Instance segmentation nei tumori delle vie areo-digestive superiori

Abstract

SUMMARY Objective To achieve instance segmentation of upper aerodigestive tract (UADT) neoplasms using a deep learning (DL) algorithm, and to identify differences in its diagnostic performance in three different sites: larynx/hypopharynx, oral cavity and oropharynx. Methods A total of 1034 endoscopic images from 323 patients were examined under narrow band imaging (NBI). The Mask R-CNN algorithm was used for the analysis. The dataset split was: 935 training, 48 validation and 51 testing images. Dice Similarity Coefficient (Dsc) was the main outcome measure. Results Instance segmentation was effective in 76.5% of images. The mean Dsc was 0.90 ± 0.05. The algorithm correctly predicted 77.8%, 86.7% and 55.5% of lesions in the larynx/hypopharynx, oral cavity, and oropharynx, respectively. The mean Dsc was 0.90 ± 0.05 for the larynx/hypopharynx, 0.60 ± 0.26 for the oral cavity, and 0.81 ± 0.30 for the oropharynx. The analysis showed inferior diagnostic results in the oral cavity compared with the larynx/hypopharynx (p < 0.001). Conclusions The study confirms the feasibility of instance segmentation of UADT using DL algorithms and shows inferior diagnostic results in the oral cavity compared with other anatomic areas.

Real‐Time Laryngeal Cancer Boundaries Delineation on White Light and Narrow‐Band Imaging Laryngoscopy with Deep Learning

“…A possible evolution of semantic segmentation is instance segmentation, which generates a segmentation mask for every single object detected in the image distinguishing among different classes. Our group tried to explore this task discovering that the laryngeal and hypopharyngeal subsites are easier to process by the instance segmentation model compared to oral cavity and oropharynx 23 . Nevertheless, contrary to the present work, the number of images was limited (test set n = 27), and further studies are needed to corroborate those findings.…”