Abstract
Uveal melanoma is the most common primary intraocular malignancy in adults, with nearly half of all patients eventually developing metastases, which are invariably fatal. Manual assessment of the level of expression of the tumor suppressor BRCA1-associated protein 1 (BAP1) in tumor cell nuclei can identify patients with a high risk of developing metastases, but may suffer from poor reproducibility. In this study, we verified whether artificial intelligence could predict manual assessments of BAP1 expression in 47 enucleated eyes with uveal melanoma, collected from one European and one American referral center. Digitally scanned pathology slides were divided into 8176 patches, each with a size of 256 × 256 pixels. These were in turn divided into a training cohort of 6800 patches and a validation cohort of 1376 patches. A densely-connected classification network based on deep learning was then applied to each patch. This achieved a sensitivity of 97.1%, a specificity of 98.1%, an overall diagnostic accuracy of 97.1%, and an F1-score of 97.8% for the prediction of BAP1 expression in individual high resolution patches, and slightly less with lower resolution. The area under the receiver operating characteristic (ROC) curves of the deep learning model achieved an average of 0.99. On a full tumor level, our network classified all 47 tumors identically with an ophthalmic pathologist. We conclude that this deep learning model provides an accurate and reproducible method for the prediction of BAP1 expression in uveal melanoma.
Highlights
Uveal melanoma is the most common primary intraocular malignancy among adults
Reliable identification of the group of patients that will develop metastases is key in uveal melanoma prognostication, and a prerequisite for developing an effective treatment to improve outcome
Previous studies showed that expression levels of SPANX-C, ADAM 10, and Raf kinase inhibitor protein are associated with metastatic progression of uveal melanoma [7,8,9]
Summary
Uveal melanoma is the most common primary intraocular malignancy among adults. Incidence reaches four to 10 cases per million inhabitants and year, partially depending on geographic location and skin tone [1,2,3,4]. Reliable identification of the group of patients that will develop metastases is key in uveal melanoma prognostication, and a prerequisite for developing an effective treatment to improve outcome. Several methods have been proposed and implemented, including gene expression assays that show excellent prognostic utility [6]. These may not be universally available in clinical routine. BAP1 is one of the most important tumor suppression factors expressed by gene BAP1 [10]. Mutational inactivation of this tumor suppressor is a key event in the acquisition of metastatic competence in uveal melanoma [11]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have