Medical image analysis has become an indispensable assisted tool in medical research, clinical disease diagnosis and treatment. However, it is difficult to collect a large number of high-quality medical images with effective annotation due to the characteristics of high annotation requirements, time-consuming, and it often requires expert knowledge. Therefore, medical image annotation is a major hurdle for developing precise and robust machine learning or deep learning models. Weakly supervised learning, as a branch of machine learning, uses limited, noisy or inaccurate data to train model parameters when compared with traditional supervised learning. The research of weakly supervised learning greatly reduces the algorithm's dependence on data annotation and effectively promotes the development of medical image analysis technology and its application in clinical practice.
This session will mainly focus on the latest developments in weakly supervised learning for medical image analysis. We are pleased to invite researchers from several communities (i.e., signal processing, machine learning, medical image analysis, biomedical engineering, etc.) to submit their results. The interest topics include, but are not limited to:
- Incomplete Supervision Learning for Medical Image Analysis;
- Inexact Supervision Learning for Medical Image Analysis;
- Inaccurate Supervision Learning for Medical Image Analysis;
- Machine Learning and Pattern Recognition for Weakly Supervised Medical Image Analysis;
- Weakly Supervised Multimodal Medical Image Representation, Understanding and Perception;
- Survey of Recent Advances on Weakly Supervised Medical Image Analysis and Related Fields;
- Other Weakly Supervised Learning for Medical Image Analysis;
Each full paper should be limited to 6-8 pages (6 pages limit + references).
January 20, 2022 January 30, 2022 (Extended!)
Notification of Acceptance: March 30, 2022
Camera-Ready Papers Due: TBD
See the ICMR 2022 Paper submission section.
- Kai Hu (firstname.lastname@example.org), Xiangtan University, China
- Dapeng Xiong (email@example.com), Cornell University, United States
- Zhineng Chen (firstname.lastname@example.org), Fudan University, Shanghai, China
- Hongtao Xie (email@example.com), University of Science and Technology of China, China
- Ioannis Kompatsiaris (firstname.lastname@example.org), CERTH-ITI, Greece