Scholarlink

<p>Current gastric cancer (GCa) risk systems are prone to errors since they evaluate a visual estimation of intestinal metaplasia percentages in histopathology images of gastric mucosa to assign a risk. This study presents an automated method to detect and quantify intestinal metaplasia using deep convolutional neural networks as well as a comparative analysis with visual estimations of three pathologists. Gastric samples were collected from two different cohorts: 149 asymptomatic volunteers from a region with a high prevalence of GCa in Colombia and 56 patients from a tertiary hospital. Deep learning models were trained to classify intestinal metaplasia, and predictions were used to estimate a percentage of intestinal metaplasia and to assign an adapted OLGIM stage. Atrophy was not assessed because of the limited reproducibility among pathologists. Results were compared with independent blinded metaplastic assessments performed by three graduated pathologists. The best-performing deep learning architecture classified intestinal metaplasia with F1-Score of <InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(0.80 \pm 0.01\)</EquationSource> </InlineEquation> and AUC of <InlineEquation ID="IEq2"> <EquationSource Format="TEX">\(0.91 \pm 0.01\)</EquationSource> </InlineEquation>. Among pathologists, inter-observer agreement by a Fleiss’s Kappa score ranged from 0.20 to 0.48. In comparison, agreement between the pathologists and the best-performing model ranged from 0.12 to 0.35. Deep learning models show potential to reliably detect and quantify the percentage of intestinal metaplasia, achieving high classification performance. In practice, visual estimation is still the only available method, yet it is marked by considerable inter-observer variability. Deep learning models provide consistent estimates that could help reduce this subjectivity in risk stratification.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Towards deep-learning based detection and quantification of intestinal metaplasia on digitized gastric biopsies: a multi-expert comparative study

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年2月26日

查看全文
  • Fabian Cano,
  • Mauricio Caviedes,
  • Andres Siabatto,
  • Jesus Villarreal,
  • Jose Quijano,
  • Álvaro Bedoya-Urresta,
  • Marino Coral Bedoya,
  • Yomaira Yepez Caicedo,
  • Angel Cruz-Roa,
  • Fabio A. González,
  • Satish E. Viswanath,
  • Eduardo Romero

摘要

Current gastric cancer (GCa) risk systems are prone to errors since they evaluate a visual estimation of intestinal metaplasia percentages in histopathology images of gastric mucosa to assign a risk. This study presents an automated method to detect and quantify intestinal metaplasia using deep convolutional neural networks as well as a comparative analysis with visual estimations of three pathologists. Gastric samples were collected from two different cohorts: 149 asymptomatic volunteers from a region with a high prevalence of GCa in Colombia and 56 patients from a tertiary hospital. Deep learning models were trained to classify intestinal metaplasia, and predictions were used to estimate a percentage of intestinal metaplasia and to assign an adapted OLGIM stage. Atrophy was not assessed because of the limited reproducibility among pathologists. Results were compared with independent blinded metaplastic assessments performed by three graduated pathologists. The best-performing deep learning architecture classified intestinal metaplasia with F1-Score of \(0.80 \pm 0.01\) and AUC of \(0.91 \pm 0.01\) . Among pathologists, inter-observer agreement by a Fleiss’s Kappa score ranged from 0.20 to 0.48. In comparison, agreement between the pathologists and the best-performing model ranged from 0.12 to 0.35. Deep learning models show potential to reliably detect and quantify the percentage of intestinal metaplasia, achieving high classification performance. In practice, visual estimation is still the only available method, yet it is marked by considerable inter-observer variability. Deep learning models provide consistent estimates that could help reduce this subjectivity in risk stratification.