What question did this study set out to answer?

The aim is to enhance semi-supervised medical image segmentation by addressing annotation bias and improving sample quality assessment.

February 26, 2026

TriCSART: Semi-Supervised Medical Image Segmentation with Triple-Level Contrastive Learning and Selective Active Re-Training

Puntos clave

The aim is to enhance semi-supervised medical image segmentation by addressing annotation bias and improving sample quality assessment.
Introduced a teacher-student architecture incorporating Triple-Level Contrastive Learning and Selective Active Re-Training.
Developed a TLC module with three distinct loss functions to improve inter-class and intra-class classification.
Implemented a SART module for evaluating and selecting high-quality samples from unlabeled data.
Achieved state-of-the-art performance on diverse benchmarks, including four public datasets and one private dataset.
Outperformed existing semi-supervised segmentation methods across multiple evaluations.
Ablation studies confirmed the contributions of TLC and SART components to the overall performance.

Resumen

Semi-supervised medical image segmentation has garnered significant attention due to challenges of limited medical data accessibility and expensive annotation costs. However, existing studies face two critical challenges: 1) while contrastive learning has demonstrated potential in semi-supervised frameworks, prior implementations lack hierarchical modeling, failing to comprehensively integrate contrastive mechanisms across intra-, inter-, and memorybankdimensions;2)conventional pseudo-labeling strategies inadequately address quality assessment, potentially propagating annotation biases through continual error accumulation. To address these issues, this paper introduces a Triple-Level Contrastive (TLC) Learning and Selective Active Re-Training (SART) strategy for medical image analysis. The proposed method adopts a teacher-student architecture with two main components: the TLC module and the SART module. The TLC module establishes multilevel semantic consistency across different views through three distinct, complementary loss functions, simultaneously enhancing inter-class discriminability and intra-class compactness. To further mitigate sample quality imbalance, the SART module introduces a metric-driven evaluation mechanism to automatically identify salient samples. Finally, these selected unlabeled samples are integrated with labeled data for re-training guided by calculated curriculum scores. Extensive experiments are conducted on five diverse bench marks, including four public datasets and one private CBCT dataset. The results demonstrate that our approach achieves state-of-the-art performance, consistently outperforming other semi-supervised segmentation strategies. Ablation studies further confirm the efficacy of each proposed component.

Me gusta

Guardar