A novel two-stage deep learning model used to assist in diagnosing neonatal necrotizing enterocolitis and determining the need for surgical treatment

Abstract

Background and Aims: Neonatal necrotizing enterocolitis (NEC) is a common life-threatening gastrointestinal disease in newborns. Abdominal X-rays (AXRs) is an important basis for diagnosing NEC and determining the need for surgical treatment. Computer-aided diagnosis (CAD) is extensively utilized in the clinical diagnosis of numerous diseases. Nevertheless, the efficacy of CAD for NEC has not been widely validated. Methods: We proposed for the first time a two-stage multimodal classification method for NEC based on AXRs data. The objective is to achieve early diagnosis of NEC and determine the optimal timing for surgical intervention. This method addresses the problem of insufficient labeled data through transfer learning and introduces coordinate attention to enhance the accuracy of target region localization and identification, thereby improving the capability of image feature extraction. Results: In total, the dataset was sourced from 2 children’s hospital consisted of 3,176 AXRs from 845 newborns diagnosed with NEC. Additionally, there were 1,825 AXRs from 470 newborns without NEC. The task for determining whether newborns has NEC achieved an accuracy of 97.49%, recall of 97.44%, precision of 83.09%, F1-score of 98.02% and AUC of 99.68%. Similarly, for the task of identifying if NEC patients require surgery, the accuracy, recall, precision, and F1-score were 78.96%, 81.50%, 80.30%, 80.89%, and 84.49% respectively. Our method performed better than the four commonly used baseline methods in the two-stage NEC diagnosis task. Conclusions: We have introduced a novel two-stage diagnostic model for NEC in newborns, which can rapidly and accurately identify NEC patients and determine if surgery is necessary.