A multi-view contrastive learning and semi-supervised self-distillation framework for early recurrence prediction in ovarian cancer

Chi Dong; Yujiao Wu; Bo Sun; Jiayi Bo; Yufei Huang; Yikang Geng; Qianhui Zhang; Ruixiang Liu; Wei Guo; Xingling Wang; Xiran Jiang

doi:10.1016/j.compmedimag.2024.102477

A multi-view contrastive learning and semi-supervised self-distillation framework for early recurrence prediction in ovarian cancer

Comput Med Imaging Graph. 2024 Dec 8:119:102477. doi: 10.1016/j.compmedimag.2024.102477. Online ahead of print.

Authors

Chi Dong¹, Yujiao Wu¹, Bo Sun², Jiayi Bo³, Yufei Huang¹, Yikang Geng¹, Qianhui Zhang¹, Ruixiang Liu¹, Wei Guo⁴, Xingling Wang⁵, Xiran Jiang⁶

Affiliations

¹ Department of Biomedical Engineering, School of Intelligent Medicine, China Medical University, Liaoning 110122, China.
² Department of Radiology, the First Affiliated Hospital of Dalian Medical University, Dalian, Liaoning, China.
³ School of Computer, Shenyang Aerospace University, Shenyang, Liaoning 110122, China.
⁴ School of Computer, Shenyang Aerospace University, Shenyang, Liaoning 110122, China. Electronic address: guowei@sau.edu.cn.
⁵ Department of Gynecology, Liaoning Cancer Hospital and Institute, Cancer Hospital of China Medical University, Shenyang 110042, China. Electronic address: wangxingling@cancerhosp-ln-cmu.com.
⁶ Department of Biomedical Engineering, School of Intelligent Medicine, China Medical University, Liaoning 110122, China. Electronic address: xrjiang@cmu.edu.cn.

PMID: 39673904
DOI: 10.1016/j.compmedimag.2024.102477

Abstract

Objective: This study presents a novel framework that integrates contrastive learning and knowledge distillation to improve early ovarian cancer (OC) recurrence prediction, addressing the challenges posed by limited labeled data and tumor heterogeneity.

Methods: The research utilized CT imaging data from 585 OC patients, including 142 cases with complete follow-up information and 125 cases with unknown recurrence status. To pre-train the teacher network, 318 unlabeled images were sourced from public datasets (TCGA-OV and PLAGH-202-OC). Multi-view contrastive learning (MVCL) was employed to generate multi-view 2D tumor slices, enhancing the teacher network's ability to extract features from complex, heterogeneous tumors with high intra-class variability. Building on this foundation, the proposed semi-supervised multi-task self-distillation (Semi-MTSD) framework integrated OC subtyping as an auxiliary task using multi-task learning (MTL). This approach allowed the co-training of a student network for recurrence prediction, leveraging both labeled and unlabeled data to improve predictive performance in data-limited settings. The student network's performance was assessed using preoperative CT images with known recurrence outcomes. Evaluation metrics included area under the receiver operating characteristic curve (AUC), accuracy (ACC), sensitivity (SEN), specificity (SPE), F1 score, floating-point operations (FLOPs), parameter count, training time, inference time, and mean corruption error (mCE).

Results: The proposed framework achieved an ACC of 0.862, an AUC of 0.916, a SPE of 0.895, and an F1 score of 0.831, surpassing existing methods for OC recurrence prediction. Comparative and ablation studies validated the model's robustness, particularly in scenarios characterized by data scarcity and tumor heterogeneity.

Conclusion: The MVCL and Semi-MTSD framework demonstrates significant advancements in OC recurrence prediction, showcasing strong generalization capabilities in complex, data-constrained environments. This approach offers a promising pathway toward more personalized treatment strategies for OC patients.

Keywords: Contrastive learning; Ovarian cancer; Recurrence; Self-distillation; Semi-supervised.