Boundary-Selective Pseudo-Label Repair and Model Absorption for Semi-Supervised Medical Image Segmentation

Yuan Liu

doi:10.63313/AJET.9070

Authors

Yuan Liu College of Computer Science and Technology, Qingdao University, Qingdao 266071, China Author

DOI:

https://doi.org/10.63313/AJET.9070

Keywords:

Semi-Supervised Segmentation, Pseudo-Label Repair, Boundary Quality, Active Contour, Model Absorption, Medical Image Analysis

Abstract

Pseudo-labels can exploit unlabeled medical images, but high-overlap masks may still contain local contour errors and selected corrections may disappear during fine-tuning. We recast pseudo-label refinement as a repair-to-model problem and present Boundary-Selective Pseudo-Label Repair and Model Absorption (CPPA). A validation-selected frozen source supplies the no-edit reference. Wavelet-frequency evidence, spatial responses, and disagreement between source predictors constrain a morphological Snake to bounded add/remove candidates. A local policy scores each contour arc against the paired no-edit source and abstains when the estimated benefit is unsafe. The selected mask supervises an edit-aware absorption bank, after which a validation-only router promotes one checkpoint or retains the source. Across 27 internal settings spanning CVC-ClinicDB, BUSI-benign, and BUSI-malignant, three label ratios, and three seeds, the final single-model outputs improve the selected source by 0.0241 Dice, 0.0536 BF1, and 0.0402 Boundary IoU on average. Adapted checkpoints are promoted in 26 of 27 settings, and all nine dataset-ratio means improve Dice, BF1, and Boundary IoU. Frozen transfer to CVC-ColonDB improves Dice and BF1 at every label ratio. The evidence supports a bounded, abstaining repair policy whose local corrections can be absorbed into one deployable network.

References

[1] Al-Dhabyani, W., Gomaa, M., Khaled, H. and Fahmy, A. (2020) Dataset of Breast Ultrasound Images. Data in Brief, 28, 104863.

[2] Bai, Y., Chen, D., Li, Q., Shen, W. and Wang, Y. (2023) Bidirectional Copy-Paste for Semi-Supervised Medical Image Segmentation. Proceedings of CVPR, 11514-11524.

[3] Bernal, J., Sanchez, F. J., Fernandez-Esparrach, G., Gil, D., Rodriguez, C. and Vilarino, F. (2015) WM-DOVA Maps for Accurate Polyp Highlighting in Colonoscopy. Computerized Medical Imaging and Graphics, 43, 99-111.

[4] Berthelot, D., Carlini, N., Goodfellow, I., Papernot, N., Oliver, A. and Raffel, C. (2019) MixMatch: A Holistic Approach to Semi-Supervised Learning. NeurIPS.

[5] Chen, H., Tao, R., Fan, Y., et al. (2023) SoftMatch: Addressing the Quantity-Quality Tradeoff in Semi-Supervised Learning. ICLR.

[6] Chen, X., Yuan, Y., Zeng, G. and Wang, J. (2021) Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision. CVPR.

[7] Chen, Y., Yang, Z., Shen, C., et al. (2024) Evidence-Based Uncertainty-Aware Semi-Supervised Medical Image Segmentation. Computers in Biology and Medicine, 170, 108004.

[8] Cheng, B., Girshick, R., Dollar, P., Berg, A. C. and Kirillov, A. (2021) Boundary IoU: Improving Object-Centric Image Segmentation Evaluation. CVPR.

[9] Fan, D.-P., Ji, G.-P., Zhou, T., et al. (2020) PraNet: Parallel Reverse Attention Network for Polyp Segmentation. MICCAI.

[10] Karimi, D. and Salcudean, S. E. (2020) Reducing the Hausdorff Distance in Medical Image Segmentation with Convolutional Neural Networks. IEEE TMI, 39, 499-513.

[11] Kervadec, H., Bouchtiba, J., Desrosiers, C., et al. (2021) Boundary Loss for Highly Unbalanced Segmentation. Medical Image Analysis, 67, 101851.

[12] Laine, S. and Aila, T. (2017) Temporal Ensembling for Semi-Supervised Learning. ICLR.

[13] Li, M., Wu, R., Liu, H., et al. (2023) InstanT: Semi-Supervised Learning with Instance-Dependent Thresholds. NeurIPS.

[14] Li, S., Zhang, C. and He, X. (2020) Shape-Aware Semi-Supervised 3D Semantic Segmentation for Medical Images. MICCAI.

[15] Luo, X., Chen, J., Song, T. and Wang, G. (2021) Semi-Supervised Medical Image Segmentation through Dual-Task Consistency. AAAI, 8801-8809.

[16] Luo, X., Wang, G., Liao, W., et al. (2022) Semi-Supervised Medical Image Segmentation via Uncertainty Rectified Pyramid Consistency. Medical Image Analysis, 80, 102517.

[17] Olsson, V., Tranheden, W., Pinto, J. and Svensson, L. (2021) ClassMix: Segmentation-Based Data Augmentation for Semantic Segmentation. WACV, 1368-1377.

[18] Ouali, Y., Hudelot, C. and Tami, M. (2020) Semi-Supervised Semantic Segmentation with Cross-Consistency Training. CVPR.

[19] Ronneberger, O., Fischer, P. and Brox, T. (2015) U-Net: Convolutional Networks for Biomedical Image Segmentation. MICCAI, 234-241.

[20] Shi, Y., Zhang, J., Ling, T., et al. (2022) Inconsistency-Aware Uncertainty Estimation for Semi-Supervised Medical Image Segmentation. IEEE TMI, 41, 608-620.

[21] Sohn, K., Berthelot, D., Li, C.-L., et al. (2020) FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence. NeurIPS.

[22] Tarvainen, A. and Valpola, H. (2017) Mean Teachers are Better Role Models. NeurIPS.

[23] Vázquez, D., Bernal, J., Sanchez, F. J., et al. (2017) A Benchmark for Endoluminal Scene Segmentation of Colonoscopy Images. Journal of Healthcare Engineering, 2017, 4037190.

[24] Wang, Y., Chen, H., Heng, Q., et al. (2023) FreeMatch: Self-Adaptive Thresholding for Semi-Supervised Learning. ICLR.

[25] Wang, Y., Wang, H., Shen, Y., et al. (2022) Semi-Supervised Semantic Segmentation Using Unreliable Pseudo Labels. CVPR.

[26] Wu, Y., Ge, Z., Zhang, D., et al. (2022) Mutual Consistency Learning for Semi-Supervised Medical Image Segmentation. Medical Image Analysis, 81, 102530.

[27] Yang, L., Qi, L., Feng, L., Zhang, W. and Shi, Y. (2023) Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation. CVPR.

[28] Yang, L., Zhuo, W., Qi, L., Shi, Y. and Gao, Y. (2022) ST++: Make Self-Training Work Better for Semi-Supervised Semantic Segmentation. CVPR, 4268-4277.

[29] Yu, L., Wang, S., Li, X., et al. (2019) Uncertainty-Aware Self-Ensembling Model for Semi-Supervised 3D Left Atrium Segmentation. MICCAI.

[30] Zhang, B., Wang, Y., Hou, W., et al. (2021) FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling. NeurIPS.

[31] Zhao, X., Qi, Z., Wang, S., et al. (2024) RCPS: Rectified Contrastive Pseudo Supervision for Semi-Supervised Medical Image Segmentation. IEEE JBHI.

[32] Zou, Y., Zhang, Z., Zhang, H., et al. (2021) PseudoSeg: Designing Pseudo Labels for Semantic Segmentation. ICLR.