Your browser doesn't support javascript.
loading
Artificial Intelligence vs. Doctors: Diagnosing Necrotizing Enterocolitis on Abdominal Radiographs.
Weller, Jennine H; Scheese, Daniel; Tragesser, Cody; Yi, Paul H; Alaish, Samuel M; Hackam, David J.
Afiliación
  • Weller JH; Division of Pediatric Surgery, Department of Surgery, Johns Hopkins University School of Medicine, Baltimore, MD, USA.
  • Scheese D; Division of Pediatric Surgery, Department of Surgery, Johns Hopkins University School of Medicine, Baltimore, MD, USA.
  • Tragesser C; Division of Pediatric Surgery, Department of Surgery, Johns Hopkins University School of Medicine, Baltimore, MD, USA.
  • Yi PH; Malone Center for Engineering in Healthcare, Johns Hopkins University School of Medicine, Baltimore, MD, USA; Department of Diagnostic Radiology and Nuclear Medicine, University of Maryland School of Medicine, Baltimore, MD, USA.
  • Alaish SM; Division of Pediatric Surgery, Department of Surgery, Johns Hopkins University School of Medicine, Baltimore, MD, USA.
  • Hackam DJ; Division of Pediatric Surgery, Department of Surgery, Johns Hopkins University School of Medicine, Baltimore, MD, USA. Electronic address: dhackam1@jhmi.edu.
J Pediatr Surg ; 59(10): 161592, 2024 Oct.
Article en En | MEDLINE | ID: mdl-38955625
ABSTRACT

BACKGROUND:

Radiographic diagnosis of necrotizing enterocolitis (NEC) is challenging. Deep learning models may improve accuracy by recognizing subtle imaging patterns. We hypothesized it would perform with comparable accuracy to that of senior surgical residents.

METHODS:

This cohort study compiled 494 anteroposterior neonatal abdominal radiographs (214 images NEC, 280 other) and randomly divided them into training, validation, and test sets. Transfer learning was utilized to fine-tune a ResNet-50 deep convolutional neural network (DCNN) pre-trained on ImageNet. Gradient-weighted Class Activation Mapping (Grad-CAM) heatmaps visualized image regions of greatest relevance to the pretrained neural network. Senior surgery residents at a single institution examined the test set. Resident and DCNN ability to identify pneumatosis on radiographic images were measured via area under the receiver operating curves (AUROC) and compared using DeLong's method.

RESULTS:

The pretrained neural network achieved AUROC of 0.918 (95% CI, 0.837-0.978) with an accuracy of 87.8% with five false negative and one false positive prediction. Heatmaps confirmed appropriate image region emphasis by the pretrained neural network. Senior surgical residents had a median area under the receiver operating curve of 0.896, ranging from 0.778 (95% CI 0.615-0.941) to 0.991 (95% CI 0.971-0.999) with zero to five false negatives and one to eleven false positive predictions. The deep convolutional neural network performed comparably to each surgical resident's performance (p > 0.05 for all comparisons).

CONCLUSIONS:

A deep convolutional neural network trained to recognize pneumatosis can quickly and accurately assist clinicians in promptly identifying NEC in clinical practice. LEVEL OF EVIDENCE III (study type Study of Diagnostic Test, study of nonconsecutive patients without a universally applied "gold standard").
Asunto(s)
Palabras clave

Texto completo: 1 Base de datos: MEDLINE Asunto principal: Radiografía Abdominal / Enterocolitis Necrotizante / Aprendizaje Profundo / Internado y Residencia Límite: Humans / Newborn Idioma: En Revista: J Pediatr Surg Año: 2024 Tipo del documento: Article País de afiliación: Estados Unidos

Texto completo: 1 Base de datos: MEDLINE Asunto principal: Radiografía Abdominal / Enterocolitis Necrotizante / Aprendizaje Profundo / Internado y Residencia Límite: Humans / Newborn Idioma: En Revista: J Pediatr Surg Año: 2024 Tipo del documento: Article País de afiliación: Estados Unidos