DRIMV_TSK: An Interpretable Surgical Evaluation Model for Incomplete Multi-View Rectal Cancer Data

2025-06-20

AI Summary

Rectal cancer surgical difficulty assessment faces challenges including sparse clinical data, incomplete multimodal inputs (e.g., high-resolution MRI, fat-suppressed MRI, clinical metrics), and poor model interpretability. To address these, we propose an interpretable surgical difficulty assessment framework tailored for incomplete multi-view data. Our method introduces a novel dual-representation learning mechanism that jointly performs missing-view imputation and representation learning; incorporates second-order similarity constraints to enhance cross-view discriminative capability; and employs a Shannon entropy–based adaptive weighting strategy to improve model interpretability. Furthermore, we integrate a TSK fuzzy inference system to generate clinically intuitive decision outputs. Evaluated on our newly constructed MVRC multi-view dataset, the proposed framework significantly outperforms state-of-the-art baselines, achieving superior performance in both predictive accuracy and interpretability.

Technology Category

• Machine Learning: Multi-instance/Multi-view Learning
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Computer Vision: Multi-modal Vision

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics

Abstract

A reliable evaluation of surgical difficulty can improve the success of the treatment for rectal cancer and the current evaluation method is based on clinical data. However, more data about rectal cancer can be collected with the development of technology. Meanwhile, with the development of artificial intelligence, its application in rectal cancer treatment is becoming possible. In this paper, a multi-view rectal cancer dataset is first constructed to give a more comprehensive view of patients, including the high-resolution MRI image view, pressed-fat MRI image view, and clinical data view. Then, an interpretable incomplete multi-view surgical evaluation model is proposed, considering that it is hard to obtain extensive and complete patient data in real application scenarios. Specifically, a dual representation incomplete multi-view learning model is first proposed to extract the common information between views and specific information in each view. In this model, the missing view imputation is integrated into representation learning, and second-order similarity constraint is also introduced to improve the cooperative learning between these two parts. Then, based on the imputed multi-view data and the learned dual representation, a multi-view surgical evaluation model with the TSK fuzzy system is proposed. In the proposed model, a cooperative learning mechanism is constructed to explore the consistent information between views, and Shannon entropy is also introduced to adapt the view weight. On the MVRC dataset, we compared it with several advanced algorithms and DRIMV_TSK obtained the best results.

Problem

• Evaluates surgical difficulty for rectal cancer using multi-view data
• Addresses incomplete data in real-world surgical evaluation scenarios
• Improves interpretability of AI models for rectal cancer treatment

Innovation

• Dual representation incomplete multi-view learning model
• Missing view imputation in representation learning
• TSK fuzzy system with Shannon entropy