Label-Free Microscopic Hyperspectral Imaging for Papillary Thyroid Carcinoma Photodiagnosis Using Patient-Level Spectral-Spatial Deep Learning
In brief
Hyperspectral imaging classified papillary thyroid cancer with 86% accuracy in 180 patients
In retrospective testing across 180 patients, label-free hyperspectral imaging with a deep-learning model distinguished papillary thyroid cancer from benign thyroid lesions with 86% accuracy and 88% sensitivity. The results suggest an objective aid to pathology, but testing used patient-level cross-validation at one study stage; external and prospective validation are still needed before clinical use.
- Journal
- Photodiagnosis and photodynamic therapy (Q2)
- Published
- 6 October 2026
- Study design
- Cohort / observational study
- Evidence level
- Level 3, Low (CEBM 3b)
- Authors
- Qingying Sun, Feifei Meng, Guangxi Shi, Wenshi Tian, Xulei Wang, Jiazheng Yan, et al.
- PMID
- 42838368
- DOI
- 10.1016/j.pdpdt.2026.105674
Why clinicians should know about it
- Picked for Pathology and Forensic Medicine (top studies of the week, 11 October 2026): HSI differentiates PTC from benign lesions
Abstract
BACKGROUND: Papillary thyroid carcinoma (PTC) may overlap microscopically with Hashimoto thyroiditis (HT) and nodular goiter (NG). Label-free optical assessment that captures morphology and wavelength-dependent tissue contrast could provide an objective adjunct to conventional pathology. METHODS: We retrospectively analyzed 180 patients (72 PTC, 54 HT, and 54 NG). Unstained serial sections were imaged by visible-near-infrared microscopic hyperspectral imaging (400-1000 nm; effective range 420-950 nm), with adjacent hematoxylin-eosin sections as the reference. We developed Thyroid Hyperspectral Imaging Multiple-Instance Learning (ThyroHSI-MIL), a patient-level dual-branch framework combining multi-scale spectral encoding, wavelength attention, spatial feature extraction, gated spectral-spatial fusion, and attention-based multiple-instance aggregation. After white-dark calibration, Savitzky-Golay smoothing, and standard normal variate normalization, model performance was assessed by stratified five-fold patient-level cross-validation. RESULTS: For PTC versus benign lesions, ThyroHSI-MIL achieved an AUC of 0.927, accuracy of 0.856, sensitivity of 0.875, specificity of 0.843, and F1 score of 0.842. Three-class classification achieved a macro-average AUC of 0.903 and accuracy of 0.844. The strongest wavelength-attention peaks occurred near 468 and 530 nm. Ablation analysis supported contributions from the spectral and spatial branches, wavelength attention, gated fusion, and patient-level aggregation. CONCLUSIONS: Label-free microscopic hyperspectral imaging with patient-level spectral-spatial learning accurately differentiated PTC from benign thyroid lesions and provided wavelength- and region-level interpretability. External and prospective validation is warranted before clinical deployment.
Abstract as published, via PubMed.
For healthcare professionals. The summary is generated by AI from the published abstract, and the evidence level is assigned automatically from the study design on the Oxford CEBM hierarchy. Neither is medical advice. Read the full paper before changing practice.