Morning Session

08:00 Welcome

08:15 Keynote I – Rene Vidal (Johns Hopkins University)

• Machine Learning in Hematology: Reinventing the Blood Test

09:00 Oral Session I – Methods

• 09:00 – Multimodal Multitask Representation Learning for Metadata Prediction in Pathology – Weng, Cai, Lin, Tan, Chen
• 09:20 – A Hierarchical Probabilistic U-Net for Modeling Multi-Scale Ambiguities – Kohl, Romera-Paredes, Haier-Hein, Rezende, Eslami, Kohli, Zisserman, Ronneberger
• 09:40 – Task incremental learning of Chest X-ray data on compact architectures – Patra

10:00 – 10:30 Coffee Break – Poster Session I (Poster List Below)

10:30 Keynote II – Julia Schnabel (King's College London)

• Deep learning for medical image quality control

11:15 Oral Session II – Image Analysis and Segmentation

• 11:15 – Multimodal Self-Supervised Learning for Medical Image Analysis – Taleb, Lippert, Nabi, Klein
• 11:35 – Evolution-based Fine-tuning of CNNs for Prostate Cancer Detection – Namdar, Gujrathi, Haider, Khalvati
• 11:55 – Unsupervised deep clustering for predictive texture pattern discovery in medical images – Perkonigg, Sobotka, Ba-Ssalamah, Langs
• 12:15 – Large-scale classification of breast MRI exams using deep convolutional networks – Gong, Muckley, Wu, Makino, Kim, Heacock, Moy, Knoll, Geras

Afternoon Session

14:00 Keynote III – Leo Grady (Paige AI)

• Changing the Paradigm of Pathology: AI and Computational Diagnostics

14:45 Oral Session III – Imaging

• 14:45 – High Resolution Medical Image Analysis with Spatial Partitioning – Hou, Cheng, Shazeer, Parmar, Li, Korfiatis, Drucker, Blezek, Song
• 15:05 – Estimating localized complexity of white-matter wiring with GANs – Hallgrimsson, Sharan, Grafton, Singh
• 15:25 – Training a Variational Network for use on 3D High Resolution MRI Data in 1 Day – Kames, Doucette, Rauscher

15:45 – 16:15 Coffee Break – Poster Session II (Poster List Below)

16:15 Keynote IV – Daniel Sodickson (NYU Langone Health)

• AI and Radiology: How machine learning will change the way we see patients, and the way we see ourselves

17:00 – 18:00 fastMRI Challenge

• Larry Zitnick, FB AI Research
• Patrick Putzky, University of Amsterdam
• Puyang Wang, United Imaging Intelligence/Johns Hopkins University
• Nicola Pezzotti, Philips Research

18:00 Closing Remarks

10:00 – 10:30 Morning Poster Session

• Multimodal Multitask Representation Learning for Metadata Prediction in Pathology – Weng, Cai, Lin, Tan, Chen [ORAL+Poster]
• A Hierarchical Probabilistic U-Net for Modeling Multi-Scale Ambiguities – Kohl, Romera-Paredes, Haier-Hein, Rezende, Eslami, Kohli, Zisserman, Ronneberger [ORAL+Poster]
• Task incremental learning of Chest X-ray data on compact architectures – Patra [ORAL+Poster]
• Multimodal Self-Supervised Learning for Medical Image Analysis – Taleb, Lippert, Nabi, Klein [ORAL+Poster]
• Evolution-based Fine-tuning of CNNs for Prostate Cancer Detection – Namdar, Gujrathi, Haider, Khalvati [ORAL+Poster]
• Unsupervised deep clustering for predictive texture pattern discovery in medical images – Perkonigg, Sobotka, Ba-Ssalamah, Langs [ORAL+Poster]
• Large-scale classification of breast MRI exams using deep convolutional networks – Gong, Muckley, Wu, Makino, Kim, Heacock, Moy, Knoll, Geras [ORAL+Poster]
• Bipartite Distance For Shape-Aware Landmark Detection in Spinal X-Rays – Zubaer, Huang, Fan, Cheung, To, Qian, Terzopoulos
• GAN-enhanced Conditional Echocardiogram – Abdi, Tsang, Abolmaesumi
• Invasiveness Prediction of Pulmonary Adenocarcinomas Using Deep Feature Fusion Networks – Li, Ma, Li
• Push it to the Limit: Discover Edge-Cases in Image Data with Autoencoders – Manakov, Tresp, Maximilian
• Noise-aware PET image Enhancement with Adaptive Deep Learning – Xiang, Wang, Gong, Zaharchuk, Zhang
• clDice - a Novel Connectivity-Preserving Loss Function for Vessel Segmentation – Paetzold, Shit, Ezhov, Tetteh, Ertuerk, Menze
• Machine Learning with Multi-Site Imaging Data: An Empirical Study on the Impact of Scanner Effects – Glocker, Robinson, Coelho de Castro, Dou, Konukoglu
• Extraction of hierarchical functional connectivity components in human brain using resting-state fMRI – Sahoo, Bassett, Davatzikos
• A Study into Echocardiography View Conversion – Abdi, Jafari, Fels, Tsang, Abolmaesumi
• Variable Projection optimization for Intravoxel Incoherent Motion (IVIM) MRI estimation – Fadnavis, Garyfallidis
• Boosting Liver and Lesion Segmentation from CT Scans by Mask Mining – Roth, Konopczynski, Hesser
• Unsupervised Sparse-view Backprojection via Convolutional and Spatial Transformer Networks – Liu, Sajda
• Collaborative Unsupervised Domain Adaptation for Medical Image Diagnosis – Zhang, Wei, Zhao, Niu, Wu, Tan, Huang
• Image Quality Assessment for Rigid Motion Compensation – Preuhs, Manhart, Roser, Stimpel, Syben, Psychogios, Kowarschik, Maier
• Harnessing spatial MRI normalization: patch individual filter layers for CNNs – Eitel, Albrecht, Paul, Ritter
• Binary Mode Multinomial Deep Learning Model for more efficient Automated Diabetic Retinopathy Detection – Trivedi, Desbiens, Gross, Ferres, Dodhia
• PILOT: Physics-Informed Learned Optimal Trajectories for Accelerated MRI – Weiss, Senouf, Vedula
• Variational Inference and Bayesian CNNs for Uncertainty Estimation in Multi-Factorial Bone Age Prediction – Stern, Urschler, Payer, Eggenreich
• In-plane organ motion prediction using a recurrent encoder-decoder framework – Vazquez Romaguera, Plantefeve, Kadoury
• Separation of target anatomical structure and occlusions in thoracic X-ray images – Hofmanninger, Langs
• Knee Cartilage Segmentation Using Diffusion-Weighted MRI – Duarte, Hedge, Kaku, Mohan, Raya
• Learning to estimate label uncertainty for automatic radiology report parsing – Olatunji, Yao
• Multi-defect microscopy image restoration under limited data conditions – Razdaibiedina, Velayutham, Modi

15:45 – 16:15 Afternoon Poster Session

• High Resolution Medical Image Analysis with Spatial Partitioning – Hou, Cheng, Shazeer, Parmar, Li, Korfiatis, Drucker, Blezek, Song [ORAL+Poster]
• Estimating localized complexity of white-matter wiring with GANs – Hallgrimsson, Sharan, Grafton, Singh [ORAL+Poster]
• Training a Variational Network for use on 3D High Resolution MRI Data in 1 Day – Kames, Doucette, Rauscher [ORAL+Poster]
• Saliency cues for continual learning of ultrasound – Patra
• End-to-End Fully Automatic Segmentation of Scoliotic Vertebrae from Spinal X-Ray Images – Imran, Huang, Tang, Fan, Cheung, To, Qian, Terzepoulos
• Hepatocellular Carcinoma Intra-arterial Treatment Response Prediction for Improved Therapeutic Decision-Making – Yang, Dvornek, Zhang, Chapiro, Lin, Abajian, Duncan
• High- and Low-level image component decomposition using VAEs for improved reconstruction and anomaly detection – Zimmerer, Petersen, Maier-Hein
• Radiologist Validated Systematic Search over Deep Neural Networks for Screening Musculoskeletal Radiographs – Chakravarty, Sheet, Ghosh, Sarkar, Sethuraman
• A Biased Sampling Network to Localise Landmarks for Automated Disease Diagnosis – Schobs, Zhou, Cogliano, Swift, Lu
• Variational inference based assessment of mammographic lesion classification algorithms under distribution shift – Gossmann, Cha, Sun
• Batch-wise Dice Loss: Rethinking the Data Imbalance for Medical Image Segmentation – Chang, Lin, Wu, Chen, Hsu
• Towards Artifact Rejection in Microscopic Urinalysis – Dutt
• Analysis of focal loss with noisy labels – Yao, Jadhav
• Data Augmentation for Early Stage Lung Nodules using Deep Image Prior and CycleGan – Martinez Manzanera, Ellis, Baltatzis, Devaraj, Desai, Le Golgoc, Nair, Glocker, Schnabel
• Neural Ordinary Differential Equations for Semantic Segmentation of Individual Colon Glands – Pinckaers, Litjens
• Class-Aware CycleGAN: A domain adaptation method for mammography and tomosynthesis – Dalmis, Birhanu, Vanegas, Kallenerg, Kroes
• Tracking-Assisted Segmentation of Biological Cells – Gupta, de Bruin, Panteli, Gavves
• Deep learning feature based medical image retrieval for large-scale datasets – Haq, Moradi, Wang
• Generating CT-scans with 3D Generative Adversarial Networks Using a Supercomputer – Ruhe, Codreanu, va Leeuwen, Podareanu, Saletore, Teuwen
• Meta-SVDD: Probabilistic Meta-Learning for One-Class Classification in Cancer Histology Images – Gamper, Chan, Tsang, Snead, Rajpoot
• One-Click Spine MRI – De Goyeneche, Peterson, He, Addy, Santos
• Improved generalizability of deep-learning based low dose volumetric contrast-enhanced MRI – Tamir, Pasumarthi, Gong, Zaharchuk, Zhang
• Deep Recursive Bayesian Maximal Path for Fully Automatic Extraction of Coronary Arteries in CT Images – Jeon, Shim, Chang
• A Deep Multi-Modal Method for Patient Wound Healing Assessment – Oota, Rowtula, Mohammed, Galitz, Liu, Gupta
• Signal recovery with un-trained convolutional neural networks – Heckel
• On the Similarity of Deep Learning Representations Across Didactic and Adversarial Examples – Douglas, Farahani
• Generative Smoke Removal – Sidorov, Wang, Alaya-Chekh
• Towards High Fidelity Direct-Contrast Synthesis from Magnetic Resonance Fingerprinting – Wang, Karasan, Doneva, Tan
• HR-CAMs : Using multi-level features for precise discriminative localization of pathology – Ingalhalikar, Shinde, Chougule, Saini
• Towards Autism detection on brain structural MRI scans with Adversarially Learned Inference – Garcia
• Neural Network Compression using Reinforcement Learning in Medical Image Segmentation – Chhabra, Soni, Avinash

Oral Presentations

• The format will be a 15 mins talk + 5 mins Q&A.
• Projector is 16:9 HDMI, bring your own dongle.
• A front poster spot will also be available to you, instructions below.

Poster Presentations

• Verify if you are in the Morning or Afternoon poster session.
• Poster size is 36"W x 48"H (or 90x122 cm), vertical portrait.
• Prints should be on lightweight paper, not laminated.