography Images

Adaptive Enhancement Technique for Cancerous Lung Nodule in Computed Tomography Images Adaptive Enhancement Technique for Cancerous Lung Nodule in Computed Tomography Images Ayman A. AbuBaker Electrical and Computer Eng. Dept., Applied Science Private University, Shafa Badran, Amman, Jordan

More information

Small cell lung cancer (SCLC) is an aggressive malignancy

Small cell lung cancer (SCLC) is an aggressive malignancy BRIEF REPORT Characteristics and Outcomes of Small Cell Lung Cancer Patients Diagnosed During Two Lung Cancer Computed Tomographic Screening Programs in Heavy Smokers Sinead Cuffe, MD,* Teng Moua, MD,

More information

Computer Aided Diagnosis System for Lung Cancer Based on Helical CT Images

Computer Aided Diagnosis System for Lung Cancer Based on Helical CT Images Computer Aided Diagnosis System for Lung Cancer Based on Helical CT Images Y.Kawata I, K. Kanazawa 1 S. Toshioka 1, N.Niki ~1, H. Satoh 2, H. Ohmatsu 3, K. Eguchi 4, N. Moriyam a 3 l Dept. of Optical.

More information

Malignant solitary pulmonary nodules: assessment of mass growth rate and doubling time at follow-up CT

Malignant solitary pulmonary nodules: assessment of mass growth rate and doubling time at follow-up CT Original Article Malignant solitary pulmonary nodules: assessment of mass growth rate and doubling time at follow-up CT Jingxu Li*, Tingting Xia*, Xinguan Yang, Xiao Dong, Jiamin Liang, Nanshan Zhong,

More information

NODULE DETECTION IN LUNG INTERVENTION BY USING VDE AND MORPHOLOGY TECHNIQUES

NODULE DETECTION IN LUNG INTERVENTION BY USING VDE AND MORPHOLOGY TECHNIQUES INTERNATIONAL JOURNAL OF RESEARCH IN COMPUTER APPLICATIONS AND ROBOTICS ISSN 2320-7345 NODULE DETECTION IN LUNG INTERVENTION BY USING VDE AND MORPHOLOGY TECHNIQUES 1 C.M. Niranjana, ME, Department of Computer

More information

Lung Cancer Screening

Lung Cancer Screening Scan for mobile link. Lung Cancer Screening What is lung cancer screening? Screening examinations are tests performed to find disease before symptoms begin. The goal of screening is to detect disease at

More information

Extraction of tumor regions keeping boundary shape information from chest X-ray CT images and benign/malignant discrimination

Extraction of tumor regions keeping boundary shape information from chest X-ray CT images and benign/malignant discrimination Extraction of tumor regions keeping boundary shape information from chest X-ray CT images and benign/malignant discrimination Yasushi Hirano a, Jun-ichi Hasegawa b, Jun-ichiro Toriwaki a, Hironobu Ohmatsu

More information

Cardiopulmonary Imaging Original Research. T screening has increased the rate of detection of small nodules,

Cardiopulmonary Imaging Original Research. T screening has increased the rate of detection of small nodules, Cardiopulmonary Imaging Original Research Christe et al. CT of Lung Nodules Cardiopulmonary Imaging Original Research CT Screening and Follow-Up of Lung Nodules: Effects of Tube Current Time Setting and

More information

Fast lung nodule detection in chest CT images using cylindrical nodule-enhancement filter

Fast lung nodule detection in chest CT images using cylindrical nodule-enhancement filter Int J CARS (2013) 8:193 205 DOI 10.1007/s11548-012-0767-5 ORIGINAL ARTICLE Fast lung nodule detection in chest CT images using cylindrical nodule-enhancement filter Atsushi Teramoto Hiroshi Fujita Received:

More information

Automated Detection of Polyps from Multi-slice CT Images using 3D Morphologic Matching Algorithm: Phantom Study

Automated Detection of Polyps from Multi-slice CT Images using 3D Morphologic Matching Algorithm: Phantom Study Automated Detection of Polyps from Multi-slice CT Images using 3D Morphologic Matching Algorithm: Phantom Study Yonghum Na, Jin Sung Kim, Bruce R Whiting, K. Ty Bae Electronic Radiology Laboratory, Mallinckrodt

More information

Lung Cancer Screening

Lung Cancer Screening Scan for mobile link. Lung Cancer Screening What is lung cancer screening? Screening examinations are tests performed to find disease before symptoms begin. The goal of screening is to detect disease at

More information

With recent advances in diagnostic imaging technologies,

With recent advances in diagnostic imaging technologies, ORIGINAL ARTICLE Management of Ground-Glass Opacity Lesions Detected in Patients with Otherwise Operable Non-small Cell Lung Cancer Hong Kwan Kim, MD,* Yong Soo Choi, MD,* Kwhanmien Kim, MD,* Young Mog

More information

PULMONARY NODULES AND MASSES : DIAGNOSTIC APPROACH AND NEW MANAGEMENT GUIDELINES. https://tinyurl.com/hmpn2018

PULMONARY NODULES AND MASSES : DIAGNOSTIC APPROACH AND NEW MANAGEMENT GUIDELINES. https://tinyurl.com/hmpn2018 PULMONARY NODULES AND MASSES : DIAGNOSTIC APPROACH AND NEW MANAGEMENT GUIDELINES Heber MacMahon MB, BCh Department of Radiology The University of Chicago https://tinyurl.com/hmpn2018 Disclosures Consultant

More information

Lung Cancer Screening with Low-Dose Helical CT in Korea: Experiences at the Samsung Medical Center

Lung Cancer Screening with Low-Dose Helical CT in Korea: Experiences at the Samsung Medical Center J Korean Med Sci 2005; 20: 402-8 ISSN 1011-8934 Copyright The Korean Academy of Medical Sciences Lung Cancer Screening with Low-Dose Helical CT in Korea: Experiences at the Samsung Medical Center To determine

More information

Subsolid lung nodules, also termed ground-glass nodules

Subsolid lung nodules, also termed ground-glass nodules ORIGINAL ARTICLE Long-Term Surveillance of Ground-Glass Nodules Evidence from the MILD Trial Silva Mario, MD,* Sverzellati Nicola, MD, PhD,* Manna Carmelinda, MD,* Negrini Giulio, MD,* Marchianò Alfonso,

More information

doi: /

doi: / Yiting Xie ; Mingzhu Liang ; David F. Yankelevitz ; Claudia I. Henschke ; Anthony P. Reeves; Automated measurement of pulmonary artery in low-dose non-contrast chest CT images. Proc. SPIE 9414, Medical

More information

Prevent Cancer Foundation Quantitative Imaging Workshop XIII

Prevent Cancer Foundation Quantitative Imaging Workshop XIII Status of the Quantitative Imaging Profile Lung Nodule Volume Assessment and Monitoring in Low Dose CT Screening Prevent Cancer Foundation Quantitative Imaging Workshop XIII June 13-14, 2016 David S. Gierada,

More information

Pulmonary Nodules. Michael Morris, MD

Pulmonary Nodules. Michael Morris, MD Pulmonary Nodules Michael Morris, MD Case 45 year old healthy male Smokes socially Normal physical exam Pre-employment screening remote +PPD screening CXR nodular opacity Case 45 year old healthy male

More information

AN ALGORITHM FOR EARLY BREAST CANCER DETECTION IN MAMMOGRAMS

AN ALGORITHM FOR EARLY BREAST CANCER DETECTION IN MAMMOGRAMS AN ALGORITHM FOR EARLY BREAST CANCER DETECTION IN MAMMOGRAMS Isaac N. Bankman', William A. Christens-Barryl, Irving N. Weinberg2, Dong W. Kim3, Ralph D. Semmell, and William R. Brody2 The Johns Hopkins

More information

Automatic Ascending Aorta Detection in CTA Datasets

Automatic Ascending Aorta Detection in CTA Datasets Automatic Ascending Aorta Detection in CTA Datasets Stefan C. Saur 1, Caroline Kühnel 2, Tobias Boskamp 2, Gábor Székely 1, Philippe Cattin 1,3 1 Computer Vision Laboratory, ETH Zurich, 8092 Zurich, Switzerland

More information

Outcomes in the NLST. Health system infrastructure needs to implement screening

Outcomes in the NLST. Health system infrastructure needs to implement screening Outcomes in the NLST Health system infrastructure needs to implement screening Denise R. Aberle, MD Professor of Radiology and Bioengineering David Geffen School of Medicine at UCLA 1 Disclosures I have

More information

Learning Objectives. 1. Identify which patients meet criteria for annual lung cancer screening

Learning Objectives. 1. Identify which patients meet criteria for annual lung cancer screening Disclosure I, Taylor Rowlett, DO NOT have a financial interest /arrangement or affiliation with one or more organizations that could be perceived as a real or apparent conflict of interest in the context

More information

A Comprehensive Cancer Center Designated by the National Cancer Institute

A Comprehensive Cancer Center Designated by the National Cancer Institute N C I C C C A Comprehensive Cancer Center Designated by the National Cancer Institute Screening and Early Detection of Lung Cancer: Ready for Practice? David S. Ettinger, MD, FACP, FCCP Alex Grass Professor

More information

Copyright 2003 IEEE. Reprinted from IEEE Transactions on Medical Imaging, vol. 22, no. 10, pp , Oct

Copyright 2003 IEEE. Reprinted from IEEE Transactions on Medical Imaging, vol. 22, no. 10, pp , Oct Copyright 2003 IEEE. Reprinted from IEEE Transactions on Medical Imaging, vol. 22, no. 10, pp. 1259-1274, Oct. 2003. This material is posted here with permission of the IEEE. Such permission of the IEEE

More information

The use of low-dose thoracic computed tomography

The use of low-dose thoracic computed tomography ORIGINAL ARTICLE Lung Cancer Screening Using Multi-Slice Thin-Section Computed Tomography and Autofluorescence Bronchoscopy Annette M. McWilliams, MD,* John R. Mayo, MD, Myeong Im Ahn, MD, Sharyn L. S.

More information

Nodular Ground-Glass Opacities on Thin-section CT: Size Change during Follow-up and Pathological Results

Nodular Ground-Glass Opacities on Thin-section CT: Size Change during Follow-up and Pathological Results Nodular Ground-Glass Opacities on Thin-section CT: Size Change during Follow-up and Pathological Results Hyun Ju Lee, MD 1 Jin Mo Goo, MD 1 Chang Hyun Lee, MD 1 Chul-Gyu Yoo, MD 2 Young Tae Kim, MD 3 Jung-Gi

More information

Automatic recognition of lung lobes and fissures from multi-slice CT images

Automatic recognition of lung lobes and fissures from multi-slice CT images Automatic recognition of lung lobes and fissures from multi-slice CT images Xiangrong Zhou* a, Tatsuro Hayashi a, Takeshi Hara a, Hiroshi Fujita a, Ryujiro Yokoyama b, Takuji Kiryu b, Hiroaki Hoshi b a

More information

The lung cancer cure rate is dismal and has. The Effect of Tumor Size on Curability of Stage I Non-small Cell Lung Cancers*

The lung cancer cure rate is dismal and has. The Effect of Tumor Size on Curability of Stage I Non-small Cell Lung Cancers* The Effect of Tumor Size on Curability of Stage I Non-small Cell Lung Cancers* Juan P. Wisnivesky, MD, MPH; David Yankelevitz, MD; and Claudia I. Henschke, PhD, MD, FCCP Objective: The objective of this

More information

LUNG NODULE SEGMENTATION IN COMPUTED TOMOGRAPHY IMAGE. Hemahashiny, Ketheesan Department of Physical Science, Vavuniya Campus

LUNG NODULE SEGMENTATION IN COMPUTED TOMOGRAPHY IMAGE. Hemahashiny, Ketheesan Department of Physical Science, Vavuniya Campus LUNG NODULE SEGMENTATION IN COMPUTED TOMOGRAPHY IMAGE Hemahashiny, Ketheesan Department of Physical Science, Vavuniya Campus tketheesan@vau.jfn.ac.lk ABSTRACT: The key process to detect the Lung cancer

More information

MEDICAL POLICY SUBJECT: LOW-DOSE COMPUTED TOMOGRAPHY (LDCT) FOR LUNG CANCER SCREENING. POLICY NUMBER: CATEGORY: Technology Assessment

MEDICAL POLICY SUBJECT: LOW-DOSE COMPUTED TOMOGRAPHY (LDCT) FOR LUNG CANCER SCREENING. POLICY NUMBER: CATEGORY: Technology Assessment MEDICAL POLICY SUBJECT: LOW-DOSE COMPUTED CANCER SCREENING 05/18/05, 03/16/06, 12/21/06, 08/16/07, PAGE: 1 OF: 6 If a product excludes coverage for a service, it is not covered, and medical policy criteria

More information

A Breast Surgeon s Use of Three Dimensional Specimen Tomosynthesis

A Breast Surgeon s Use of Three Dimensional Specimen Tomosynthesis A Breast Surgeon s Use of Three Dimensional Specimen Tomosynthesis Cary S. Kaufman MD, FACS Associate Clinical Professor of Surgery A Breast Surgeon s Use of Three Dimensional Specimen Tomosynthesis Cary

More information

Comparison of three mathematical prediction models in patients with a solitary pulmonary nodule

Comparison of three mathematical prediction models in patients with a solitary pulmonary nodule Original Article Comparison of three mathematical prediction models in patients with a solitary pulmonary nodule Xuan Zhang*, Hong-Hong Yan, Jun-Tao Lin, Ze-Hua Wu, Jia Liu, Xu-Wei Cao, Xue-Ning Yang From

More information

Low-Dose CT: Clinical Studies & the Radiologist Perspective

Low-Dose CT: Clinical Studies & the Radiologist Perspective Low-Dose CT: Clinical Studies & the Radiologist Perspective RD-ASiR RD-MBIR SD-FBP RD=0.35 msv (80% dose reduction) Perry J. Pickhardt, MD UW School of Medicine & Public Health Low-Dose CT: Clinical Overview

More information

Cover Page. The handle holds various files of this Leiden University dissertation

Cover Page. The handle   holds various files of this Leiden University dissertation Cover Page The handle http://hdl.handle.net/1887/40114 holds various files of this Leiden University dissertation Author: Exter, Paul L. den Title: Diagnosis, management and prognosis of symptomatic and

More information

Early Detection of Lung Cancer

Early Detection of Lung Cancer Early Detection of Lung Cancer Aswathy N Iyer Dept Of Electronics And Communication Engineering Lymie Jose Dept Of Electronics And Communication Engineering Anumol Thomas Dept Of Electronics And Communication

More information

Characteristics of Subsolid Pulmonary Nodules Showing Growth During Follow-up With CT Scanning

Characteristics of Subsolid Pulmonary Nodules Showing Growth During Follow-up With CT Scanning CHEST Original Research Characteristics of Subsolid Pulmonary Nodules Showing Growth During Follow-up With CT Scanning Haruhisa Matsuguma, MD ; Kiyoshi Mori, MD ; Rie Nakahara, MD ; Haruko Suzuki, MD ;

More information

Pediatric High-Resolution Chest CT

Pediatric High-Resolution Chest CT Pediatric High-Resolution Chest CT Alan S. Brody, MD Professor of Radiology and Pediatrics Chief, Thoracic Imaging Cincinnati Children s s Hospital Cincinnati, Ohio, USA Pediatric High-Resolution CT Short

More information

Lung nodule volumetry: segmentation algorithms within the same software package cannot be used interchangeably

Lung nodule volumetry: segmentation algorithms within the same software package cannot be used interchangeably Eur Radiol (2010) 20: 1878 1885 DOI 10.1007/s00330-010-1749-z COMPUTED TOMOGRAPHY H. Ashraf B. de Hoop S. B. Shaker A. Dirksen K. S. Bach H. Hansen M. Prokop J. H. Pedersen Lung nodule volumetry: segmentation

More information