TY - JOUR
T1 - Direct Gene Expression Profile Prediction for Uveal Melanoma from Digital Cytopathology Images via Deep Learning and Salient Image Region Identification
AU - Liu, T. Y.Alvin
AU - Chen, Haomin
AU - Gomez, Catalina
AU - Correa, Zelia M.
AU - Unberath, Mathias
N1 - Publisher Copyright:
© 2022 American Academy of Ophthalmology
PY - 2023/3
Y1 - 2023/3
N2 - 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.
AB - 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.
KW - Artificial intelligence
KW - Cytopathology
KW - Deep learning
KW - Gene expression profile
KW - Uveal melanoma
UR - http://www.scopus.com/inward/record.url?scp=85149602451&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85149602451&partnerID=8YFLogxK
U2 - 10.1016/j.xops.2022.100240
DO - 10.1016/j.xops.2022.100240
M3 - Article
C2 - 36561353
AN - SCOPUS:85149602451
SN - 2666-9145
VL - 3
JO - Ophthalmology Science
JF - Ophthalmology Science
IS - 1
M1 - 100240
ER -