Programme

08:00 – 08:10 Registration

08:10 – 08:20 Opening Remarks

08:20 – 09:05 Plenary Talk

♣ Dr. Dinggang Shen, “Full-Stack, Full-Spectrum AI in Medical Imaging”

09:05 – 09:50 Plenary Talk

♣ Dr. Hervé Delingette, “From Data-driven to Biophysics-based AI in Medical Image Analysis”

09:50 – 10:00 Coffee Break

10:00 – 11:00 Session 1: Computer-Aided Detection/Diagnosis

Session Chair: Dr. Mingxia Liu and Dr. Qingyu Zhao

[MLMI-O-1] 10:00~10:15 Jointly Discriminative and Generative Recurrent Neural Networks for Learning from fMRI

[MLMI-O-2] 10:15~10:30 Learning-based Bone Quality Classification Method for Spinal Metastasis

[MLMI-O-3] 10:30~10:45 Distanced LSTM: Time-Distanced Gates in Long Short-Term Memory Models for Lung Cancer Detection

[MLMI-O-4] 10:45~11:00 Lesion Detection with Deep Aggregated 3D Contextual Feature and Auxiliary Information

11:00 – 12:00 Poster Session (can be posted until the late afternoon)

[MLMI-P-1] Unsupervised Conditional Consensus Adversarial Network for Brain Disease Identification with Structural MRI

[MLMI-P-2] Semantic filtering through deep source separation on microscopy images

[MLMI-P-3] FusionNet: Incorporating Shape and Texture for Abnormality Detection in 3D Abdominal CT Scans

[MLMI-P-4] Detecting Lesion Bounding Ellipses with Gaussian Proposal Networks

[MLMI-P-5] Relu cascade of feature pyramid networks for CT pulmonary nodule detection

[MLMI-P-6] Joint Localization of Optic Disc and Fovea in Ultra-Widefield Fundus Images

[MLMI-P-7] Reinforced Transformer for Medical Image Captioning

[MLMI-P-8] MSAFusionNet: Multiple Subspace Attention Based Deep Multi-modal Fusion Network

[MLMI-P-9] Ultrasound Liver Fibrosis Diagnosis using Multi-indicator guided Deep Neural Networks

[MLMI-P-10] Sturm: Sparse Tubal-Regularized Multilinear Regression for fMRI

[MLMI-P-11] BOLD fMRI-based Brain Perfusion Prediction Using Deep Dilated Wide Activation Networks

[MLMI-P-12] Adaptive Functional Connectivity Network using Parallel Hierarchical BiLSTM for MCI Diagnosis

[MLMI-P-13] Multi Task Convolutional Neural Network for Joint Bone Age Assessment and Ossification Center Detection from Hand Radiograph

[MLMI-P-14] Spatial Regularized Classification Network for Spinal Dislocation Diagnosis

[MLMI-P-15] GFD Faster R-CNN: Gabor Fractal DenseNet Faster R-CNN for automatic detection of esophageal abnormalities in endoscopic images

[MLMI-P-16] A Relation Hashing Network Embedded with Prior Features for Skin Lesion Classification

[MLMI-P-17] Semi-Supervised Multi-Task Learning with Chest X-Ray Images

[MLMI-P-18] Novel Bi-directional Images Synthesis based on WGAN-GP with GMM-based Noise Generation

[MLMI-P-19] Joint Shape Representation and Classification for Detecting PDAC

[MLMI-P-20] Detecting abnormalities in resting-state dynamics: An unsupervised learning approach

[MLMI-P-21] A Hybrid Multi-atrous and Multi-scale Network for Liver Lesion Detection

[MLMI-P-22] Renal Cell Carcinoma Staging with Learnable Image Histogram-based Deep Neural Network

[MLMI-P-23] Gated Recurrent Neural Networks for Accelerated Ventilation MRI

[MLMI-P-24] A Cascaded Multi-Modality Analysis in Mild Cognitive Impairment

[MLMI-P-25] An Active Learning Approach for Reducing Annotation Cost in Skin Lesion Analysis

[MLMI-P-26] LSTMs and resting-state fMRI for classification and understanding of Parkinson’s disease

[MLMI-P-27] Deep learning model integrating dilated convolution and deep supervision for brain tumor segmentation in multi-parametric MRI

[MLMI-P-28] Brain MR Image Segmentation in Small Dataset with Adversarial Defense and Task Reorganization

[MLMI-P-29] Automated Segmentation of Skin Lesion Based on Pyramid Attention Network

[MLMI-P-30] Privacy-preserving Federated Brain Tumour Segmentation

[MLMI-P-31] Children’s Neuroblastoma Segmentation using Morphological Features

[MLMI-P-32] Deep Active Lesion Segmentation

[MLMI-P-33] Automatic Couinaud Segmentation from CT Volumes on Liver Using GLC-Unet

[MLMI-P-34] Conv-MCD: A Plug-and-Play Multi-task Module for Medical Image Segmentation

[MLMI-P-35] Learn to Step-wise Focus on Targets for Biomedical Image Segmentation

[MLMI-P-36] Weakly Supervised Learning Strategy for Lung Defect Segmentation

[MLMI-P-37] A joint 3D UNet-Graph Neural Network-based method for Airway Segmentation from chest CTs

[MLMI-P-38] High- and Low-Level Feature Enhancement for Medical Image Segmentation

[MLMI-P-39] Shape-Aware Complementary-Task Learning for Multi-Organ Segmentation

[MLMI-P-40] Tree-LSTM: Using LSTM to Encode Memory in Anatomical Tree Prediction from 3D Images

[MLMI-P-41] Automatic Rodent Brain MRI Lesion Segmentation with Fully Convolutional Networks

[MLMI-P-42] Deep Residual Learning for Instrument Segmentation in Robotic Surgery

[MLMI-P-43] Advancing Pancreas Segmentation in Multi-protocol MRI Volumes using Hausdorff-Sine Loss Function

[MLMI-P-44] Biomedical Image Segmentation by Retina-like Sequential Attention Mechanism Using Only A Few Training Images

[MLMI-P-45] Unsupervised Lesion Detection with Locally Gaussian Approximation

[MLMI-P-46] Infant Brain Deformable Registration Using Global and Local Label-Driven Deep Regression Learning

[MLMI-P-47] Modelling Airway Geometry as Stock Market Data using Bayesian Changepoint Detection

[MLMI-P-48] Conv2Warp: An unsupervised deformable image registration with continuous convolution and warping

[MLMI-P-49] FAIM-A ConvNet Method for Unsupervised 3D Medical Image Registration

[MLMI-P-50] Pseudo-labeled bootstrapping and multi-stage transfer learning for the classification and localization of dysplasia in Barrett’s Esophagus

[MLMI-P-51] Correspondence-Steered Volumetric Descriptor Learning Using Deep Functional Maps

[MLMI-P-52] Dense-residual Attention Network for Skin Lesion Segmentation

[MLMI-P-53] A Maximum Entropy Deep Reinforcement Learning Neural Tracker

[MLMI-P-54] Multi-Scale Attentional Network for Multi-Focal Segmentation of Active Bleed after Pelvic Fractures

[MLMI-P-55] Joint Holographic Detection and Reconstruction

[MLMI-P-56] Weakly Supervised Segmentation by a Deep Geodesic Prior

12:00 – 13:00 Lunch

13:00 – 14:30 Session 2: Medical Image Segmentation

Session Chair: Dr. Heung-Il Suk and Dr. Jaeil Kim

[MLMI-O-5] 13:00~13:15 End-to-End Adversarial Shape Learning for Abdominal Organ Segmentation

[MLMI-O-6] 13:15~13:30 Boundary Aware Networks for Medical Image Segmentation

[MLMI-O-7] 13:30~13:45 Weakly Supervised Confidence Learning for Brain MR Image Dense Parcellation

[MLMI-O-8] 13:45~14:00 Lesion Detection by Efficiently Bridging 3D Context

[MLMI-O-9] 14:00~14:15 Cross-Modal Attention-Guided Convolutional Network for Multi-Modal Cardiac Segmentation

[MLMI-O-10] 14:15~14:30 Automatic Fetal Brain Extraction Using Multi-Stage U-Net with Deep Supervision

14:30 – 14:40 Coffee Break

14:40 – 16:10 Session 3: Registration and Reconstruction

Session Chair: Dr. Pingkun Yan and Dr. Marleen de Bruijne

[MLMI-O-11] 14:40~14:55 Communal Domain Metric Learning for Registration in Drifted Image Spaces

[MLMI-O-12] 14:55~15:10 Morphological Simplification of Brain MR Images by Deep Learning for Facilitating Deformable Registration

[MLMI-O-13] 15:10~15:25 Residual Attention Generative Adversarial Networks for Nuclei Detection on Routine Colon Cancer Histology Images

[MLMI-O-14] 15:25~15:40 Anatomy-Aware Self-supervised Fetal MRI Synthesis from Unpaired Ultrasound Images

[MLMI-O-15] 15:40~15:55 Select, Attend, and Transfer: Light, Learnable Skip Connections

[MLMI-O-16] 15:55~16:10 Confounder-Aware Visualization of ConvNets

16:10 – 16:20 Coffee Break

16:20 – 17:50 Session 4: Automated Medical Image Analysis

Session Chair: Dr. Jaeil Kim and Dr. Ziyue Xu

[MLMI-O-17] 16:20~16:35 DCCL: A Benchmark for Cervical Cytology Analysis

[MLMI-O-18] 16:35~16:50 WSI-Net: Branch-based and Hierarchy-aware Network for Segmentation and Classification of Breast Histopathological Whole-slide Images

[MLMI-O-19] 16:50~17:05 Globally-Aware Multiple Instance Classifier for Breast Cancer Screening

[MLMI-O-20] 17:05~17:20 Smartphone-Supported Malaria Diagnosis Based on Deep Learning

[MLMI-O-21] 17:20~17:35 Multi-Template based Auto-weighted Adaptive Structural Learning for ASD Diagnosis

[MLMI-O-22] 17:35~17:50 Improving Whole-Brain Neural Decoding of fMRI with Domain Adaptation