Department of Pediatrics, School of Medicine, University of Virginia, Charlottesville, VA.
Department of Paediatrics and Child Health, Aga Khan University, Karachi, Pakistan.
J Pediatr Gastroenterol Nutr. 2021 Jun 1;72(6):833-841. doi: 10.1097/MPG.0000000000003057.
Striking histopathological overlap between distinct but related conditions poses a disease diagnostic challenge. There is a major clinical need to develop computational methods enabling clinicians to translate heterogeneous biomedical images into accurate and quantitative diagnostics. This need is particularly salient with small bowel enteropathies; environmental enteropathy (EE) and celiac disease (CD). We built upon our preliminary analysis by developing an artificial intelligence (AI)-based image analysis platform utilizing deep learning convolutional neural networks (CNNs) for these enteropathies.
Data for the secondary analysis was obtained from three primary studies at different sites. The image analysis platform for EE and CD was developed using CNNs including one with multizoom architecture. Gradient-weighted class activation mappings (Grad-CAMs) were used to visualize the models' decision-making process for classifying each disease. A team of medical experts simultaneously reviewed the stain color normalized images done for bias reduction and Grad-CAMs to confirm structural preservation and biomedical relevance, respectively.
Four hundred and sixty-one high-resolution biopsy images from 150 children were acquired. Median age (interquartile range) was 37.5 (19.0-121.5) months with a roughly equal sex distribution; 77 males (51.3%). ResNet50 and shallow CNN demonstrated 98% and 96% case-detection accuracy, respectively, which increased to 98.3% with an ensemble. Grad-CAMs demonstrated models' ability to learn different microscopic morphological features for EE, CD, and controls.
Our AI-based image analysis platform demonstrated high classification accuracy for small bowel enteropathies which was capable of identifying biologically relevant microscopic features and emulating human pathologist decision-making process. Grad-CAMs illuminated the otherwise "black box" of deep learning in medicine, allowing for increased physician confidence in adopting these new technologies in clinical practice.
不同但相关的疾病之间存在明显的组织病理学重叠，这给疾病诊断带来了挑战。临床医生需要开发能够将异质的生物医学图像转化为准确和定量诊断的计算方法。这一需求在小肠肠病中尤为突出，包括肠病相关的肠功能紊乱（EE）和乳糜泻（CD）。我们在之前的分析基础上，针对这些肠病，建立了一个基于人工智能（AI）的图像分析平台，利用深度学习卷积神经网络（CNN）。
本二次分析的数据来自三个不同地点的初步研究。EE 和 CD 的图像分析平台是使用包括多缩放架构的 CNN 开发的。梯度加权类激活映射（Grad-CAMs）用于可视化模型对每种疾病进行分类的决策过程。一组医学专家同时对经过偏置减少处理的染色颜色归一化图像和 Grad-CAMs 进行审查，以分别确认结构保存和生物医学相关性。
从 150 名儿童中获得了 461 张高分辨率活检图像。中位年龄（四分位间距）为 37.5（19.0-121.5）个月，性别分布大致相等；男性 77 名（51.3%）。ResNet50 和浅层 CNN 的病例检出准确率分别为 98%和 96%，集成后准确率提高到 98.3%。Grad-CAMs 证明了模型学习 EE、CD 和对照不同微观形态特征的能力。
我们的基于 AI 的图像分析平台对小肠肠病的分类准确率很高，能够识别具有生物学意义的微观特征，并模拟人类病理学家的决策过程。Grad-CAMs 阐明了医学中深度学习的“黑箱”问题，使医生更有信心在临床实践中采用这些新技术。
