3rd Workshop on Deep Learning in Medical Image Analysis

After the success of the 1st DLMIA and the 2nd DLMIA, held with MICCAI 2015 and MICCAI 2016, respectively, where we welcomed hundreds of attendees and influential invited speakers, we present the 3rd DLMIA to be held with MICCAI 2017. Deep learning methods have experienced an immense growth in interest from the medical image analysis community because of their ability to process very large training sets, to transfer learned features between different databases, and to analyse multimodal data. Deep Learning in Medical Image Analysis (DLMIA) is a workshop dedicated to the presentation of works focused on the design and use of deep learning methods in medical image analysis applications. We believe that this workshop is setting the trends and identifying the challenges of the use of deep learning methods in medical image analysis. The main objective of this workshop is to advance scientific research of deep learning methods in medical image analysis. The workshop is going to foster the debate within the medical image analysis community of the recently proposed deep learning methods and also attract the attention of the applied optimization research community.

Article on Computer Vision News on DLMIA 2017 (see page 18-19)

Nvidia best paper award went to Bob De Vos, University Medical Center Utrecht; Floris Berendsen, Leiden University Medical Center; Max Viergever, n/a; Marius Staring, UMC; Ivana Isgum, UMC Utrecht. End-to-End Unsupervised Deformable Image Registration with a Convolutional Neural Network.

Proceedings published by SPRINGER under the “Lecture Notes in Computer Science” book series.

Topics of Interest:

● Medical imaging-based analysis using deep learning

● Medical signal-based analysis using deep learning

● Medical image reconstruction using deep learning

● Deep learning-based medical imaging applications

● Image description by means of deep learning techniques

● Deep learning model selection in medical imaging

Submission guidelines

● DLMIA uses the same guidelines as the main conference submissions, described in detail here.
● Papers should be formatted in Lecture Notes in Computer Science style. Latex style files can be found on the Springer website, which also contains Office Word instructions (scroll to the bottom half of the web page). The file format for submissions is Adobe Portable Document Format (PDF). Other formats will not be accepted.
● The maximum number of pages is 8. Submissions exceeding this limit will be rejected without review.
● You should not modify any of the formatting commands in the style files. Any modifications found may result in automatic rejection.
● The review process is double blind. Submissions are to be fully anonymized (see the guidelines for anonymity here).
● It is also possible to submit supplementary material with your submission (see the guidelines for supplementary material submission here). The deadline for submitting the supplementary material is the same as for the main paper.

Submission

IMPORTANT DATES

March 22nd : DLMIA'17 site goes online
May 22nd : results released for MICCAI'17 papers
June 12th (extended to June 16th) : DLMIA'17 paper and supplementary material submission deadline
July 11th : DLMIA'17 paper notification of acceptance
July 17 th : DLMIA'17 Camera-ready version submission
September 14th: Workshop Day!

KEYNOTE SPEAKERS

The Impact of Deep Learning on Radiology - slides

Dr. Ronald M. Summers, M.D., Ph.D.

National Institutes of Health

Advances in Deep Neural Architectures for Medical Image Analysis

Dr. Chis Pal

University of Montreal

Beyond Deep Learning: Medical Image Recognition, Segmentation and Parsing

Dr. Kevin Zhou

Siemens Healthineers

PROGRAM

8:00am - 8:03am: Opening Remarks
8:03am - 8:45am: Invited Talk: Beyond Deep Learning: Medical Image Recognition, Segmentation and Parsing - Dr. Kevin Zhou
Oral paper session #1
8:45am - 9:00am: Adversarial training and dilated convolutions for brain MRI segmentation - Pim Moeskops*, Eindhoven University of Technology; Mitko Veta, Eindhoven University of Technology; Maxime Lafarge, Eindhoven University of Technology; Koen Eppenhof, Eindhoven University of Technology; Josien Pluim, Eindhoven
9:00am - 9:15am: CNNs Enable Accurate and Fast Segmentation of Drusen in Optical Coherence Tomography - Shekoufeh Gorgi Zadeh*, Institute of Computer Science II, University of Bonn; Maximilian W.M. Wintergerst, Department of Ophthalmology, University of Bonn; Vitalis Wiens, University of Bonn; Sarah Thiele, Department of Ophthalmology, University of Bonn; Frank Holz, Department of Ophthalmology, University of Bonn; Robert P. Finger, Department of Ophthalmology, University of Bonn; Thomas Schultz, Institute of Computer Science II, University of Bonn
9:15am - 9:30am: Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations - Carole Sudre*, UCL; Wenqi Li, University College London; Tom Vercauteren, University College London; Sebastien Ourselin, University College London; M. Jorge Cardoso, UCL
9:30am - 9:45am: A deep level set method for image segmentation - Min Tang*, University of Alberta; Sepehr Valipour, University of Alberta; Zichen Zhang, University of Alberta; Dana Cobzas, University of Alberta; Martin Jagersand, University of Alberta
9:45am - 10:00am: Learning Spatio-Temporal Aggregation for Fetal Heart Analysis in Ultrasound Video - Arijit Patra*, University of Oxford; Weilin Huang, Oxforf; Alison Noble, University of Oxford
10:00am - 10:30am: Coffee break 
10:30am - 10:45am: Nvidia Talk - slides
Oral paper session #2
10:45am - 11:00am: Fully convolutional regression network for accurate detection of measurement points - Michal Sofka*, 4Catalyzer
11:00am - 11:15am: Deep Residual Recurrent Neural Networks for Characterisation of Cardiac Cycle Phase from Echocardiograms - Fatemeh Taheri Dezaki*, University of British Columbia; Neeraj Dhungel, University of British Columbia; Amir Abdi, University of British Columbia; Christina Luong, Vancouver General Hospital; Terasa Tsang, Vancouver General Hospital; John Jue, Vancouver General Hospital; Ken Gin, Vancouver General Hospital; Dale Hawley, Vancouver General Hospital; Robert Rohling, University of British Columbia; Purang Abolmaesumi, The Univ. of British Columbia
11:15am - 11:30am: 3D Randomized Connection Network with Graph-based Inference - Siqi Bao*, HKUST; Pei Wang, HKUST; Albert Chung, Hong Kong University of Science and Technology
11:30am - 12:30pm: Poster Session (please see below for the list of posters)
12:30pm - 1:30pm: Lunch 
1:30pm - 2:15pm: Invited TAlk: The Impact of Deep Learning on RAdiology - Dr. Ronald Summers - slides
Oral paper session #3
2:15pm - 2:30pm: Non-rigid Craniofacial 2D-3D Registration Using CNN-Based Regression - Yuru Pei*, Peking University; Yungeng Zhang, Peking University; Haifang Qin, Peking University; Gengyu Ma, Usens Inc; Yuke Guo, Luoyang Institute of Science and Technology; Tianmin Xu, Peking University; Hongbin Zha, Peking University, China
2:30pm - 2:45pm: Context-based Normalization of Histological Stains using Deep Convolutional Features - Daniel Bug*, RWTH-Aachen University; Steffen Schneider, RWTH-Aachen University; Anne Grote, Hannover Medical School; Eva Oswald, Oncotest GmbH; Julia Schüler, Oncotest GmbH; Friedrich Feuerhake, Hannover Medical School; Dorit Merhof, RWTH Aachen University
2:45pm - 3:00pm: Domain-adversarial neural networks to address the appearance variability of histopathology images - Maxime Lafarge*, Eindhoven University of Technology; Josien Pluim, Eindhoven; Koen Eppenhof, Eindhoven University of Technology; Pim Moeskops, "Eindhoven University of Technology, Netherlands"; Mitko Veta, Eindhoven University of Technology
3:00pm - 3:15pm: End-to-End Unsupervised Deformable Image Registration with a Convolutional Neural Network - Bob De Vos*, University Medical Center Utrecht; Floris Berendsen, Leiden University Medical Center; Max Viergever, n/a; Marius Staring, UMC; Ivana Isgum, UMC Utrecht
3:15pm - 3:30pm: Butterfly Network talk 
3:30pm - 4:00pm: Coffee Break 
4:00pm - 4:45pm: Invited Talk: Advances in Deep Neural Architectures for Medical Image Analysis - Dr. Chris Pal
Oral paper session #4
4:45pm - 5:00pm: Computationally efficient cardiac views projection using 3D Convolutional Neural Networks - Matthieu Le*, Arterys; Jesse Lieman-Sifry, Arterys; Felix Lau, Arterys; Sean Sall, Arterys; Albert Hsiao, Arterys; Daniel Golden, Arterys
5:00pm - 5:15pm: Region-aware Deep Localization Framework for Cervical Vertebrae in X-Ray Images - S M Masudur Rahman Al Arif*, City University London; Karen Knapp, University of Exeter; Gregory Slabaugh, City University London
5:15pm - 5:30pm	Best Paper Award and closing remarks  

Poster Session papers
Skin Lesion Segmentation via Refinement Network - Xinzi He, Shenzhen University; Zhen Yu*, Shenzhen university; Tianfu Wang , Shenzhen university; Baiying Lei, Shenzhen university
ssEMnet: Serial-section Electron Microscopy Image Registration using a Spatial Transformer Network with Learned Features - Inwan Yoo*, Ulsan National Institute of Science and Technology; David G. C. Hildebrand, The Rockefeller University; Willie F. Tobin, Harvard Medical School; Wei-Chung Allen Lee, Harvard Medical School; Won-Ki Jeong, Ulsan National Institute of Science and Technology
Fast Predictive Simple Geodesic Regression - Zhipeng Ding*, Department of Computer Science, University of North Carolina at Chapel Hill; Greg Fleishman, Imaging Genetics Center, USC; Xiao Yang, UNC Chapel Hill; Paul Thompson, Laboratory of Neuro Imaging, Keck School of Medicine of USC; Roland Kwitt, University of Salzburg, Austria; Marc Niethammer, UNC
Transitioning between Convolutional and Fully Connected Layers in Neural Networks - Shazia Akbar*, Sunnybrook Research Institute; Mohammad Peikari, Sunnybrook Research Institute; Sherine Salame, Sunnybrook Health Sciences Centre; Sharon Nofech-Mozes, Sunnybrook Health Sciences Centre; Anne Martel, Sunnybrook Research Institute
A Unified Framework for Tumor Proliferation Score Prediction in Breast Histopathology - Kyunghyun Paeng*, Lunit Inc.; Sangheum Hwang, Lunit Inc.; Sunggyun Park, Lunit Inc.; Minsoo Kim, Lunit Inc.
Fast, Simple Calcium Imaging Segmentation with Fully Convolutional Networks - Alex Klibisz, Oak Ridge National Labs; Derek Rose*, Oak Ridge National Labs; Matthew Eicholtz, Oak Ridge National Labs; Jay Blundon, St. Jude Children’s Research Hospital; Stanislav Zakharenko, St. Jude Children’s Research Hospital;
Grey Matter Segmentation in Spinal Cord MRIs via 3D Convolutional Encoder Networks with Shortcut Connections - Adam Porisky*, UBC
A Deep Residual Inception Network for HEp-2 Cell Classification - Yuexiang Li*, Shenzhen University; Linlin Shen, Shenzhen University
Stain Colour Normalisation to Improve Mitosis Detection on Breast Histology Images - Azam Hamidinekoo*, Aberystwyth University; Reyer Zwiggelaar, University of Aberystwyth
Analyzing Microscopic Images of Peripheral Blood Smear using Deep Learning - Dheeraj Mundhra*, Sigtuple; Bharath Cheluvaraju, Sigtuple; Jaiprasad Rampure, Sigtuple; Tathagato Rai Dastidar, Sigtuple
AGNet: Attention-guided Network for Surgical Tool Presence Detection - Xiaowei Hu*, The Chinese University of Hong Kong; Lequan Yu, The Chinese University of Hong Kong; Hao Chen, The Chinese University of Hong Kong; Jing Qin, The Hong Kong Polytechnic University; Pheng-Ann Heng, The Chinese Univsersity of Hong Kong
Joint Segmentation of Multiple Thoracic Organs in CT Images with Two Collaborative Deep Architectures - Roger Trullo*, Univ Normandy
Left Atrium Segmentation in CT Volumes with Fully Convolutional Networks - Honghui Liu*, Tsinghua University; Jianjiang Feng, Tsinghua University; Zishun Feng, Tsinghua University; Jiwen Lu, Tsinghua University; Jie Zhou, """Tsinghua University, China"""
Multi-Stage Diagnosis of Alzheimer’s Disease with Incomplete Multimodal Data via Multi-Task Deep Learning - Kim Han Thung*, UNC; Pew-Thian Yap, UNC-Chapel Hill; Dinggang Shen, UNC
Simultaneous Multiple Surface Segmentation Using Deep Learning - Abhay Shah*, University Of Iowa; Michael Abramoff, University of Iowa; Xiaodong Wu, University of Iowa
Accurate Lung Segmentation via Network-Wise Training of Convolutional Networks - Sangheum Hwang (Lunit Inc.) and Sunggyun Park (Lunit Inc.).
Quantifying the Impact of Type 2 Diabetes on Brain Perfusion using Deep Neural Networks - Behrouz Saghafi*, UT Southwestern Medical Center; Prabhat Garg, UT Southwestern Medical Center; Ben Wagner, UT Southwestern Medical Center; Carrie Smith, Wake Forest School of Medicine; Jianzhao Xu, Wake Forest School of Medicine; Ananth Madhuranthakam, Wake Forest School of Medicine; Youngkyoo Jung, Wake Forest School of Medicine; Jasmin Divers, Wake Forest School of Medicine; Barry Freedman, Wake Forest School of Medicine; Joseph Maldjian, UT Southwestern Medical Center; Albert Montillo, University of Texas Southwestern Medical Center
Pathological Pulmonary Lobe Segmentation from CT Images using Progressive Holistically Nested Neural Networks and Random Walker - Kevin George, National Institutes of Health; Adam Harrison, National Institutes of Health; Dakai Jin, National Institutes of Health; Ziyue Xu*, National Institutes of Health; Daniel Mollura, National Institutes of Health
3D FCN Feature Driven Regression Forest-Based Pancreas Localization and Segmentation - Masahiro Oda*, Nagoya University; Natsuki Shimizu, Nagoya University; Holger Roth, "Nagoya University, Japan"; Ken'ichi Karasawa, Nagoya University; Takayuki Kitasaka, "Aichi Institute of Technology, Japan"; Kazunari Misawa, Aichi Cancer Center; Michitaka Fujiwara , Nagoya University Hospital; Daniel Rueckert, Imperial; Kensaku Mori, Nagoya University
Self-Supervised Learning for Spinal MRIs - Amir Jamaludin*, University of Oxford; Timor Kadir, Optellum; Andrew Zisserman, University of Oxford
Multi-Scale Networks for Segmentation of Brain Magnetic Resonance Images - Jie Wei, Northwestern Polytechnical University; Yong Xia*, Northwestern Polytechnical University
Accelerated Magnetic Resonance Imaging by Adversarial Neural Network - Ohad Chitrit*, BGU; Tammy Riklin Raviv, BGU
A Multi-Scale CNN and Curriculum Learning Strategy for Mammogram Classification - William Lotter*, Harvard University
Deep Learning for Automatic Detection of Abnormal Findings in Breast Mammography - Ayelet Akselrod-Ballin*, IBM-Research

Dr. Gustavo Carneiro
University of Adelaide, Australia

Dr. João Manuel R. S. Tavares
Universidade do Porto, Portugal

Dr. Andrew P. Bradley
University of Queensland, Australia

Dr. João Paulo Papa
Universidade Estadual Paulista, Brazil

Dr. Jaime S. Cardoso
Universidade do Porto, Portugal

Dr. Jacinto C. Nascimento
Instituto Superior Tecnico, Portugal

Dr. Vasileios Belagiannis
University of Oxford, UK

Dr. Zhi Lu
University of South Australia, Australia

Aaron Carass (Johns Hopkins University)

Adrian Barbu (Florida State University)

Adrien Depeursinge (HES-SO and EPFL)

Albert Montillo (University of Texas Southwestern Medical Center)

Amarjot Singh (University of Cambridge)

Amin Khatami (Deakin University)

Amir Jamaludin (University of Oxford)

Angshul Majumdar (Indian Institute of Technology Delhi)

Ankush Gupta (University of Oxford)

Anne Martel (Sunnybrook Research Institute)

Ariel Benou (Ben-Gurion University of the Negev)

Ayelet Akselrod-Ballin (IBM-Research)

Carlos Arteta (University of Oxford)

Carole Sudre (University College London)

Daguang Xu (Siemens Healthineers)

Dana Cobzas (University of Alberta)

Daniel Worrall (University College London)

Daniela Iacoviello (Sapienza University of Rome)

Dario Oliveira (IBM Research)

Deepak Mishra (Indian Institute of Technology Delhi)

Diogo Pernes (INESC TEC and University of Porto)

Erik Smista (Norwegian University of Science and Technology)

Evangelia Zacharaki (CentraleSupélec)

Felix Achilles (Technical University of Munich)

Gabriel Maicas (University of Adelaide)

Ghassan Hamarneh (Simon Fraser University)

Gregory Slabaugh (City University London)

Grzegorz Chlebus (Fraunhofer MEVIS, Bremen)

Guilherme Aresta (INESC TEC and University of Porto)

Gustavo Souza (Federal University of Sao Carlos)

Haifang Qin (Peking University)

Hariharan Ravishankar (GE Global Research)

Hayit Greenspan (Tel Aviv University)

Helder Oliveira (Universidade do Porto)

Holger Roth (Nagoya University)

Hyun Jun Kim (VUNO Inc.)

Islem Rekik (University of Dundee)

Itzik Avital (Tel Aviv University)

Jianming Liang (Arizona State University)

John (Zhaoyang) Xu (Queen Mary University of London)

Jose Costa Pereira (INESC TEC and University of Porto)

Kelwin Fernandes (University of Porto)

Kyu-Hwan Jung (VUNO Inc.)

Le Lu (National Institutes of Health)

Maria Gabrani (IBM Research Zurich)

Marleen de Bruijne (Erasmus MC Rotterdam / University of Copenhagen)

Mehmet Ayg\"{u}n (Istanbul Technical University)

Michal Drozdzal (Polytechnique Montreal)

Mohammad Arafat Hussain (University of British Columbia)

Narayanan Babu (GE Global Research)

Neeraj Dhungel (University of British Columbia)

Nico Hoffmann (Technical University of Dresden)

Nishikant Deshmukh (Johns Hopkins University)

Pew-Thian Yap (University of North Carolina-Chapel Hill)

Pheng-Ann Heng (The Chinese University of Hong Kong)

Philippe C. Cattin (University of Basel)

Prasad Sudhakar (GE Global Research)

Rafeef Abugharbieh (University of British Columbia)

Rami Ben-Ari (IBM-Research)

Roger Tam (University of British Columbia)

S. Chakra Chennubhotla (University of Pittsburgh)

Saad Ullah Akram (University of Oulu, Finland)

Shadi Albarqouni (Technical University of Munich)

Simon Pezold (MIAC, University of Basel)

Siqi Bao (Hong Kong University of Science and Technology)

Song Wang (University of South Carolina)

Steffen Schneider (RWTH-Aachen University)

Takayuki Kitasaka (Aichi Institute of Technology)

Tammy Riklin Raviv (Ben-Gurion University of the Negev)

Teresa Araujo (INESC TEC and University of Porto)

Thomas Schultz (Institute of Computer Science II, University of Bonn)

Tom Brosch (University of British Columbia)

Vijay Kumar (University of Adelaide)

Vivek Vaidya (GE Global Research)

Weidong Cai (University of Sydney)

Xiang Xiang (Johns Hopkins University)

Xiao Yang (University of North Carolina Chapel Hill)

Xiaodong Wu (University of Iowa)

Xiaoguang Lu (Siemens Healthineers)

Xiaohui Xie (University of California, Irvine)

Yefeng Zheng (Siemens)

Yong Xia (Northwestern Polytechnical University)

Youngjin Yoo (University of British Columbia)

Zhi Huang (Purdue University)

Zhibin Liao (University of Adelaide)

Zita Marinho (Instituto Superior Tecnico)

Ziyue Xu (National Institutes of Health)

Submission guidelines

IMPORTANT DATES

KEYNOTE SPEAKERS

PROGRAM

ORGANISERS

PROGRAM COMMITTEE

Sponsors