Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Addressing Class Imbalance in Semi-supervised Image Segmentation: A Study on Cardiac MRI

About

Due to the imbalanced and limited data, semi-supervised medical image segmentation methods often fail to produce superior performance for some specific tailed classes. Inadequate training for those particular classes could introduce more noise to the generated pseudo labels, affecting overall learning. To alleviate this shortcoming and identify the under-performing classes, we propose maintaining a confidence array that records class-wise performance during training. A fuzzy fusion of these confidence scores is proposed to adaptively prioritize individual confidence metrics in every sample rather than traditional ensemble approaches, where a set of predefined fixed weights are assigned for all the test cases. Further, we introduce a robust class-wise sampling method and dynamic stabilization for a better training strategy. Our proposed method considers all the under-performing classes with dynamic weighting and tries to remove most of the noises during training. Upon evaluation on two cardiac MRI datasets, ACDC and MMWHS, our proposed method shows effectiveness and generalizability and outperforms several state-of-the-art methods found in the literature.

Hritam Basak, Sagnik Ghosal, Ram Sarkar• 2022

Related benchmarks

TaskDatasetResultRank
Medical Image SegmentationAMOS 5% labeled
Mean Dice38.73
29
Semi-supervised medical image segmentationSynapse (20% labeled)
Average Dice Score33.24
27
Multi-organ SegmentationSynapse 20% labeled data (test)
Avg. Dice33.24
16
Showing 3 of 3 rows

Other info

Follow for update