Categorizing high-grade serous ovarian carcinoma into clinically relevant subgroups using deep learning–based histomic clusters

Background High-grade serous ovarian carcinoma (HGSC) exhibits significant heterogeneity, posing challenges for effective clinical categorization. Understanding the histomorphological diversity within HGSC could lead to improved prognostic stratification and personalized treatment approaches. Method...

Full description

Saved in:
Bibliographic Details
Main Authors: Byungsoo Ahn, Eunhyang Park
Format: Article
Language:English
Published: Korean Society of Pathologists & the Korean Society for Cytopathology 2025-03-01
Series:Journal of Pathology and Translational Medicine
Subjects:
Online Access:http://www.jpatholtm.org/upload/pdf/jptm-2024-10-23.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849762327453237248
author Byungsoo Ahn
Eunhyang Park
author_facet Byungsoo Ahn
Eunhyang Park
author_sort Byungsoo Ahn
collection DOAJ
description Background High-grade serous ovarian carcinoma (HGSC) exhibits significant heterogeneity, posing challenges for effective clinical categorization. Understanding the histomorphological diversity within HGSC could lead to improved prognostic stratification and personalized treatment approaches. Methods We applied the Histomic Atlases of Variation Of Cancers model to whole slide images from The Cancer Genome Atlas dataset for ovarian cancer. Histologically distinct tumor clones were grouped into common histomic clusters. Principal component analysis and K-means clustering classified HGSC samples into three groups: highly differentiated (HD), intermediately differentiated (ID), and lowly differentiated (LD). Results HD tumors showed diverse patterns, lower densities, and stronger eosin staining. ID tumors had intermediate densities and balanced staining, while LD tumors were dense, patternless, and strongly hematoxylin-stained. RNA sequencing revealed distinct patterns in mitochondrial oxidative phosphorylation and energy metabolism, with upregulation in the HD, downregulation in the LD, and the ID positioned in between. Survival analysis showed significantly lower overall survival for the LD compared to the HD and ID, underscoring the critical role of mitochondrial dynamics and energy metabolism in HGSC progression. Conclusions Deep learning-based histologic analysis effectively stratifies HGSC into clinically relevant prognostic groups, highlighting the role of mitochondrial dynamics and energy metabolism in disease progression. This method offers a novel approach to HGSC categorization.
format Article
id doaj-art-96feba3862ab47d98311c9cd39adee2f
institution DOAJ
issn 2383-7837
2383-7845
language English
publishDate 2025-03-01
publisher Korean Society of Pathologists & the Korean Society for Cytopathology
record_format Article
series Journal of Pathology and Translational Medicine
spelling doaj-art-96feba3862ab47d98311c9cd39adee2f2025-08-20T03:05:45ZengKorean Society of Pathologists & the Korean Society for CytopathologyJournal of Pathology and Translational Medicine2383-78372383-78452025-03-015929110410.4132/jptm.2024.10.2317139Categorizing high-grade serous ovarian carcinoma into clinically relevant subgroups using deep learning–based histomic clustersByungsoo Ahn0Eunhyang Park1 Department of Pathology, Severance Hospital, Yonsei University College of Medicine, Seoul, Korea Department of Pathology, Severance Hospital, Yonsei University College of Medicine, Seoul, KoreaBackground High-grade serous ovarian carcinoma (HGSC) exhibits significant heterogeneity, posing challenges for effective clinical categorization. Understanding the histomorphological diversity within HGSC could lead to improved prognostic stratification and personalized treatment approaches. Methods We applied the Histomic Atlases of Variation Of Cancers model to whole slide images from The Cancer Genome Atlas dataset for ovarian cancer. Histologically distinct tumor clones were grouped into common histomic clusters. Principal component analysis and K-means clustering classified HGSC samples into three groups: highly differentiated (HD), intermediately differentiated (ID), and lowly differentiated (LD). Results HD tumors showed diverse patterns, lower densities, and stronger eosin staining. ID tumors had intermediate densities and balanced staining, while LD tumors were dense, patternless, and strongly hematoxylin-stained. RNA sequencing revealed distinct patterns in mitochondrial oxidative phosphorylation and energy metabolism, with upregulation in the HD, downregulation in the LD, and the ID positioned in between. Survival analysis showed significantly lower overall survival for the LD compared to the HD and ID, underscoring the critical role of mitochondrial dynamics and energy metabolism in HGSC progression. Conclusions Deep learning-based histologic analysis effectively stratifies HGSC into clinically relevant prognostic groups, highlighting the role of mitochondrial dynamics and energy metabolism in disease progression. This method offers a novel approach to HGSC categorization.http://www.jpatholtm.org/upload/pdf/jptm-2024-10-23.pdfcarcinoma, ovarian epithelialoxidative phosphorylationenergy metabolismdeep learning
spellingShingle Byungsoo Ahn
Eunhyang Park
Categorizing high-grade serous ovarian carcinoma into clinically relevant subgroups using deep learning–based histomic clusters
Journal of Pathology and Translational Medicine
carcinoma, ovarian epithelial
oxidative phosphorylation
energy metabolism
deep learning
title Categorizing high-grade serous ovarian carcinoma into clinically relevant subgroups using deep learning–based histomic clusters
title_full Categorizing high-grade serous ovarian carcinoma into clinically relevant subgroups using deep learning–based histomic clusters
title_fullStr Categorizing high-grade serous ovarian carcinoma into clinically relevant subgroups using deep learning–based histomic clusters
title_full_unstemmed Categorizing high-grade serous ovarian carcinoma into clinically relevant subgroups using deep learning–based histomic clusters
title_short Categorizing high-grade serous ovarian carcinoma into clinically relevant subgroups using deep learning–based histomic clusters
title_sort categorizing high grade serous ovarian carcinoma into clinically relevant subgroups using deep learning based histomic clusters
topic carcinoma, ovarian epithelial
oxidative phosphorylation
energy metabolism
deep learning
url http://www.jpatholtm.org/upload/pdf/jptm-2024-10-23.pdf
work_keys_str_mv AT byungsooahn categorizinghighgradeserousovariancarcinomaintoclinicallyrelevantsubgroupsusingdeeplearningbasedhistomicclusters
AT eunhyangpark categorizinghighgradeserousovariancarcinomaintoclinicallyrelevantsubgroupsusingdeeplearningbasedhistomicclusters