Background: Artificial intelligence (AI) is increasingly being used to detect neoplasia and interpret endoscopic images. The T stage of Barrett's carcinoma is a major criterion for subsequent treatment decisions. Although endoscopic ultrasound is still the standard for preoperative staging, its value is debatable. Novel tools are required to assist with staging, to optimize results. This study aimed to investigate the accuracy of T stage of Barrett's carcinoma by an AI system based on endoscopic images.
Methods: 1020 images (minimum one per patient, maximum three) from 577 patients with Barrett's adenocarcinoma were used for training and internal validation of a convolutional neural network. In all, 821 images were selected to train the model and 199 images were used for validation.
Results: AI recognized Barrett's mucosa without neoplasia with an accuracy of 85 % (95 %CI 82.7-87.1). Mucosal cancer was identified with a sensitivity of 72 % (95 %CI 67.5-76.4), specificity of 64 % (95 %CI 60.0-68.4), and accuracy of 68 % (95 %CI 64.6-70.7). The sensitivity, specificity, and accuracy for early Barrett's neoplasia < T1b sm2 were 57 % (95 %CI 51.8-61.0), 77 % (95 %CI 72.3-80.2), and 67 % (95 %CI 63.4-69.5), respectively. More advanced stages (T3/T4) were diagnosed correctly with a sensitivity of 71 % (95 %CI 65.1-76.7) and specificity of 73 % (95 %CI 69.7-76.5). The overall accuracy was 73 % (95 %CI 69.6-75.5).
Conclusions: The AI system identified esophageal cancer with high accuracy, suggesting its potential to assist endoscopists in clinical decision making.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1055/a-1811-9407 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
[Status and prospect of esophageal cancer screening].
Zhonghua Zhong Liu Za Zhi
January 2025
Cancer Registry Office, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing100021, China.
Esophageal cancer is one of the global public health problems, which is a serious threat to life and health. Screening is not only an important main measures to reduce the incidence and mortality of esophageal cancer, but also an effective strategy for early prevention and early treatment. There are significant differences in the screening status of esophageal adenocarcinoma and esophageal squamous cell carcinoma cancer between China and abroad.
View Article and Find Full Text PDFHistological features indicate the risk of progression of patients with Barrett's esophagus.
Pathol Res Pract
January 2025
Department of Pathology and Laboratory Medicine, Penn State Health Hershey Medical Center, Penn State College of Medicine, Hershey, PA 17033, United States. Electronic address:
Our understanding of predictors of progression in Barrett's esophagus (BE) remains incomplete. To address this gap, we evaluated histological features and biomarkers that could predict dysplastic/neoplastic progression in patients with BE. We conducted a retrospective study to identify eligible BE patients and classified the cases into two groups: cases with BE progression (n = 10; progressing to high-grade dysplasia or carcinoma within five years of initial diagnosis) and cases without BE progression (n = 52; without progression to high-grade dysplasia or carcinoma within five years).
View Article and Find Full Text PDF[Telemedicine and AI-supported diagnostics in the daily routine of visceral medicine].
Chirurgie (Heidelb)
January 2025
Universitätsklinik für Viszeralchirurgie - Pius-Hospital Oldenburg, Universitätsmedizin Oldenburg, Oldenburg, Deutschland.
Advances in telemedicine, exemplified by augmented reality (AR) and virtual reality (VR), are rapidly progressing. For instance, AR available over long distances has already been successfully utilized in crisis intervention, such as in war zones. The potential of telemedicine also appears promising in structurally weak areas or in the involvement of experts in emergency situations.
View Article and Find Full Text PDFMicroenvironment and Biomarkers in Esophageal Cancers: An Approach for Early Detection and Identification.
Cureus
November 2024
School of Medicine, Swansea University, Swansea, GBR.
Background Esophageal cancer is a prevalent and highly lethal malignancy worldwide, comprising two main subtypes: esophageal squamous cell carcinoma (ESCC) and esophageal adenocarcinoma (EAC). While both subtypes are frequently encountered, ESCC has historically been more common globally. However, in recent decades, EAC has emerged as the predominant type in industrialized nations, often developing from Barrett's esophagus, a condition driven by chronic gastroesophageal reflux disease (GERD).
View Article and Find Full Text PDFIntraoperative Molecular Imaging With Pafolacianine: Histologic Characteristics of Identified Nodules.
Clin Lung Cancer
November 2024
Cleveland Clinic Lerner College of Medicine of Case Western Reserve University, Cleveland, OH. Electronic address:
Background: With increased early detection efforts, surgery for early-stage lung cancer is expected to rise. Pafolacianine is the first FDA approved targeted optical imaging agent indicated as an adjunct for intraoperative identification of malignant and nonmalignant pulmonary lesions in adult patients with known or suspected cancer in the lung.
Methods: This is a retrospective review of the malignant and nonmalignant lesions identified by pafolacianine with intraoperative molecular imaging (IMI) in the multi-center Phase 2 and Phase 3 ELUCIDATE clinical trials.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!