Instant diagnosis of gastroscopic biopsy via deep-learned single-shot femtosecond stimulated Raman histology
Abstract Gastroscopic biopsy provides the only effective way for gastric cancer diagnosis, but the gold standard histopathology is time-consuming and incompatible with gastroscopy. Conventional stimulated Raman scattering (SRS) microscopy has shown promise in label-free diagnosis on human tissues, yet it requires the tuning of picosecond lasers to achieve chemical specificity at the cost of time and complexity. Here, we demonstrated single-shot femtosecond SRS (femto-SRS) could reach the maximum speed and sensitivity with preserved chemical resolution by integrating with U-Net. Fresh gastroscopic biopsy was imaged in < 60 seconds, revealing essential histoarchitectural hallmarks perfectly agreed with standard histopathology. Moreover, a diagnostic neural network (CNN) was constructed based on images from 279 patients that predicts gastric cancer with accuracy > 96%. We further demonstrated semantic segmentation of intratumor heterogeneity and evaluation of resection margins of endoscopic submucosal dissection (ESD) tissues to simulate rapid and automated intraoperative diagnosis. Our method holds potential for synchronizing gastroscopy and histopathological diagnosis.