The Potential of Artificial Intelligence to Detect Lymphovascular Invasion in Testicular Cancer

Abstract

Testicular cancer is the most common cancer in men aged from 15 to 34 years. Lymphovascular invasion refers to the presence of tumours within endothelial-lined lymphatic or vascular channels, and has been shown to have prognostic significance in testicular germ cell tumours. In non-seminomatous tumours, lymphovascular invasion is the most powerful prognostic factor for stage 1 disease. For the pathologist, searching multiple slides for lymphovascular invasion can be highly time-consuming. The aim of this retrospective study was to develop and assess an artificial intelligence algorithm that can identify areas suspicious for lymphovascular invasion in histological digital whole slide images. Areas of possible lymphovascular invasion were annotated in a total of 184 whole slide images of haematoxylin and eosin (H&E) stained tissue from 19 patients with testicular germ cell tumours, including a mixture of seminoma and non-seminomatous cases. Following consensus review by specialist uropathologists, we trained a deep learning classifier for automatic segmentation of areas suspicious for lymphovascular invasion. The classifier identified 34 areas within a validation set of 118 whole slide images from 10 patients, each of which was reviewed by three expert pathologists to form a majority consensus. The precision was 0.68 for areas which were considered to be appropriate to flag, and 0.56 for areas considered to be definite lymphovascular invasion. An artificial intelligence tool which highlights areas of possible lymphovascular invasion to reporting pathologists, who then make a final judgement on its presence or absence, has been demonstrated as feasible in this proof-of-concept study. Further development is required before clinical deployment.

Ki-67 assessment of pancreatic neuroendocrine neoplasms: Systematic review and meta-analysis of manual vs. digital pathology scoring

“…ARM, which is basically a modified microscope associated with an attached computer unit, enables real-time image analysis using a traditional light microscope and glass slides, without the need to first photograph or digitize slides 36 , 44 , 45 . If coupled with image analysis software, ARM allows quantifying immunohistochemical stains including Ki-67, and can also be combined with elaborate AI-based algorithms to perform more complex tasks 44 – 46 . Like other DIA methods, ARM has significant potential for improving PanNEN grading on cell block material 36 .…”

Deep learning for subtypes identification of pure seminoma of the testis

“…DL approaches applied to histopathological slide images aim to significantly speed up the diagnosis and simplify their implementation into clinical workflow. DL approached were previously applied to TGCTs WSIs to detecting tumor-infiltrating lymphocytes [18], to detect lymphovascular invasion [19]. However, to the best of our knowledge, seminomas and TGCTs histology images have not been extensively studied using DL methods.…”

Digital Pathology Transformation in a Supraregional Germ Cell Tumour Network

“…While algorithms with European Conformity in vitro device (CE IVD) approval enabling diagnostic use exist in other tumour types, such as prostate biopsy reporting [ 29 , 30 ], very little has been published on the potential use of AI in testicular germ cell tumours. One report focused on the automated detection of LVI by AI [ 31 ] and another on the prognostic impact of tumour infiltrating lymphocytes [ 32 ]. In general terms, these tumours, being relatively rare, have limited datasets for algorithm building and marked heterogeneity due to mixed tumour typing makes the training and validation of AI more challenging; thus, such tools remain at relatively early stages in the roadmap to clinical deployment [ 33 ].…”