Deep Learning in Pancreatic Tissue: Identification of Anatomical Structures, Pancreatic Intraepithelial Neoplasia, and Ductal Adenocarcinoma

Abstract

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.

Setting the Research Agenda for Clinical Artificial Intelligence in Pancreatic Adenocarcinoma Imaging

“…Three publications focused on AI for the histopathological diagnosis of PDAC. Fu et al (2021) and Naito et al (2021) proposed DL approaches for PDAC diagnosis and segmentation in WSI, while Kriegsmann et al (2021) were the first to utilise DL to automatically identify different anatomical tissue structures and diseases on WSI [ 8 , 47 , 48 ]. AI validation is limited.…”

“…Three publications focused on AI for the histopathological diagnosis of PDAC. [8,47,48]. AI validation is limited.…”

Tumour Size and T-Stage in Pancreatic Cancer Resection Specimens Depend on the Pathology Examination Approach

“…This puts at risk the meaningfulness of comparing stage-related outcomes between institutions, to the detriment of patient management, clinical research and cancer registries. Even if, in the not-too-far future, artificial-intelligence-assisted tumour size measurement may overcome current obstacles, study cohorts with correctly measured pancreatic cancers will be invaluable for establishing a robust ground truth [31].…”

Robust deep learning model for prognostic stratification of pancreatic ductal adenocarcinoma patients

“…Studies ( Cheerla and Gevaert, 2019 ; Peng et al., 2020 ) have demonstrated that WSI data alone, as well as together with genomic data, can achieve a remarkable performance in cancer prognosis prediction. However, most pancreatic cancer-specific studies using WSI data focused on diagnosis, i.e., pancreatic cancer detection and segmentation ( Fu et al., 2021 ; Kriegsmann et al., 2021 ; Le et al, 2019 ). The predictive value of WSI for prognosis purpose has not been rigorously shown in pancreatic cancer.…”