Deep learning-based classification of desmoplastic reaction on H&E predicts poor prognosis in esophageal squamous cell carcinoma.

Researchers

Journal

Modalities

Models

Abstract

Desmoplastic reaction (DR) categorization has been shown to be a promising prognostic factor in esophageal squamous cell carcinoma (ESCC). Usual DR evaluation is performed using semiquantitative scores which can be subjective. This study aimed to investigate whether a deep-learning classifier could be used for DR classification. We further assess the prognostic significance of the deep-learning classifier and compare it to that of manual DR reporting and other pathological factors currently used in the clinic.From 222 surgically resected ESCC cases, 31 randomly selected hematoxylin-eosin-digitized whole slides of patients with immature DR were used to train and develop a deep-learning classifier. The classifier was trained for 89 370 iterations. The accuracy of the deep-learning classifier was assessed on 30 unseen cases, and results revealed a Dice coefficient score of 0.81. For survival analysis, the classifier was then applied to the entire cohort of patients, which was split into a training (n = 156) and a test (n = 66) cohort. The automated DR classification had a higher prognostic significance for disease-specific survival than the manually classified DR in both the training and test cohorts. In addition, the automated DR classification outperformed the prognostic accuracy of the gold-standard factors of tumor depth and lymph node metastasis.This study demonstrated that DR can be objectively and quantitatively assessed in ESCC using a deep-learning classifier and that automatically classed DR has a higher prognostic significance than manual DR and other features currently used in the clinic.This article is protected by copyright. All rights reserved.