Direct Gene Expression Profile Prediction for Uveal Melanoma from Digital Cytopathology Images via Deep Learning and Salient Image Region Identification

T Y Alvin Liu; Haomin Chen; Catalina Gomez; Zelia M Correa; Mathias Unberath

doi:10.1016/j.xops.2022.100240

Direct Gene Expression Profile Prediction for Uveal Melanoma from Digital Cytopathology Images via Deep Learning and Salient Image Region Identification

Ophthalmol Sci. 2022 Oct 30;3(1):100240. doi: 10.1016/j.xops.2022.100240. eCollection 2023 Mar.

Authors

T Y Alvin Liu¹, Haomin Chen², Catalina Gomez², Zelia M Correa³, Mathias Unberath²

Affiliations

¹ Wilmer Eye Institute, Johns Hopkins University, Baltimore, Maryland.
² Malone Center for Engineering in Healthcare, Johns Hopkins University, Baltimore, Maryland.
³ Bascom Palmer Eye Institute, University of Miami, Miami, Florida.

Abstract

Objective: To demonstrate that deep learning (DL) methods can produce robust prediction of gene expression profile (GEP) in uveal melanoma (UM) based on digital cytopathology images.

Design: Evaluation of a diagnostic test or technology.

Subjects participants and controls: Deidentified smeared cytology slides stained with hematoxylin and eosin obtained from a fine needle aspirated from UM.

Methods: Digital whole-slide images were generated by fine-needle aspiration biopsies of UM tumors that underwent GEP testing. A multistage DL system was developed with automatic region-of-interest (ROI) extraction from digital cytopathology images, an attention-based neural network, ROI feature aggregation, and slide-level data augmentation.

Main outcome measures: The ability of our DL system in predicting GEP on a slide (patient) level. Data were partitioned at the patient level (73% training; 27% testing).

Results: In total, our study included 89 whole-slide images from 82 patients and 121 388 unique ROIs. The testing set included 24 slides from 24 patients (12 class 1 tumors; 12 class 2 tumors; 1 slide per patient). Our DL system for GEP prediction achieved an area under the receiver operating characteristic curve of 0.944, an accuracy of 91.7%, a sensitivity of 91.7%, and a specificity of 91.7% on a slide-level analysis. The incorporation of slide-level feature aggregation and data augmentation produced a more predictive DL model (P = 0.0031).

Conclusions: Our current work established a complete pipeline for GEP prediction in UM tumors: from automatic ROI extraction from digital cytopathology whole-slide images to slide-level predictions. Our DL system demonstrated robust performance and, if validated prospectively, could serve as an image-based alternative to GEP testing.

Keywords: ANN, artificial neural network; Artificial intelligence; CAM, class activation map; Cytopathology; DA, data augmentation; DL, deep learning; Deep learning; FA, feature aggregation; FNAB, fine-needle aspiration biopsy; GEP, gene expression profile; Gene expression profile; ML, machine learning; ROI, region-of-interest; UM, uveal melanoma; Uveal melanoma.