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

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.

Review of Stimulated Raman Scattering Microscopy Techniques and Applications in the Biosciences

“…[ 111 ] Moreover, combined with deep‐learning algorithms, rapid SRS diagnosis was demonstrated to have an excellent ability to identify fresh laryngeal squamous cell carcinoma. [ 112 ] Overall, SRS microscopy combined with Raman tags, flow cytometry, deep‐learning algorithms, or other methods can be an essential tool for cancer histopathology and quantitative cancerous analysis.…”

Spatial light-modulated stimulated Raman scattering (SLM-SRS) microscopy for rapid multiplexed vibrational imaging

“…Thus, the detection of SRL or SRG requires the use of amplitude-modulator and lock-in amplifier to demodulate the SRS signal from the excitation beams. With the high chemical specificity and sensitivity, SRS microscopy has been used for a wide range of biological and biomedical applications 3-6.…”

The deubiquitinase USP34 stabilizes SOX2 and induces cell survival and drug resistance in laryngeal squamous cell carcinoma

“…1,2 In clinic, laryngeal cancer mainly refers to primary laryngeal cancer, and laryngeal squamous cell carcinoma (LSCC) is the most common pathological type of laryngeal cancer, accounting for about 90%. 3 At present, LSCC is mainly treated by surgery, radiotherapy, or chemotherapy. 4 However, the public data shows that the incidence of LSCC has a significant upward trend in recent years due to many factors such as personal bad living habits, environmental pollution, and genetics.…”