期刊
INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES
卷 22, 期 10, 页码 -出版社
MDPI
DOI: 10.3390/ijms22105385
关键词
pancreatic cancer; convolutional neuronal networks; artificial intelligence; deep learning
资金
- German Research Foundation [Ga 1818/2-3]
- state of Baden-Wurttemberg through bwHPC
- German Research Foundation (DFG) [INST 35/1314-1 FUGG, INST 35/1503-1 FUGG, INST 35/1134-1 FUGG]
- Ministry of Science, Research and the Arts Baden-Wurttemberg (MWK)
This study used deep learning to automatically identify histopathological images of pancreatic tissue specimens, achieving identification of different anatomical tissue structures and diseases. The convolutional neuronal network and optimized algorithm allowed for automatic localization and quantification of lesions in whole tissue slides. This approach serves as a valuable tool for routine diagnostic review and research in pancreatic cancer.
Identification of pancreatic ductal adenocarcinoma (PDAC) and precursor lesions in histological tissue slides can be challenging and elaborate, especially due to tumor heterogeneity. Thus, supportive tools for the identification of anatomical and pathological tissue structures are desired. Deep learning methods recently emerged, which classify histological structures into image categories with high accuracy. However, to date, only a limited number of classes and patients have been included in histopathological studies. In this study, scanned histopathological tissue slides from tissue microarrays of PDAC patients (n = 201, image patches n = 81.165) were extracted and assigned to a training, validation, and test set. With these patches, we implemented a convolutional neuronal network, established quality control measures and a method to interpret the model, and implemented a workflow for whole tissue slides. An optimized EfficientNet algorithm achieved high accuracies that allowed automatically localizing and quantifying tissue categories including pancreatic intraepithelial neoplasia and PDAC in whole tissue slides. SmoothGrad heatmaps allowed explaining image classification results. This is the first study that utilizes deep learning for automatic identification of different anatomical tissue structures and diseases on histopathological images of pancreatic tissue specimens. The proposed approach is a valuable tool to support routine diagnostic review and pancreatic cancer research.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据