AttentioScope: a multi-indicator quantification framework with attention mechanism based on thyroid fine-needle aspiration smear images
The interpretability of deep learning models is crucial for their clinical application in computational pathology. Although attention-based methods can provide intuitive heatmap explanations, their reliability on challenging samples still requires systematic, fine-grained evaluation tools to assess model performance more comprehensively. To this end, this paper proposes a multi-metric quantitative framework based on thyroid fine-needle aspiration smear images to evaluate the comprehensive performance of different models through visual analysis. First, the framework assesses the reliability and focus capability of attention distributions by computing multi-dimensional quantitative metrics such as entropy, concentration, stability, and compactness of the attention heatmaps. Second, by correlating the heatmaps with underlying image features, it identifies whether models rely on pathology-irrelevant low-level features. To validate the effectiveness of the framework, we systematically evaluated four mainstream attention-based multiple instance learning (MIL) models (CLAM, TransMIL, PEGTB-MIL, ADMIL) on athyroid fine-needle aspiration smear image dataset. Experimental results show that in challenging samples of high-performance models, attention mechanisms may exhibit patterns such as feature hijacking or spatial bias, which traditional performance metrics fail to effectively reveal. This framework aims to conduct a fine-grained evaluation of attention-based models, assisting in identifying potential hidden deficiencies in challenging samples, thereby providing a reference framework for model assessment and optimization.
Authors
- 胡亚君
- En Fan (ORCID: https://orcid.org/0000-0002-1354-1354)
- Qinlong Lv (ORCID: https://orcid.org/0009-0004-5188-2741)
- Yunming Qiu
- Zonghua Wen
Institutions
- Shanxi Medical University (CN)
- Shenzhen University (CN)
- Shaoxing University (CN)
Publication Details
- Journal
- Frontiers in Endocrinology
- Published
- 2026-11-13
- DOI
- https://doi.org/10.3389/fendo.2026.1908393
- Primary Topic
- AI in cancer detection
- Type
- article
- Field-Weighted Citation Impact
- 0.00