Thyroid pathology image classification via multi-scale feature fusion and multi-instance learning.
1/5 보강
[BACKGROUND] The global incidence of thyroid cancer has significantly increased, while traditional pathological diagnosis remains time-consuming and expert-dependent.
APA
Li X, Liu G, et al. (2025). Thyroid pathology image classification via multi-scale feature fusion and multi-instance learning.. Diagnostic pathology, 20(1), 112. https://doi.org/10.1186/s13000-025-01703-5
MLA
Li X, et al.. "Thyroid pathology image classification via multi-scale feature fusion and multi-instance learning.." Diagnostic pathology, vol. 20, no. 1, 2025, pp. 112.
PMID
41088391 ↗
Abstract 한글 요약
[BACKGROUND] The global incidence of thyroid cancer has significantly increased, while traditional pathological diagnosis remains time-consuming and expert-dependent. This study develops an auxiliary diagnostic tool designed to reduce the workload of pathologists and improve diagnostic accuracy.
[METHODS] Our study utilized 543 WSIs from Liuzhou Cancer Hospital for model development, employing a novel multi-feature fusion architecture that combines RetCCL, iBOT, and DINO embeddings. We systematically evaluated stain normalization and multi-scale analysis across four multiple-instance learning (MIL) frameworks: CLAM-SB (single-branch), CLAM-MB (multi-branch), DTFD (double-tier), and LA-MIL (location-aware). The method was rigorously validated on an independent set of 128 WSIs from Taizhou Cancer Hospital.
[RESULTS] The results show that stain normalization, multi-scale fusion, and multi-feature fusion significantly improve classification performance. In 10-fold cross-validation on the internal dataset, the system demonstrated significant improvements over the baseline RetCCL model: AUC (0.9900 vs. 0.9629), accuracy (0.9594 vs. 0.8951), with relative improvements of 2.8% in AUC and 7.2% in accuracy. Precision increased by 11.5% (0.9434 vs. 0.8461) and F1-score by 9.8% (0.9511 vs. 0.8665). On the external validation dataset, the model maintained robust performance with an AUC of 0.9584, accuracy of 0.9070, precision of 0.9247, and F1-score of 0.9348, confirming its reliability and applicability.
[CONCLUSIONS] We propose a weakly supervised MIL framework integrating multi-scale analysis and cross-model feature fusion for thyroid cancer diagnosis. Our method showed promising and consistent results across internal and external datasets. While further clinical validation and workflow integration are needed, the results suggest the potential of this approach to assist pathologists in diagnostic workflows, particularly in resource-constrained settings.
[METHODS] Our study utilized 543 WSIs from Liuzhou Cancer Hospital for model development, employing a novel multi-feature fusion architecture that combines RetCCL, iBOT, and DINO embeddings. We systematically evaluated stain normalization and multi-scale analysis across four multiple-instance learning (MIL) frameworks: CLAM-SB (single-branch), CLAM-MB (multi-branch), DTFD (double-tier), and LA-MIL (location-aware). The method was rigorously validated on an independent set of 128 WSIs from Taizhou Cancer Hospital.
[RESULTS] The results show that stain normalization, multi-scale fusion, and multi-feature fusion significantly improve classification performance. In 10-fold cross-validation on the internal dataset, the system demonstrated significant improvements over the baseline RetCCL model: AUC (0.9900 vs. 0.9629), accuracy (0.9594 vs. 0.8951), with relative improvements of 2.8% in AUC and 7.2% in accuracy. Precision increased by 11.5% (0.9434 vs. 0.8461) and F1-score by 9.8% (0.9511 vs. 0.8665). On the external validation dataset, the model maintained robust performance with an AUC of 0.9584, accuracy of 0.9070, precision of 0.9247, and F1-score of 0.9348, confirming its reliability and applicability.
[CONCLUSIONS] We propose a weakly supervised MIL framework integrating multi-scale analysis and cross-model feature fusion for thyroid cancer diagnosis. Our method showed promising and consistent results across internal and external datasets. While further clinical validation and workflow integration are needed, the results suggest the potential of this approach to assist pathologists in diagnostic workflows, particularly in resource-constrained settings.
🏷️ 키워드 / MeSH 📖 같은 키워드 OA만
같은 제1저자의 인용 많은 논문 (5)
- Progress of clinical research on fractional laser treatment of androgenetic alopecia: A review article.
- Efficacy and Safety of Botulinum Toxin Type A for Treatment of Glabellar Lines: A Network Meta-Analysis of Randomized Controlled Trials.
- Sunken Upper Eyelid Deformity Correction by Orbital Fat Pad Repositioning and Orbicularis Oculi Muscle Folding in Blepharoplasty.
- Forehead Fat Grafting: Asian Facial Contouring and Augmentation.
- Effects of Virtual Reality-Based Cognitive Behavioral Therapy on Sick Role Adaptation for Patients With Colorectal Cancer: A Randomised Controlled Trial.
🏷️ 같은 키워드 · 무료전문 — 이 논문 MeSH/keyword 기반
- A Phase I Study of Hydroxychloroquine and Suba-Itraconazole in Men with Biochemical Relapse of Prostate Cancer (HITMAN-PC): Dose Escalation Results.
- Self-management of male urinary symptoms: qualitative findings from a primary care trial.
- Clinical and Liquid Biomarkers of 20-Year Prostate Cancer Risk in Men Aged 45 to 70 Years.
- Diagnostic accuracy of Ga-PSMA PET/CT versus multiparametric MRI for preoperative pelvic invasion in the patients with prostate cancer.
- Association of patient health education with the postoperative health related quality of life in low- intermediate recurrence risk differentiated thyroid cancer patients.
- Early local immune activation following intra-operative radiotherapy in human breast tissue.