Memory-Augmented Active Deep Learning for Identifying Relations Between Distant Medical Concepts in Electroencephalography Reports

Size: px
Start display at page:

Download "Memory-Augmented Active Deep Learning for Identifying Relations Between Distant Medical Concepts in Electroencephalography Reports"

Transcription

1 Memory-Augmented Active Deep Learning for Identifying Relations Between Distant Medical Concepts in Electroencephalography Reports Ramon Maldonado, BS, Travis Goodwin, PhD Sanda M. Harabagiu, PhD The University of Texas at Dallas Human Language Technology Research Institute travis, sanda}

2 Conflicts There are no conflicts of interest

3 Outline 1. Introduction 2. The data 3. Memory-Augmented Active Deep Learning 4. EEG-RelNet for long distance relation detection 5. Experimental Results 6. Conclusion

4 Introduction Clinical electroencephalography (EEG) is the most important investigation in the diagnosis and management of epilepsies. As more clinical EEG becomes available, the interpretation of EEG signals can be improved by providing neurologists with results of search for patients that exhibit similar EEG characteristics. MERCuRY (Multi-modal ElectroencephalogRam patient Cohort discovery) - Goodwin & Harabagiu (2016) 1 for cohort identification

5 Introduction QUERY: Patients with shifting arrhythmic delta suspected of underlying cerebrovascular disease EXAMPLE RECORD: CLINICAL HISTORY: 55 y/o man admitted for change in mental status, with a past medical history of GI bleed, anemia, encephalopathy, and others. MEDICATIONS: Pantoprazole, Folic Acid, Carvedilol DESCRIPTION OF THE RECORD: The background EEG is characterized by slowing and disorganization. There is prominent shifting arrhythmic delta activity more prominent in the left mid to anterior temporal region. Photic stimulation generates scant driving. IMPRESSION: Abnormal EEG due to: 1. Marked background slowing and disorganization; 2. Some arrhythmic delta activity CLINICAL CORRELATION: These findings are supportive of a bihemispheric disturbance of cerebral function. These are nonspecific findings which can be seen in a toxic and metabolic encephalopathy and/or underlying cerebrovascular disease

6 Introduction Current state-of-the-art relation identification methods require arguments to be in the same sentence Our method operates on pairs of concepts from the same EEG reports not constrained to appear in the same sentence/section Accurate relations enable higher quality Medical Knowledge Embeddings (MKE) (Maldonado et al., 2017) Capture knowledge from a large corpus of EEG reports using deep learning Represent concepts and relations as low-dimensional vectors Vector representation helps resolve semantic heterogeneity from differences in terminology

7 Introduction EEG-RelNet Extension of RelNet from Bansal, Neelakantan, & McCallum (2017) Processes entire EEG report to model cross-sentence relations Memory-augmented neural network with abstract memory cells Concept memory cells Relation memory cells Memories implicitly model current knowledge about medical concepts and their relations in the EEG report

8 Outline 1. Introduction 2. The data 3. Memory-Augmented Active Deep Learning 4. EEG-RelNet for long distance relation detection 5. Experimental Results 6. Conclusion

9 The Data EEG reports from Temple University Hospital (TUH) 25,000 reports from 15,000 patients collected over 12 years Sections: 1. Clinical History: Lists past and current medical problems, symptoms, signs, and treatments as well as significant medical events. 2. Medications 3. Introduction: depiction of the techniques used for the EEG 4. Description: a complete and objective description of the EEG, noting all observed activity, patterns, and events 5. Impression: states whether the EEG test is normal or abnormal and, if abnormal, lists the abnormalities in order of importance 6. Clinical Correlation: explains what the EEG findings mean in terms of clinical interpretation

10 The Data - Preprocessing Multi-Task Active Deep Learning system for concept detection & attribute classification (Maldonado et. al 2017) EEG activities, EEG events, medical problems, treatments Medical concept attributes Modality Polarity Medical Concept Type 16 EEG activity attributes (morphology, dispersal, location, etc.) 365,218 concepts with 3,062,846 attributes Normalization UMLS for medical problems and treatments 10 EEG event types EEG activities are normalized by morphology attribute

11 Outline 1. Introduction 2. The data 3. Memory-Augmented Active Deep Learning 4. EEG-RelNet for long distance relation detection 5. Experimental Results 6. Conclusion

12 Memory-Augmented Active Deep Learning The purpose of the Memory-Augmented Active Deep Learning (MAADL) system is to automatically identify relations between pairs of medical concepts in EEG reports, regardless of how distant they are. The MAADL Paradigm consists of 5 steps: STEP 1: The development of an annotation schema STEP 2: Annotation of initial training data STEP 3: Design of deep learning method capable of learning from the data STEP 4: Development of sampling methods for MAADL STEP 5: Usage of the Active Learning system involving: STEP 5.a: Accepting/Editing annotations of sampled examples STEP 5.b: Re-training the deep learning model

13 MAADL Annotation Schema Three relation types: EVIDENCES, EVOKES, TREATMENT-FOR 1 EVIDENCES 2 EVOKES EEG event EEG activity medical problem treatment medical problem EEG event EEG activity medical problem treatment EEG activity 3 TREATMENT FOR treatment medical problem

14 Memory-Augmented Active Deep Learning EEG Reports Deep Learning-Based Identification of medical concepts + their attributes Automatically recognized Relations between medical concepts Active Learning Loop STEP 4 EEG Report Annotation SAMPLING STEP 1 STEP 2 Initial Training Data Manual Annotation of Relations between Medical Concepts. Relation types: EVIDENCES EVOKES TREATMENT-FOR EEG Reports with Seed Annotations of Relations between Medical Concepts STEP 3 Deep Learning-Based Recognition of Relations EEG-RelNet Relational Memories STEP 5 Validation/ Editing of Sampled Annotations of Relations in EEG Reports Re-Training Data

15 Outline 1. Introduction 2. The data 3. Memory-Augmented Active Deep Learning 4. EEG-RelNet for long distance relation detection 5. Experimental Results 6. Conclusion

16 EEG-RelNet EEG-RelNet Operates on the full text of an EEG report Considers each pair of medical concepts identified in the report Detects EVIDENCES, EVOKES, and TREATMENT-FOR relations between any pair of concepts 3 modules Input Encoding Module encodes the report into concept- and sentence-level embedding vectors Dynamic Relational Memory maintains and updates 2 sets of hidden states (memories) to accumulate information about each concept and potential relation Output Module feeds the updated memories to prediction layer

17 EEG-RelNet Input Encoding Module Learn an embedding c i R N for each medical concept c i in the report c i = W C c, a 1 c i,, a A c i c is the normalized concept name embedding a 1 c i,, a A c i are the attribute embeddings for concept c i Learn an embedding s i R N for each sentence s i by combining word embeddings e j for each word w j in sentence s i s i = σ j m f j e j f 1, f m is a learned positional mask e j = c i if word w j corresponds to concept c i

18 EEG-RelNet Dynamic Relational Memory (DRM) Module To account for long-distance relations, we use the DRM Module to keep track of the interactions between the medical concepts in each report The DRM for a report with d concepts consists of: d Concept Memories which accumulate information about each concept d(d 1) Relation Memories which accumulate information about the potential relations between each pair of concepts

19 EEG-RelNet c Concept Memory Cell Relation Memory Cell c Concept Memory Cell c Concept Memory Cell c c Concept Memory Cell Concept Memory Cell Relation Memory Cell Relation Memory Cell Relation Memory Cell Relation Memory Cell c c Concept Memory Cell Concept Memory Cell Relational Memory c c Concept Memory Cell Concept Memory Cell Relational Memory s s s

20 EEG-RelNet Concept Memory h i is updated as follows: i c = s k, h i + c i i + i h i = φ W u h i + W v c i + W s s k h i h i + i c h i c i i s Relation Memory r i is updated as follows: c c ij = i j s k, r ij ij + i r ij = φ W A r ij + W B s k r ij r ij + ij r ij j ij ij s

21 EEG-RelNet Output Module Identifies the relation (if any) between any pair of medical concepts from the report using the updated DRM after processing each sentence in the report To determine the relation between concepts c i and c j 1. We pass the concept memories h i and h j along with the relation memory r ij to a fully connected PReLU layer: q ij = φ W q h i, h j, r ij ; 2. Then softmax: R ij = softmax φ W z q ij. 3. The predicted relation type is R ij = argmax t R t ij

22 Outline 1. Introduction 2. The data 3. Memory-Augmented Active Deep Learning 4. EEG-RelNet for long distance relation detection 5. Experimental Results 6. Conclusion

23 Experimental Results To measure the impact of the EEG-RelNet architecture, we compare against: 1. EEG-RelNet_NRM: a configuration of EEG-RelNet with no relation memories (i.e. q ij = φ W q h i, h j ) 2. EEG-RelNet_NA: a configuration of EEG-RelNet that ignores medical concept attributes (i.e. c i = c) 3. A Heuristic baseline: a high-recall, rule-based method from our previous work using concept type and section information to relate concepts deterministically We use 5-fold cross validation on the full set of 140 manually annotated EEG reports selected via active learning containing 1513 relations between 3691 medical concepts

24 Experimental Results The performance of the MAADL system for detecting relations between medical concepts in EEG reports

25 Experimental Results Active Learning Learning Curves shown for the first 100 EEG reports annotated and evaluated with F 1 measure.

26 Experimental Results - Discussion Best performance for EVOKES relations vs (TREATMENT-FOR), (EVIDENCES) EVOKES always involves an EEG Activity EEG activities have a richer representation Context is often clearer for EVOKES relations Could use existing ontologies to inform medical problem and treatment concepts (e.g. TREATMENT-FOR(Lamictal, seizure)) TREATMENT-FOR relations have high recall and low precision Most common treatments (medications) have uninformative context Improves markedly as AL progresses

27 Outline 1. Introduction 2. The data 3. Memory-Augmented Active Deep Learning 4. EEG-RelNet for long distance relation detection 5. Experimental Results 6. Conclusion

28 Conclusion In this work, we presented a novel active deep learning framework for identifying relations between medical concepts in EEG reports. EEG-RelNet: a novel deep neural architecture capable of inferring relations between medical concepts not mentioned in the same sentence or section To our knowledge, this is the first method capable of detecting relations between distant medical concepts in medical narratives Updates a set of memories that accumulate information about each concept and potential relation in the EEG report Experimental results show promise Future work Incorporate outside knowledge to improve representation of medical problems/treatments Use MAADL system to improve Medical Knowledge Embeddings for epilepsy

29 Acknowledgements Research reported in this publication was supported by the National Human Genome Research Institute of the National Institutes of Health under award number 1U01HG The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health.

30 Questions

Memory-Augmented Active Deep Learning for Identifying Relations Between Distant Medical Concepts in Electroencephalography Reports

Memory-Augmented Active Deep Learning for Identifying Relations Between Distant Medical Concepts in Electroencephalography Reports Memory-Augmented Active Deep Learning for Identifying Relations Between Distant Medical s in Electroencephalography Reports Abstract Ramon Maldonado, BS, Travis R. Goodwin, MS, Sanda M. Harabagiu, PhD

More information

Multi-modal Patient Cohort Identification from EEG Report and Signal Data

Multi-modal Patient Cohort Identification from EEG Report and Signal Data Multi-modal Patient Cohort Identification from EEG Report and Signal Data Travis R. Goodwin and Sanda M. Harabagiu The University of Texas at Dallas Human Language Technology Research Institute http://www.hlt.utdallas.edu

More information

Inferring Clinical Correlations from EEG Reports with Deep Neural Learning

Inferring Clinical Correlations from EEG Reports with Deep Neural Learning Inferring Clinical Correlations from EEG Reports with Deep Neural Learning Methods for Identification, Classification, and Association using EHR Data S23 Travis R. Goodwin (Presenter) & Sanda M. Harabagiu

More information

arxiv: v1 [cs.lg] 4 Feb 2019

arxiv: v1 [cs.lg] 4 Feb 2019 Machine Learning for Seizure Type Classification: Setting the benchmark Subhrajit Roy [000 0002 6072 5500], Umar Asif [0000 0001 5209 7084], Jianbin Tang [0000 0001 5440 0796], and Stefan Harrer [0000

More information

Motivation: Attention: Focusing on specific parts of the input. Inspired by neuroscience.

Motivation: Attention: Focusing on specific parts of the input. Inspired by neuroscience. Outline: Motivation. What s the attention mechanism? Soft attention vs. Hard attention. Attention in Machine translation. Attention in Image captioning. State-of-the-art. 1 Motivation: Attention: Focusing

More information

ELECTROENCEPHALOGRAPHIC SLOWING: A PRIMARY SOURCE OF ERROR IN AUTOMATIC SEIZURE DETECTION

ELECTROENCEPHALOGRAPHIC SLOWING: A PRIMARY SOURCE OF ERROR IN AUTOMATIC SEIZURE DETECTION ELECTROENCEPHALOGRAPHIC SLOWING: A PRIMARY SOURCE OF ERROR IN AUTOMATIC SEIZURE DETECTION E. von Weltin, T. Ahsan, V. Shah, D. Jamshed, M. Golmohammadi, I. Obeid and J. Picone Neural Engineering Data Consortium,

More information

Text mining for lung cancer cases over large patient admission data. David Martinez, Lawrence Cavedon, Zaf Alam, Christopher Bain, Karin Verspoor

Text mining for lung cancer cases over large patient admission data. David Martinez, Lawrence Cavedon, Zaf Alam, Christopher Bain, Karin Verspoor Text mining for lung cancer cases over large patient admission data David Martinez, Lawrence Cavedon, Zaf Alam, Christopher Bain, Karin Verspoor Opportunities for Biomedical Informatics Increasing roll-out

More information

DeepASL: Enabling Ubiquitous and Non-Intrusive Word and Sentence-Level Sign Language Translation

DeepASL: Enabling Ubiquitous and Non-Intrusive Word and Sentence-Level Sign Language Translation DeepASL: Enabling Ubiquitous and Non-Intrusive Word and Sentence-Level Sign Language Translation Biyi Fang Michigan State University ACM SenSys 17 Nov 6 th, 2017 Biyi Fang (MSU) Jillian Co (MSU) Mi Zhang

More information

A Predictive Chronological Model of Multiple Clinical Observations T R A V I S G O O D W I N A N D S A N D A M. H A R A B A G I U

A Predictive Chronological Model of Multiple Clinical Observations T R A V I S G O O D W I N A N D S A N D A M. H A R A B A G I U A Predictive Chronological Model of Multiple Clinical Observations T R A V I S G O O D W I N A N D S A N D A M. H A R A B A G I U T H E U N I V E R S I T Y O F T E X A S A T D A L L A S H U M A N L A N

More information

Case-based reasoning using electronic health records efficiently identifies eligible patients for clinical trials

Case-based reasoning using electronic health records efficiently identifies eligible patients for clinical trials Case-based reasoning using electronic health records efficiently identifies eligible patients for clinical trials Riccardo Miotto and Chunhua Weng Department of Biomedical Informatics Columbia University,

More information

OPTIMIZING CHANNEL SELECTION FOR SEIZURE DETECTION

OPTIMIZING CHANNEL SELECTION FOR SEIZURE DETECTION OPTIMIZING CHANNEL SELECTION FOR SEIZURE DETECTION V. Shah, M. Golmohammadi, S. Ziyabari, E. Von Weltin, I. Obeid and J. Picone Neural Engineering Data Consortium, Temple University, Philadelphia, Pennsylvania,

More information

Formulating Emotion Perception as a Probabilistic Model with Application to Categorical Emotion Classification

Formulating Emotion Perception as a Probabilistic Model with Application to Categorical Emotion Classification Formulating Emotion Perception as a Probabilistic Model with Application to Categorical Emotion Classification Reza Lotfian and Carlos Busso Multimodal Signal Processing (MSP) lab The University of Texas

More information

Intelligent Machines That Act Rationally. Hang Li Toutiao AI Lab

Intelligent Machines That Act Rationally. Hang Li Toutiao AI Lab Intelligent Machines That Act Rationally Hang Li Toutiao AI Lab Four Definitions of Artificial Intelligence Building intelligent machines (i.e., intelligent computers) Thinking humanly Acting humanly Thinking

More information

A Probabilistic Reasoning Method for Predicting the Progression of Clinical Findings from Electronic Medical Records

A Probabilistic Reasoning Method for Predicting the Progression of Clinical Findings from Electronic Medical Records A Probabilistic Reasoning Method for Predicting the Progression of Clinical Findings from Electronic Medical Records Travis Goodwin, Sanda M. Harabagiu, PhD University of Texas at Dallas, Richardson, TX,

More information

Extracting geographic locations from the literature for virus phylogeography using supervised and distant supervision methods

Extracting geographic locations from the literature for virus phylogeography using supervised and distant supervision methods Extracting geographic locations from the literature for virus phylogeography using supervised and distant supervision methods D. Weissenbacher 1, A. Sarker 2, T. Tahsin 1, G. Gonzalez 2 and M. Scotch 1

More information

Intelligent Machines That Act Rationally. Hang Li Bytedance AI Lab

Intelligent Machines That Act Rationally. Hang Li Bytedance AI Lab Intelligent Machines That Act Rationally Hang Li Bytedance AI Lab Four Definitions of Artificial Intelligence Building intelligent machines (i.e., intelligent computers) Thinking humanly Acting humanly

More information

Convolutional Neural Networks for Text Classification

Convolutional Neural Networks for Text Classification Convolutional Neural Networks for Text Classification Sebastian Sierra MindLab Research Group July 1, 2016 ebastian Sierra (MindLab Research Group) NLP Summer Class July 1, 2016 1 / 32 Outline 1 What is

More information

The Impact of Belief Values on the Identification of Patient Cohorts

The Impact of Belief Values on the Identification of Patient Cohorts The Impact of Belief Values on the Identification of Patient Cohorts Travis Goodwin, Sanda M. Harabagiu Human Language Technology Research Institute University of Texas at Dallas Richardson TX, 75080 {travis,sanda}@hlt.utdallas.edu

More information

Extraction of Adverse Drug Effects from Clinical Records

Extraction of Adverse Drug Effects from Clinical Records MEDINFO 2010 C. Safran et al. (Eds.) IOS Press, 2010 2010 IMIA and SAHIA. All rights reserved. doi:10.3233/978-1-60750-588-4-739 739 Extraction of Adverse Drug Effects from Clinical Records Eiji Aramaki

More information

Audiovisual to Sign Language Translator

Audiovisual to Sign Language Translator Technical Disclosure Commons Defensive Publications Series July 17, 2018 Audiovisual to Sign Language Translator Manikandan Gopalakrishnan Follow this and additional works at: https://www.tdcommons.org/dpubs_series

More information

Rumor Detection on Twitter with Tree-structured Recursive Neural Networks

Rumor Detection on Twitter with Tree-structured Recursive Neural Networks 1 Rumor Detection on Twitter with Tree-structured Recursive Neural Networks Jing Ma 1, Wei Gao 2, Kam-Fai Wong 1,3 1 The Chinese University of Hong Kong 2 Victoria University of Wellington, New Zealand

More information

Rolls,E.T. (2016) Cerebral Cortex: Principles of Operation. Oxford University Press.

Rolls,E.T. (2016) Cerebral Cortex: Principles of Operation. Oxford University Press. Digital Signal Processing and the Brain Is the brain a digital signal processor? Digital vs continuous signals Digital signals involve streams of binary encoded numbers The brain uses digital, all or none,

More information

Deep Learning based Information Extraction Framework on Chinese Electronic Health Records

Deep Learning based Information Extraction Framework on Chinese Electronic Health Records Deep Learning based Information Extraction Framework on Chinese Electronic Health Records Bing Tian Yong Zhang Kaixin Liu Chunxiao Xing RIIT, Beijing National Research Center for Information Science and

More information

Automatic Context-Aware Image Captioning

Automatic Context-Aware Image Captioning Technical Disclosure Commons Defensive Publications Series May 23, 2017 Automatic Context-Aware Image Captioning Sandro Feuz Sebastian Millius Follow this and additional works at: http://www.tdcommons.org/dpubs_series

More information

Artificial Neural Networks (Ref: Negnevitsky, M. Artificial Intelligence, Chapter 6)

Artificial Neural Networks (Ref: Negnevitsky, M. Artificial Intelligence, Chapter 6) Artificial Neural Networks (Ref: Negnevitsky, M. Artificial Intelligence, Chapter 6) BPNN in Practice Week 3 Lecture Notes page 1 of 1 The Hopfield Network In this network, it was designed on analogy of

More information

Language to Logical Form with Neural Attention

Language to Logical Form with Neural Attention Language to Logical Form with Neural Attention August 8, 2016 Li Dong and Mirella Lapata Semantic Parsing Transform natural language to logical form Human friendly -> computer friendly What is the highest

More information

Medical Knowledge Attention Enhanced Neural Model. for Named Entity Recognition in Chinese EMR

Medical Knowledge Attention Enhanced Neural Model. for Named Entity Recognition in Chinese EMR Medical Knowledge Attention Enhanced Neural Model for Named Entity Recognition in Chinese EMR Zhichang Zhang, Yu Zhang, Tong Zhou College of Computer Science and Engineering, Northwest Normal University,

More information

Learning the Fine-Grained Information Status of Discourse Entities

Learning the Fine-Grained Information Status of Discourse Entities Learning the Fine-Grained Information Status of Discourse Entities Altaf Rahman and Vincent Ng Human Language Technology Research Institute The University of Texas at Dallas Plan for the talk What is Information

More information

An Edge-Device for Accurate Seizure Detection in the IoT

An Edge-Device for Accurate Seizure Detection in the IoT An Edge-Device for Accurate Seizure Detection in the IoT M. A. Sayeed 1, S. P. Mohanty 2, E. Kougianos 3, and H. Zaveri 4 University of North Texas, Denton, TX, USA. 1,2,3 Yale University, New Haven, CT,

More information

PMR5406 Redes Neurais e Lógica Fuzzy. Aula 5 Alguns Exemplos

PMR5406 Redes Neurais e Lógica Fuzzy. Aula 5 Alguns Exemplos PMR5406 Redes Neurais e Lógica Fuzzy Aula 5 Alguns Exemplos APPLICATIONS Two examples of real life applications of neural networks for pattern classification: RBF networks for face recognition FF networks

More information

Learning Convolutional Neural Networks for Graphs

Learning Convolutional Neural Networks for Graphs GA-65449 Learning Convolutional Neural Networks for Graphs Mathias Niepert Mohamed Ahmed Konstantin Kutzkov NEC Laboratories Europe Representation Learning for Graphs Telecom Safety Transportation Industry

More information

Assessing Functional Neural Connectivity as an Indicator of Cognitive Performance *

Assessing Functional Neural Connectivity as an Indicator of Cognitive Performance * Assessing Functional Neural Connectivity as an Indicator of Cognitive Performance * Brian S. Helfer 1, James R. Williamson 1, Benjamin A. Miller 1, Joseph Perricone 1, Thomas F. Quatieri 1 MIT Lincoln

More information

Recognizing Scenes by Simulating Implied Social Interaction Networks

Recognizing Scenes by Simulating Implied Social Interaction Networks Recognizing Scenes by Simulating Implied Social Interaction Networks MaryAnne Fields and Craig Lennon Army Research Laboratory, Aberdeen, MD, USA Christian Lebiere and Michael Martin Carnegie Mellon University,

More information

Standardize and Optimize. Trials and Drug Development

Standardize and Optimize. Trials and Drug Development Informatics Infrastructure to Standardize and Optimize Quantitative Imaging in Clinical Trials and Drug Development Daniel L. Rubin, MD, MS Assistant Professor of Radiology Member, Stanford Cancer Center

More information

Biceps Activity EMG Pattern Recognition Using Neural Networks

Biceps Activity EMG Pattern Recognition Using Neural Networks Biceps Activity EMG Pattern Recognition Using eural etworks K. Sundaraj University Malaysia Perlis (UniMAP) School of Mechatronic Engineering 0600 Jejawi - Perlis MALAYSIA kenneth@unimap.edu.my Abstract:

More information

5th Mini-Symposium on Cognition, Decision-making and Social Function: In Memory of Kang Cheng

5th Mini-Symposium on Cognition, Decision-making and Social Function: In Memory of Kang Cheng 5th Mini-Symposium on Cognition, Decision-making and Social Function: In Memory of Kang Cheng 13:30-13:35 Opening 13:30 17:30 13:35-14:00 Metacognition in Value-based Decision-making Dr. Xiaohong Wan (Beijing

More information

Direct memory access using two cues: Finding the intersection of sets in a connectionist model

Direct memory access using two cues: Finding the intersection of sets in a connectionist model Direct memory access using two cues: Finding the intersection of sets in a connectionist model Janet Wiles, Michael S. Humphreys, John D. Bain and Simon Dennis Departments of Psychology and Computer Science

More information

Incorporation of Imaging-Based Functional Assessment Procedures into the DICOM Standard Draft version 0.1 7/27/2011

Incorporation of Imaging-Based Functional Assessment Procedures into the DICOM Standard Draft version 0.1 7/27/2011 Incorporation of Imaging-Based Functional Assessment Procedures into the DICOM Standard Draft version 0.1 7/27/2011 I. Purpose Drawing from the profile development of the QIBA-fMRI Technical Committee,

More information

A HMM-based Pre-training Approach for Sequential Data

A HMM-based Pre-training Approach for Sequential Data A HMM-based Pre-training Approach for Sequential Data Luca Pasa 1, Alberto Testolin 2, Alessandro Sperduti 1 1- Department of Mathematics 2- Department of Developmental Psychology and Socialisation University

More information

Sentiment Analysis of Reviews: Should we analyze writer intentions or reader perceptions?

Sentiment Analysis of Reviews: Should we analyze writer intentions or reader perceptions? Sentiment Analysis of Reviews: Should we analyze writer intentions or reader perceptions? Isa Maks and Piek Vossen Vu University, Faculty of Arts De Boelelaan 1105, 1081 HV Amsterdam e.maks@vu.nl, p.vossen@vu.nl

More information

Machine Reading for Question Answering: from symbolic to neural computation. Jianfeng Gao, Rangan Majumder and Bill Dolan Microsoft AI & R 7/17/2017

Machine Reading for Question Answering: from symbolic to neural computation. Jianfeng Gao, Rangan Majumder and Bill Dolan Microsoft AI & R 7/17/2017 Machine Reading for Question Answering: from symbolic to neural computation Jianfeng Gao, Rangan Majumder and Bill Dolan Microsoft AI & R 7/17/2017 Outline Symbolic approaches to QA Knowledge representation

More information

ERA: Architectures for Inference

ERA: Architectures for Inference ERA: Architectures for Inference Dan Hammerstrom Electrical And Computer Engineering 7/28/09 1 Intelligent Computing In spite of the transistor bounty of Moore s law, there is a large class of problems

More information

SVM-based Discriminative Accumulation Scheme for Place Recognition

SVM-based Discriminative Accumulation Scheme for Place Recognition SVM-based Discriminative Accumulation Scheme for Place Recognition Andrzej Pronobis CAS/CVAP, KTH Stockholm, Sweden pronobis@csc.kth.se Óscar Martínez Mozos AIS, University Of Freiburg Freiburg, Germany

More information

AMERICAN BOARD OF CLINICAL NEUROPHYSIOLOGY

AMERICAN BOARD OF CLINICAL NEUROPHYSIOLOGY AMERICAN BOARD OF CLINICAL NEUROPHYSIOLOGY Part I Content Outline I. Physiology and Instrumentation 30% A. Physiology 1. Anatomy of neural generation 2. Mechanisms of EEG and evoked potential generation

More information

GIANT: Geo-Informative Attributes for Location Recognition and Exploration

GIANT: Geo-Informative Attributes for Location Recognition and Exploration GIANT: Geo-Informative Attributes for Location Recognition and Exploration Quan Fang, Jitao Sang, Changsheng Xu Institute of Automation, Chinese Academy of Sciences October 23, 2013 Where is this? La Sagrada

More information

A Descriptive Delta for Identifying Changes in SNOMED CT

A Descriptive Delta for Identifying Changes in SNOMED CT A Descriptive Delta for Identifying Changes in SNOMED CT Christopher Ochs, Yehoshua Perl, Gai Elhanan Department of Computer Science New Jersey Institute of Technology Newark, NJ, USA {cro3, perl, elhanan}@njit.edu

More information

Why did the network make this prediction?

Why did the network make this prediction? Why did the network make this prediction? Ankur Taly (Google Inc.) Joint work with Mukund Sundararajan and Qiqi Yan Some Deep Learning Successes Source: https://www.cbsinsights.com Deep Neural Networks

More information

M.Sc. in Cognitive Systems. Model Curriculum

M.Sc. in Cognitive Systems. Model Curriculum M.Sc. in Cognitive Systems Model Curriculum April 2014 Version 1.0 School of Informatics University of Skövde Sweden Contents 1 CORE COURSES...1 2 ELECTIVE COURSES...1 3 OUTLINE COURSE SYLLABI...2 Page

More information

A Simple Pipeline Application for Identifying and Negating SNOMED CT in Free Text

A Simple Pipeline Application for Identifying and Negating SNOMED CT in Free Text A Simple Pipeline Application for Identifying and Negating SNOMED CT in Free Text Anthony Nguyen 1, Michael Lawley 1, David Hansen 1, Shoni Colquist 2 1 The Australian e-health Research Centre, CSIRO ICT

More information

CSE Introduction to High-Perfomance Deep Learning ImageNet & VGG. Jihyung Kil

CSE Introduction to High-Perfomance Deep Learning ImageNet & VGG. Jihyung Kil CSE 5194.01 - Introduction to High-Perfomance Deep Learning ImageNet & VGG Jihyung Kil ImageNet Classification with Deep Convolutional Neural Networks Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton,

More information

Distillation of Knowledge from the Research Literatures on Alzheimer s Dementia

Distillation of Knowledge from the Research Literatures on Alzheimer s Dementia JSCI 2017 1 Distillation of Knowledge from the Research Literatures on Alzheimer s Dementia Wutthipong Kongburan, Mark Chignell, and Jonathan H. Chan School of Information Technology King Mongkut's University

More information

Applying Data Mining for Epileptic Seizure Detection

Applying Data Mining for Epileptic Seizure Detection Applying Data Mining for Epileptic Seizure Detection Ying-Fang Lai 1 and Hsiu-Sen Chiang 2* 1 Department of Industrial Education, National Taiwan Normal University 162, Heping East Road Sec 1, Taipei,

More information

CROWD ANALYTICS VIA ONE SHOT LEARNING AND AGENT BASED INFERENCE. Peter Tu, Ming-Ching Chang, Tao Gao. GE Global Research

CROWD ANALYTICS VIA ONE SHOT LEARNING AND AGENT BASED INFERENCE. Peter Tu, Ming-Ching Chang, Tao Gao. GE Global Research CROWD ANALYTICS VIA ONE SHOT LEARNING AND AGENT BASED INFERENCE Peter Tu, Ming-Ching Chang, Tao Gao GE Global Research ABSTRACT For the purposes of inferring social behavior in crowded conditions, three

More information

CHAPTER 6 HUMAN BEHAVIOR UNDERSTANDING MODEL

CHAPTER 6 HUMAN BEHAVIOR UNDERSTANDING MODEL 127 CHAPTER 6 HUMAN BEHAVIOR UNDERSTANDING MODEL 6.1 INTRODUCTION Analyzing the human behavior in video sequences is an active field of research for the past few years. The vital applications of this field

More information

AI Support for Communication Disabilities. Shaun Kane University of Colorado Boulder

AI Support for Communication Disabilities. Shaun Kane University of Colorado Boulder AI Support for Communication Disabilities Shaun Kane University of Colorado Boulder Augmentative and Alternative Communication (AAC) AAC Any tool to replace or supplement spoken and written communication

More information

A Framework for Conceptualizing, Representing, and Analyzing Distributed Interaction. Dan Suthers

A Framework for Conceptualizing, Representing, and Analyzing Distributed Interaction. Dan Suthers 1 A Framework for Conceptualizing, Representing, and Analyzing Distributed Interaction Dan Suthers Work undertaken with Nathan Dwyer, Richard Medina and Ravi Vatrapu Funded in part by the U.S. National

More information

Highly Accurate Brain Stroke Diagnostic System and Generative Lesion Model. Junghwan Cho, Ph.D. CAIDE Systems, Inc. Deep Learning R&D Team

Highly Accurate Brain Stroke Diagnostic System and Generative Lesion Model. Junghwan Cho, Ph.D. CAIDE Systems, Inc. Deep Learning R&D Team Highly Accurate Brain Stroke Diagnostic System and Generative Lesion Model Junghwan Cho, Ph.D. CAIDE Systems, Inc. Deep Learning R&D Team Established in September, 2016 at 110 Canal st. Lowell, MA 01852,

More information

Graphical Induction of Qualified Medical Knowledge

Graphical Induction of Qualified Medical Knowledge International Journal of Semantic Computing c World Scientific Publishing Company Graphical Induction of Qualified Medical Knowledge Travis Goodwin & Sanda M. Harabagiu Human Language Technology Research

More information

arxiv: v2 [cs.cv] 19 Dec 2017

arxiv: v2 [cs.cv] 19 Dec 2017 An Ensemble of Deep Convolutional Neural Networks for Alzheimer s Disease Detection and Classification arxiv:1712.01675v2 [cs.cv] 19 Dec 2017 Jyoti Islam Department of Computer Science Georgia State University

More information

On the Use of Brainprints as Passwords

On the Use of Brainprints as Passwords 9/24/2015 2015 Global Identity Summit (GIS) 1 On the Use of Brainprints as Passwords Zhanpeng Jin Department of Electrical and Computer Engineering Department of Biomedical Engineering Binghamton University,

More information

A hierarchical modeling approach to data analysis and study design in a multi-site experimental fmri study

A hierarchical modeling approach to data analysis and study design in a multi-site experimental fmri study A hierarchical modeling approach to data analysis and study design in a multi-site experimental fmri study Bo Zhou Department of Statistics University of California, Irvine Sep. 13, 2012 1 / 23 Outline

More information

Semantic Structure of the Indian Sign Language

Semantic Structure of the Indian Sign Language Semantic Structure of the Indian Sign Language Purushottam Kar and Achla M. Raina Indian Institute of Technology Kanpur 6 January 2008 Overview Indian Sign Language An Introduction Sociolinguistic and

More information

Association of Neurophysiological Technologists of Australia Inc (also known as ANTA)

Association of Neurophysiological Technologists of Australia Inc (also known as ANTA) Association of Neurophysiological Technologists of Australia Inc (also known as ANTA) ABN: 80 872 615 302 www.anta.asn.au Competency Statements Electroencephalography (EEG) These competency statements

More information

A Novel Capsule Neural Network Based Model For Drowsiness Detection Using Electroencephalography Signals

A Novel Capsule Neural Network Based Model For Drowsiness Detection Using Electroencephalography Signals A Novel Capsule Neural Network Based Model For Drowsiness Detection Using Electroencephalography Signals Luis Guarda Bräuning (1) Nicolas Astorga (1) Enrique López Droguett (1) Marcio Moura (2) Marcelo

More information

COMP9444 Neural Networks and Deep Learning 5. Convolutional Networks

COMP9444 Neural Networks and Deep Learning 5. Convolutional Networks COMP9444 Neural Networks and Deep Learning 5. Convolutional Networks Textbook, Sections 6.2.2, 6.3, 7.9, 7.11-7.13, 9.1-9.5 COMP9444 17s2 Convolutional Networks 1 Outline Geometry of Hidden Unit Activations

More information

Bundles of Synergy A Dynamical View of Mental Function

Bundles of Synergy A Dynamical View of Mental Function Bundles of Synergy A Dynamical View of Mental Function Ali A. Minai University of Cincinnati University of Cincinnati Laxmi Iyer Mithun Perdoor Vaidehi Venkatesan Collaborators Hofstra University Simona

More information

BayesOpt: Extensions and applications

BayesOpt: Extensions and applications BayesOpt: Extensions and applications Javier González Masterclass, 7-February, 2107 @Lancaster University Agenda of the day 9:00-11:00, Introduction to Bayesian Optimization: What is BayesOpt and why it

More information

Active User Affect Recognition and Assistance

Active User Affect Recognition and Assistance Active User Affect Recognition and Assistance Wenhui Liao, Zhiwe Zhu, Markus Guhe*, Mike Schoelles*, Qiang Ji, and Wayne Gray* Email: jiq@rpi.edu Department of Electrical, Computer, and System Eng. *Department

More information

Knowledge networks of biological and medical data An exhaustive and flexible solution to model life sciences domains

Knowledge networks of biological and medical data An exhaustive and flexible solution to model life sciences domains Knowledge networks of biological and medical data An exhaustive and flexible solution to model life sciences domains Dr. Sascha Losko, Dr. Karsten Wenger, Dr. Wenzel Kalus, Dr. Andrea Ramge, Dr. Jens Wiehler,

More information

University of Canberra. This thesis is available in print format from the University of Canberra Library.

University of Canberra. This thesis is available in print format from the University of Canberra Library. University of Canberra This thesis is available in print format from the University of Canberra Library. If you are the author of this thesis and wish to have the whole thesis loaded here, please contact

More information

CS-E Deep Learning Session 4: Convolutional Networks

CS-E Deep Learning Session 4: Convolutional Networks CS-E4050 - Deep Learning Session 4: Convolutional Networks Jyri Kivinen Aalto University 23 September 2015 Credits: Thanks to Tapani Raiko for slides material. CS-E4050 - Deep Learning Session 4: Convolutional

More information

3D Deep Learning for Multi-modal Imaging-Guided Survival Time Prediction of Brain Tumor Patients

3D Deep Learning for Multi-modal Imaging-Guided Survival Time Prediction of Brain Tumor Patients 3D Deep Learning for Multi-modal Imaging-Guided Survival Time Prediction of Brain Tumor Patients Dong Nie 1,2, Han Zhang 1, Ehsan Adeli 1, Luyan Liu 1, and Dinggang Shen 1(B) 1 Department of Radiology

More information

Amy Kruse, Ph.D. Strategic Analysis, Inc. LCDR Dylan Schmorrow USN Defense Advanced Research Projects Agency

Amy Kruse, Ph.D. Strategic Analysis, Inc. LCDR Dylan Schmorrow USN Defense Advanced Research Projects Agency What can modern neuroscience technologies offer the forward-looking applied military psychologist? Exploring the current and future use of EEG and NIR in personnel selection and training. Amy Kruse, Ph.D.

More information

What Effect Do Schemas Have On The Recall Of

What Effect Do Schemas Have On The Recall Of What Effect Do Schemas Have On The Recall Of Memories AIM:Bartlett aimed to investigate the effect of culture on memory. memory ability/ability to recall and have advantageous effects if asked to do a

More information

Lesson 6 Learning II Anders Lyhne Christensen, D6.05, INTRODUCTION TO AUTONOMOUS MOBILE ROBOTS

Lesson 6 Learning II Anders Lyhne Christensen, D6.05, INTRODUCTION TO AUTONOMOUS MOBILE ROBOTS Lesson 6 Learning II Anders Lyhne Christensen, D6.05, anders.christensen@iscte.pt INTRODUCTION TO AUTONOMOUS MOBILE ROBOTS First: Quick Background in Neural Nets Some of earliest work in neural networks

More information

Schema-Driven Relationship Extraction from Unstructured Text

Schema-Driven Relationship Extraction from Unstructured Text Wright State University CORE Scholar Kno.e.sis Publications The Ohio Center of Excellence in Knowledge- Enabled Computing (Kno.e.sis) 2007 Schema-Driven Relationship Extraction from Unstructured Text Cartic

More information

Artificial Neural Networks

Artificial Neural Networks Artificial Neural Networks Torsten Reil torsten.reil@zoo.ox.ac.uk Outline What are Neural Networks? Biological Neural Networks ANN The basics Feed forward net Training Example Voice recognition Applications

More information

A Multichannel Deep Belief Network for the Classification of EEG Data

A Multichannel Deep Belief Network for the Classification of EEG Data A Multichannel Deep Belief Network for the Classification of EEG Data Alaa M. Al-kaysi a, Ahmed Al-Ani a and Tjeerd W. Boonstra b,c,d a Faculty of Engineering and Information Technology, University of

More information

A Vision-based Affective Computing System. Jieyu Zhao Ningbo University, China

A Vision-based Affective Computing System. Jieyu Zhao Ningbo University, China A Vision-based Affective Computing System Jieyu Zhao Ningbo University, China Outline Affective Computing A Dynamic 3D Morphable Model Facial Expression Recognition Probabilistic Graphical Models Some

More information

Classification of EEG signals in an Object Recognition task

Classification of EEG signals in an Object Recognition task Classification of EEG signals in an Object Recognition task Iacob D. Rus, Paul Marc, Mihaela Dinsoreanu, Rodica Potolea Technical University of Cluj-Napoca Cluj-Napoca, Romania 1 rus_iacob23@yahoo.com,

More information

Object recognition and hierarchical computation

Object recognition and hierarchical computation Object recognition and hierarchical computation Challenges in object recognition. Fukushima s Neocognitron View-based representations of objects Poggio s HMAX Forward and Feedback in visual hierarchy Hierarchical

More information

Epilepsy and Neuropsychology

Epilepsy and Neuropsychology Epilepsy and Neuropsychology Dr. Sare Akdag, RPsych Neuropsychology Service, BC Children s Hospital Clinical Assistant Professor, Dept of Paediatrics, UBC November 24, 2008 BC Epilepsy Society Lecture

More information

Exploiting deduction and abduction services for information retrieval. Ralf Moeller Hamburg University of Technology

Exploiting deduction and abduction services for information retrieval. Ralf Moeller Hamburg University of Technology Exploiting deduction and abduction services for information retrieval Ralf Moeller Hamburg University of Technology Seman&c Technologies: Data Descrip&ons Ontologies (specified in, e.g., OWL, UML) (aka

More information

Deep Learning Analytics for Predicting Prognosis of Acute Myeloid Leukemia with Cytogenetics, Age, and Mutations

Deep Learning Analytics for Predicting Prognosis of Acute Myeloid Leukemia with Cytogenetics, Age, and Mutations Deep Learning Analytics for Predicting Prognosis of Acute Myeloid Leukemia with Cytogenetics, Age, and Mutations Andy Nguyen, M.D., M.S. Medical Director, Hematopathology, Hematology and Coagulation Laboratory,

More information

Word Length Processing via Region-to-Region Connectivity

Word Length Processing via Region-to-Region Connectivity Word Length Processing via Region-to-Region Connectivity Mariya Toneva Machine Learning Department, Neural Computation Carnegie Mellon University Data Analysis Project DAP committee: Tom Mitchell, Robert

More information

Annotation and Retrieval System Using Confabulation Model for ImageCLEF2011 Photo Annotation

Annotation and Retrieval System Using Confabulation Model for ImageCLEF2011 Photo Annotation Annotation and Retrieval System Using Confabulation Model for ImageCLEF2011 Photo Annotation Ryo Izawa, Naoki Motohashi, and Tomohiro Takagi Department of Computer Science Meiji University 1-1-1 Higashimita,

More information

Neuroinformatics. Ilmari Kurki, Urs Köster, Jukka Perkiö, (Shohei Shimizu) Interdisciplinary and interdepartmental

Neuroinformatics. Ilmari Kurki, Urs Köster, Jukka Perkiö, (Shohei Shimizu) Interdisciplinary and interdepartmental Neuroinformatics Aapo Hyvärinen, still Academy Research Fellow for a while Post-docs: Patrik Hoyer and Jarmo Hurri + possibly international post-docs PhD students Ilmari Kurki, Urs Köster, Jukka Perkiö,

More information

EARLY STAGE DIAGNOSIS OF LUNG CANCER USING CT-SCAN IMAGES BASED ON CELLULAR LEARNING AUTOMATE

EARLY STAGE DIAGNOSIS OF LUNG CANCER USING CT-SCAN IMAGES BASED ON CELLULAR LEARNING AUTOMATE EARLY STAGE DIAGNOSIS OF LUNG CANCER USING CT-SCAN IMAGES BASED ON CELLULAR LEARNING AUTOMATE SAKTHI NEELA.P.K Department of M.E (Medical electronics) Sengunthar College of engineering Namakkal, Tamilnadu,

More information

Keywords Artificial Neural Networks (ANN), Echocardiogram, BPNN, RBFNN, Classification, survival Analysis.

Keywords Artificial Neural Networks (ANN), Echocardiogram, BPNN, RBFNN, Classification, survival Analysis. Design of Classifier Using Artificial Neural Network for Patients Survival Analysis J. D. Dhande 1, Dr. S.M. Gulhane 2 Assistant Professor, BDCE, Sevagram 1, Professor, J.D.I.E.T, Yavatmal 2 Abstract The

More information

How can Natural Language Processing help MedDRA coding? April Andrew Winter Ph.D., Senior Life Science Specialist, Linguamatics

How can Natural Language Processing help MedDRA coding? April Andrew Winter Ph.D., Senior Life Science Specialist, Linguamatics How can Natural Language Processing help MedDRA coding? April 16 2018 Andrew Winter Ph.D., Senior Life Science Specialist, Linguamatics Summary About NLP and NLP in life sciences Uses of NLP with MedDRA

More information

Semi-Automatic Construction of Thyroid Cancer Intervention Corpus from Biomedical Abstracts

Semi-Automatic Construction of Thyroid Cancer Intervention Corpus from Biomedical Abstracts jsci2016 Semi-Automatic Construction of Thyroid Cancer Intervention Corpus from Biomedical Wutthipong Kongburan, Praisan Padungweang, Worarat Krathu, Jonathan H. Chan School of Information Technology King

More information

Jia Jia Tsinghua University 26/09/2017

Jia Jia Tsinghua University 26/09/2017 Jia Jia jjia@tsinghua.edu.cn Tsinghua University 26/09/2017 Stage 1: Online detection of mental health problems Stress Detection via Harvesting Social Media Detecting Stress Based on Social Interactions

More information

Annotating Temporal Relations to Determine the Onset of Psychosis Symptoms

Annotating Temporal Relations to Determine the Onset of Psychosis Symptoms Annotating Temporal Relations to Determine the Onset of Psychosis Symptoms Natalia Viani, PhD IoPPN, King s College London Introduction: clinical use-case For patients with schizophrenia, longer durations

More information

Recognition of sign language gestures using neural networks

Recognition of sign language gestures using neural networks Recognition of sign language gestures using neural s Peter Vamplew Department of Computer Science, University of Tasmania GPO Box 252C, Hobart, Tasmania 7001, Australia vamplew@cs.utas.edu.au ABSTRACT

More information

Object Detectors Emerge in Deep Scene CNNs

Object Detectors Emerge in Deep Scene CNNs Object Detectors Emerge in Deep Scene CNNs Bolei Zhou, Aditya Khosla, Agata Lapedriza, Aude Oliva, Antonio Torralba Presented By: Collin McCarthy Goal: Understand how objects are represented in CNNs Are

More information

Timing and the cerebellum (and the VOR) Neurophysiology of systems 2010

Timing and the cerebellum (and the VOR) Neurophysiology of systems 2010 Timing and the cerebellum (and the VOR) Neurophysiology of systems 2010 Asymmetry in learning in the reverse direction Full recovery from UP using DOWN: initial return to naïve values within 10 minutes,

More information

Cognitive Neuroscience History of Neural Networks in Artificial Intelligence The concept of neural network in artificial intelligence

Cognitive Neuroscience History of Neural Networks in Artificial Intelligence The concept of neural network in artificial intelligence Cognitive Neuroscience History of Neural Networks in Artificial Intelligence The concept of neural network in artificial intelligence To understand the network paradigm also requires examining the history

More information

arxiv: v1 [cs.ai] 5 Oct 2018 October 8, 2018

arxiv: v1 [cs.ai] 5 Oct 2018 October 8, 2018 André Ofner Research Focus Cognitive Sciences University of Potsdam Potsdam, Germany ofner@uni-potsdam.de Sebastian Stober Artificial Intelligence Lab Otto von Guericke University Magdeburg, Germany stober@ovgu.de

More information

Automatic Detection of Epileptic Seizures in EEG Using Machine Learning Methods

Automatic Detection of Epileptic Seizures in EEG Using Machine Learning Methods Automatic Detection of Epileptic Seizures in EEG Using Machine Learning Methods Ying-Fang Lai 1 and Hsiu-Sen Chiang 2* 1 Department of Industrial Education, National Taiwan Normal University 162, Heping

More information