Deep Gaussian process with uncertainty estimation for microsatellite instability and immunotherapy response prediction from histology

Determining tumor microsatellite status has significant clinical value because tumors that are microsatellite instability-high (MSI-H) or mismatch repair deficient (dMMR) respond well to immune checkpoint inhibitors (ICIs) and oftentimes not to chemotherapeutics. We propose MSI-SEER, a deep Gaussian process-based Bayesian model that analyzes H&E whole-slide images in weakly-supervised-learning to predict microsatellite status in gastric and colorectal cancers. We performed extensive validation using multiple large datasets comprised of patients from diverse racial backgrounds. MSI-SEER achieved state-of-the-art performance with MSI prediction by integrating uncertainty prediction. We achieved high accuracy for predicting ICI responsiveness by combining tumor MSI status with stroma-to-tumor ratio. Finally, MSI-SEER's tile-level predictions revealed novel insights into the role of spatial distribution of MSI-H regions in the tumor microenvironment and ICI response.

Authors

Institutions

Publication Details

Journal
npj Digital Medicine
Published
2025-05-19
DOI
https://doi.org/10.1038/s41746-025-01580-8
Citations
5
Primary Topic
Cell Image Analysis Techniques
Type
article
Field-Weighted Citation Impact
8.17

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Deep Gaussian process with uncertainty estimation for microsatellite instability and immunotherapy response prediction from histology

Jae‐Ho Cheong, Sung Hak Lee, Imon Banerjee, Tae Hyun Hwang et al.
5 citations
npj Digital Medicine
Cell Image Analysis Techniques
8.17
article

Deep Gaussian process with uncertainty estimation for microsatellite instability and immunotherapy response prediction from histology

Jae‐Ho Cheong, Sung Hak Lee, Imon Banerjee, Tae Hyun Hwang, Taeil Son, Yoon Jin, Sam C. Wang, Hyunki Kim, Rish K. Pai, N. Jewel Samadder, Ji‐Youn Sung, Jean R. Clemenceau, Inyeop Jang, Minji Kim, Isabel Barnfather, Young-Hoon Kim, Jeonghyun Kang, Jeong Hwan Park, In‐Ho Kim, Sunho Park, Mark Pettigrew
article en
5 citations

Abstract

Determining tumor microsatellite status has significant clinical value because tumors that are microsatellite instability-high (MSI-H) or mismatch repair deficient (dMMR) respond well to immune checkpoint inhibitors (ICIs) and oftentimes not to chemotherapeutics. We propose MSI-SEER, a deep Gaussian process-based Bayesian model that analyzes H&E whole-slide images in weakly-supervised-learning to predict microsatellite status in gastric and colorectal cancers. We performed extensive validation using multiple large datasets comprised of patients from diverse racial backgrounds. MSI-SEER achieved state-of-the-art performance with MSI prediction by integrating uncertainty prediction. We achieved high accuracy for predicting ICI responsiveness by combining tumor MSI status with stroma-to-tumor ratio. Finally, MSI-SEER's tile-level predictions revealed novel insights into the role of spatial distribution of MSI-H regions in the tumor microenvironment and ICI response.

npj Digital MedicineVol. 8(1)
Seoul National University (KR), Yonsei University (KR), Kyung Hee University (KR), St. Mary's Hospital (US), Southwestern Medical Center (US), SNUH SMG-SNU Boramae Medical Center (KR), Mayo Clinic in Arizona (US), Mayo Clinic Hospital (US), Gangnam Severance Hospital (KR), Mayo Clinic in Florida (US), The Catholic University of Korea Seoul St. Mary's Hospital (KR), Yonsei University Health System (KR), The University of Texas Southwestern Medical Center (US), Catholic University of Korea (KR), Vanderbilt University Medical Center (US)
U.S. Department of Defense, University of Texas Southwestern Medical Center, National Research Foundation, Yonsei University, Catholic University of Korea, National Research Foundation of Korea, National Institutes of Health, National Cancer Institute
Climate action
Openalex Percentile: Top 3%
Cell Image Analysis Techniques
8.17
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.