在使用深度学习模型的组织病理性胃活检中检测Helicobacter pylori感染
Rafael Parra-Medina1,2,3,4, Carlos Zambrano-Betancourt2,4, Sergio Peña-Rojas4
1Departamento de Patología, Fundación Universitaria de Ciencias de la Salud (FUCS), Bogotá 111411, Colombia.
Journal of imaging
|July 25, 2025
概括
深层卷积神经网络 (DCNNs) 在数字病理学图像中显示出用于诊断Helicobacter pylori (HP) 胃炎的潜力. InceptionV3实现了高精度,超过了AutoML方法,并表明了改进诊断工作流程的潜力.
科学领域:
- 数字病理学数字病理学
- 计算病理学计算病理学
- 医学图像分析 医学图像分析
背景情况:
- 传统的Helicobacter pylori (HP) 胃炎诊断依赖于手动显微镜检查H&E染色的胃活检.
- 数字病理引入了诸如图像分辨率限制和HP检测中的观察者间变异性等挑战.
- 深度卷积神经网络 (DCNN) 提供了全幻灯片图像 (WSI) 中自动和准确的HP识别的潜力.
研究的目的:
- 评估DCNN和AutoML模型在组织病理性胃活检样本中检测HP感染的疗效.
- 为了比较各种预训练的DCNN架构 (InceptionV3,Resnet50,VGG16) 和AutoML方法的性能.
- 评估HP胃炎数字病理学的自动化方法的诊断准确性和可靠性.
主要方法:
- 开发和验证DCNN和AutoML模型,使用100个H&E染色胃活检WSI的数据集.
- 选择45,795个补丁用于模型培训和开发.
- 在数据集中使用免疫组织化学来预先确认HP感染.
- 使用AUC,准确性,回忆,F1分数和MCC等指标进行性能评估.
主要成果:
- 发明V3,Resnet50和VGG16实现了曲线下的面积 (AUC) 为1.
- InceptionV3表现出卓越的性能,准确率为97%,回忆率为100%,F1得分为97%,MCC为93%.
- 在关键指标上,AutoML模型 (BoostedNet,AutoKeras) 的表现低于85%.
- 在InceptionV3的外部验证中,总的准确率为78%.
结论:
- 与AutoML方法相比,DCNN模型在胃活检中对诊断HP感染具有显著的潜力.
- 最佳模型性能在不同的病理学应用中可能会有所不同,因此需要针对问题的具体方法.
- 在数字病理学中采用DCNN可以提高诊断准确性,减少变化,并简化HP胃炎检测工作流程.
相关概念视频
01:28Peptic Ulcer Disease III: Clinical Manifestations and Diagnostic Studies
202
Peptic ulcer disease (PUD) presents with diverse symptoms depending on the location and severity of the ulcer. Clinical manifestations of peptic ulcer include dull pain and a burning sensation in the mid-epigastric region.
Few clinical manifestations differentiate gastric ulcers from duodenal ulcers. Distinctions in the location, timing, and pain relief are crucial for healthcare providers in differentiating between gastric and duodenal ulcers during clinical assessments.
Few clinical manifestations differentiate gastric ulcers from duodenal ulcers. Distinctions in the location, timing, and pain relief are crucial for healthcare providers in differentiating between gastric and duodenal ulcers during clinical assessments.
202
01:16Treating Helicobacter pylori in Peptic Ulcers: Antimicrobial Therapy
549
Helicobacter pylori, a resilient gram-negative bacterium, can thrive in the stomach's harsh, acidic environment. Infection with H. pylori leads to a cascade of events within the stomach lining. One of the critical disruptions caused by this bacterium is the interference with somatostatin production, a hormone responsible for regulating acid secretion. This interference tips the balance, escalating acid secretion and diminishing bicarbonate levels. This imbalance compromises the defensive...
549