Next Article in Journal
Current Concepts of Non-Coding RNAs in the Pathogenesis of Non-Clear Cell Renal Cell Carcinoma
Next Article in Special Issue
Secondary Somatic Mutations in G-Protein-Related Pathways and Mutation Signatures in Uveal Melanoma
Previous Article in Journal
The CD73/Ado System—A New Player in RT Induced Adverse Late Effects
Previous Article in Special Issue
Real-World Impact of Immune Checkpoint Inhibitors in Metastatic Uveal Melanoma
Open AccessArticle

Prediction of BAP1 Expression in Uveal Melanoma Using Densely-Connected Deep Classification Networks

1
School of Automation, Beijing University of Posts and Telecommunications, Beijing 100876, China
2
Engineering Research Center of Information Network, Ministry of Education, Beijing 100876, China
3
St. Erik Eye Hospital, Polhemsgatan 50, 112 82 Stockholm, Sweden
4
Department of Oncology and Pathology, Karolinska Institutet, 171 76 Stockholm, Sweden
5
Department of Clinical Neuroscience, Karolinska Institutet, 171 76 Stockholm, Sweden
6
Departments of Ophthalmology and Pathology, Emory University School of Medicine, Atlanta, GA 30322, USA
*
Authors to whom correspondence should be addressed.
These authors contributed equally to the research.
Cancers 2019, 11(10), 1579; https://doi.org/10.3390/cancers11101579
Received: 23 September 2019 / Revised: 9 October 2019 / Accepted: 14 October 2019 / Published: 16 October 2019
(This article belongs to the Special Issue Uveal Melanoma)
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. View Full-Text
Keywords: BAP1 expression prediction; ophthalmic histopathology images; densely-connected network; deep learning; immunohistochemistry; precision medicine; artificial intelligence BAP1 expression prediction; ophthalmic histopathology images; densely-connected network; deep learning; immunohistochemistry; precision medicine; artificial intelligence
Show Figures

Figure 1

MDPI and ACS Style

Sun, M.; Zhou, W.; Qi, X.; Zhang, G.; Girnita, L.; Seregard, S.; Grossniklaus, H.E.; Yao, Z.; Zhou, X.; Stålhammar, G. Prediction of BAP1 Expression in Uveal Melanoma Using Densely-Connected Deep Classification Networks. Cancers 2019, 11, 1579.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop