Rapid histology of laryngeal squamous cell carcinoma with deep-learning based stimulated Raman scattering microscopy

TLDR

Accurate, rapid intraoperative histology is essential in larynx surgery to maximize tumor removal while preserving healthy tissue. The study aims to test whether deep‑learning stimulated Raman scattering microscopy can automatically diagnose laryngeal squamous cell carcinoma on fresh, unprocessed specimens. The authors imaged 80 paired frozen sections with SRS and H&E, then used 18,750 SRS fields from 45 fresh surgical specimens to train a 34‑layer residual CNN that classified 33 unseen samples and simulated margin assessment. SRS with deep learning achieved near‑perfect concordance with standard histology (κ > 0.90) and 100 % accuracy on 33 independent specimens, correctly detecting neoplasia even at grossly normal margins.

Abstract

Maximal resection of tumor while preserving the adjacent healthy tissue is particularly important for larynx surgery, hence precise and rapid intraoperative histology of laryngeal tissue is crucial for providing optimal surgical outcomes. We hypothesized that deep-learning based stimulated Raman scattering (SRS) microscopy could provide automated and accurate diagnosis of laryngeal squamous cell carcinoma on fresh, unprocessed surgical specimens without fixation, sectioning or staining. Methods: We first compared 80 pairs of adjacent frozen sections imaged with SRS and standard hematoxylin and eosin histology to evaluate their concordance. We then applied SRS imaging on fresh surgical tissues from 45 patients to reveal key diagnostic features, based on which we have constructed a deep learning based model to generate automated histologic results. 18,750 SRS fields of views were used to train and cross-validate our 34-layered residual convolutional neural network, which was used to classify 33 untrained fresh larynx surgical samples into normal and neoplasia. Furthermore, we simulated intraoperative evaluation of resection margins on totally removed larynxes. Results: We demonstrated near-perfect diagnostic concordance (Cohen's kappa, κ > 0.90) between SRS and standard histology as evaluated by three pathologists. And deep-learning based SRS correctly classified 33 independent surgical specimens with 100% accuracy. We also demonstrated that our method could identify tissue neoplasia at the simulated resection margins that appear grossly normal with naked eyes. Conclusion: Our results indicated that SRS histology integrated with deep learning algorithm provides potential for delivering rapid intraoperative diagnosis that could aid the surgical management of laryngeal cancer.