This book consists of full papers presented in the 2nd workshop of ”Medical Image Learning with Noisy and Limited Data (MILLanD)” held in conjunction with the 26th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2023).
The 24 full papers presented were carefully reviewed and selected from 38 submissions. The conference focused on challenges and limitations of current deep learning methods applied to limited and noisy medical data and present new methods for training models using such imperfect data.
Efficient Annotation and Training Strategies.- Reducing Manual
Annotation Costs for Cell Segmentation by Upgrading Low-quality
Annotations.- ScribSD: Scribble-supervised Fetal MRI Segmentation based on
Simultaneous Feature and Prediction Self-Distillation.- Label-efficient
Contrastive Learning-based Model for Nuclei Detection and Classification in
3D Cardiovascular Immunofluorescent Images.- Affordable Graph Neural Network
Framework using Topological Graph Contraction.- Approaches for Noisy,
Missing, and Low Quality Data.- Dual-domain Iterative Network with Adaptive
Data Consistency for Joint Denoising and Few-angle Reconstruction of Low-dose
Cardiac SPECT.- A Multitask Framework for Label Refinement and Lesion
Segmentation in Clinical Brain Imaging.- COVID-19 Lesion Segmentation
Framework for the Contrast-enhanced CT in the Absence of Contrast-enhanced CT
Annotation.- Feasibility of Universal Anomaly Detection without Knowingthe
Abnormality in Medical Image.- Unsupervised, Self-supervised, and Contrastive
Learning.- Decoupled Conditional Contrastive Learning with Variable Metadata
for Prostate Lesion Detection.- FBA-Net: Foreground and Background Aware
Contrastive Learning for Semi-Supervised Atrium Segmentation.- Masked Image
Modeling for Label-Efficient Segmentation in Two-Photon Excitation
Microscopy.- Automatic Quantification of COVID-19 Pulmonary Edema by
Self-supervised Contrastive Learning.- SDLFormer: A Sparse and Dense
Locality-enhanced Transformer for Accelerated MR Image
Reconstruction.- Robust Unsupervised Image to Template Registration Without
Image Similarity Los.- A Dual-Branch Network with Mixed and Self-Supervision
for Medical Image Segmentation: An Application to Segment Edematous Adipose
Tissue.- Weakly-supervised, Semi-supervised, and Multitask
Learning.- Combining Weakly Supervised Segmentation with Multitask Learning
forImproved 3D MRI Brain Tumour Classification.- Exigent Examiner and Mean
Teacher: An Advanced 3D CNN-based Semi-Supervised Brain Tumor Segmentation
Framework.- Extremely Weakly-supervised Blood Vessel Segmentation with
Physiologically Based Synthesis and Domain Adaptation.- Multi-Task Learning
for Few-Shot Differential Diagnosis of Breast Cancer Histopathology
Image.- Active Learning.- Efficient Annotation for Medical Image Analysis: A
One-Pass Selective Annotation Approach.- Test-time Augmentation-based Active
Learning and Self-training for Label-efficient Segmentation.- Active Transfer
Learning for 3D Hippocampus Segmentation.- Transfer Learning.- Using Training
Samples as Transitive Information Bridges in Predicted 4D MRI.- To Pretrain
or not to Pretrain? A Case Study of Domain-Specific Pretraining for Semantic
Segmentation in Histopathology.- Large-scale Pretraining on Pathological
Images for Fine-tuning of Small Pathological Benchmarks.
Lisainfo e-raamatute kohta