paper-with-me

홈 › Papers

Alleviating Class Imbalance in Semi-supervised Multi-organ Segmentation via Balanced Subclass Regularization

2024-08-26 · Zhenghao Feng, Lu Wen, Binyu Yan, Jiaqi Cui, Yan Wang

Semi-supervised learning (SSL) has shown notable potential in relieving the heavy demand of dense prediction tasks on large-scale well-annotated datasets, especially for the challenging multi-organ segmentation (MoS). However, the prevailing class-imbalance problem in MoS, caused by the substantial variations in organ size, exacerbates the learning difficulty of the SSL network. To alleviate this issue, we present a two-phase semi-supervised network (BSR-Net) with balanced subclass regularization for MoS. Concretely, in Phase I, we introduce a class-balanced subclass generation strategy based on balanced clustering to effectively generate multiple balanced subclasses from original biased ones according to their pixel proportions. Then, in Phase II, we design an auxiliary subclass segmentation (SCS) task within the multi-task framework of the main MoS task. The SCS task contributes a balanced subclass regularization to the main MoS task and transfers unbiased knowledge to the MoS network, thus alleviating the influence of the class-imbalance problem. Extensive experiments conducted on two publicly available datasets, i.e., the MICCAI FLARE 2022 dataset and the WORD dataset, verify the superior performance of our method compared with other methods.

📄 PDF Abstract BibTeX arXiv:2408.14047

Code (0)

등록된 구현이 없습니다.

Tasks

Organ Segmentation

Similar Papers 제목 키워드 기반

Energy Score-based Pseudo-Label Filtering and Adaptive Loss for Imbalanced Semi-supervised SAR target recognition

2024-11-06 · Xinzheng Zhang, Yuqing Luo, Guopeng Li

Automatic target recognition (ATR) is an important use case for synthetic aperture radar (SAR) image interpretation. Recent years have seen significant advancements in SAR ATR technology based on semi-supervised learning…

Pseudo LabelPseudo Label FilteringTriplet

DHC: Dual-debiased Heterogeneous Co-training Framework for Class-imbalanced Semi-supervised Medical Image Segmentation

2023-07-22 · Haonan Wang, Xiaomeng Li

The volume-wise labeling of 3D medical images is expertise-demanded and time-consuming; hence semi-supervised learning (SSL) is highly desirable for training with limited labeled data. Imbalanced class distribution is a …

Image SegmentationMedical Image SegmentationSemantic SegmentationSemi-supervised Medical Image Segmentation

Semi-Supervised Object Detection with Adaptive Class-Rebalancing Self-Training

2021-07-11 · Fangyuan Zhang, Tianxiang Pan, Bin Wang

This study delves into semi-supervised object detection (SSOD) to improve detector performance with additional unlabeled data. State-of-the-art SSOD performance has been achieved recently by self-training, in which train…

object-detectionObject DetectionSemi-Supervised Object Detection

BASIC: Semi-supervised Multi-organ Segmentation with Balanced Subclass Regularization and Semantic-conflict Penalty

2025-01-07 · Zhenghao Feng, Lu Wen, Yuanyuan Xu, Binyu Yan 외

Semi-supervised learning (SSL) has shown notable potential in relieving the heavy demand of dense prediction tasks on large-scale well-annotated datasets, especially for the challenging multi-organ segmentation (MoS). Ho…

Multi-Task LearningOrgan Segmentation

Calibrating Label Distribution for Class-Imbalanced Barely-Supervised Knee Segmentation

2022-05-07 · Yiqun Lin, Huifeng Yao, Zezhong Li, Guoyan Zheng 외

Segmentation of 3D knee MR images is important for the assessment of osteoarthritis. Like other medical data, the volume-wise labeling of knee MR images is expertise-demanded and time-consuming; hence semi-supervised lea…