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

SIMPLE SUMMARY: Testicular cancer predominantly affects young adult men and is the most common cancer affecting this demographic. An important prognostic factor for early-stage disease is the presence of tumours within blood vessels or lymphatic channels, which is termed lymphovascular invasion. This is identified by careful microscopic examination of the tumour after orchidectomy, which is frequently challenging and time-consuming. We trained a proof-of-concept deep learning artificial intelligence algorithm to automatically identify areas suspicious for lymphovascular invasion in digital whole slide images from testicular tumours. Our study demonstrates that automated detection of areas suspicious for lymphovascular invasion by artificial intelligence algorithms is feasible and may prove useful in the context of a decision support tool. 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.