SurGen: 1020 H&E-stained whole slide images with survival and genetic markers

Craig Myles; In Um; Craig Marshall; David Harris-Birtill; David Harrison

doi:10.1093/gigascience/giaf086

SurGen: 1020 H&E-stained whole slide images with survival and genetic markers

Craig Myles^*, In Um, Craig Marshall, David Harris-Birtill, David Harrison

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

Abstract

Background: Cancer remains one of the leading causes of morbidity and mortality worldwide. Comprehensive datasets that combine histopathological images with genetic and survival data across various tumour sites are essential for advancing computational pathology and personalised medicine.

Results: We present SurGen, a dataset comprising 1,020 H&E-stained whole-slide images (WSIs) from 843 colorectal cancer cases. The dataset includes detailed annotations for key genetic mutations (KRAS, NRAS, BRAF) and mismatch repair status, as well as survival data for 426 cases. We illustrate SurGen’s utility with a proof-of-concept model that predicts mismatch repair status directly from WSIs, achieving a test area under the receiver operating characteristic curve of 0.8273. These preliminary results underscore the dataset’s potential to facilitate research in biomarker discovery, prognostic modelling, and advanced machine learning applications in colorectal cancer and beyond.

Conclusions: SurGen offers a valuable resource for the scientific community, enabling studies that require high-quality WSIs linked with comprehensive clinical and genetic information on colorectal cancer. Our initial findings affirm the dataset’s capacity to advance diagnostic precision and foster the development of personalised treatment strategies in colorectal oncology.

Original language	English
Article number	giaf086
Pages (from-to)	1-16
Number of pages	16
Journal	GigaScience
Volume	14
Early online date	8 Oct 2025
DOIs	https://doi.org/10.1093/gigascience/giaf086
Publication status	Published - 2025

Keywords

Whole-slide image (WSI)
Hematoxylin and eosin (H&E) stain
Mismatch repair (MMR)
Microsatellite instability (MSI)
KRAS mutation
NRAS mutation
BRAF mutation
Colorectal cancer
Digital pathology
Dataset

Access to Document

10.1093/gigascience/giaf086Licence: CC BY

Myles-et-al-2025-SurGen-H&E-stained-whole-slides-GigaSci-giaf086-CCBY
Copyright © The Author(s) 2025. Published by Oxford University Press on behalf of GigaScience. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted reuse, distribution, and reproduction in any medium, provided the original work is properly cited.
Final published version, 2.45 MBLicence: CC BY

Handle.net

Persistent link

Cite this

@article{7f93510495bc400784fe61059b0f8d08,

title = "SurGen: 1020 H\&E-stained whole slide images with survival and genetic markers",

abstract = "Background: Cancer remains one of the leading causes of morbidity and mortality worldwide. Comprehensive datasets that combine histopathological images with genetic and survival data across various tumour sites are essential for advancing computational pathology and personalised medicine. Results: We present SurGen, a dataset comprising 1,020 H\&E-stained whole-slide images (WSIs) from 843 colorectal cancer cases. The dataset includes detailed annotations for key genetic mutations (KRAS, NRAS, BRAF) and mismatch repair status, as well as survival data for 426 cases. We illustrate SurGen{\textquoteright}s utility with a proof-of-concept model that predicts mismatch repair status directly from WSIs, achieving a test area under the receiver operating characteristic curve of 0.8273. These preliminary results underscore the dataset{\textquoteright}s potential to facilitate research in biomarker discovery, prognostic modelling, and advanced machine learning applications in colorectal cancer and beyond. Conclusions: SurGen offers a valuable resource for the scientific community, enabling studies that require high-quality WSIs linked with comprehensive clinical and genetic information on colorectal cancer. Our initial findings affirm the dataset{\textquoteright}s capacity to advance diagnostic precision and foster the development of personalised treatment strategies in colorectal oncology. ",

keywords = "Whole-slide image (WSI), Hematoxylin and eosin (H\&E) stain, Mismatch repair (MMR), Microsatellite instability (MSI), KRAS mutation, NRAS mutation, BRAF mutation, Colorectal cancer, Digital pathology, Dataset",

author = "Craig Myles and In Um and Craig Marshall and David Harris-Birtill and David Harrison",

note = "Funding: C.M. is supported by NHS Lothian. This work is supported in part by the Industrial Centre for AI Research in Digital Diagnostics (iCAIRD), which is funded by Innovate UK on behalf of UK Research and Innovation (UKRI) (project number 104690).",

year = "2025",

doi = "10.1093/gigascience/giaf086",

language = "English",

volume = "14",

pages = "1--16",

journal = "GigaScience",

issn = "2047-217X",

publisher = "Oxford University Press",

}

TY - JOUR

T1 - SurGen: 1020 H&E-stained whole slide images with survival and genetic markers

AU - Myles, Craig

AU - Um, In

AU - Marshall, Craig

AU - Harris-Birtill, David

AU - Harrison, David

N1 - Funding: C.M. is supported by NHS Lothian. This work is supported in part by the Industrial Centre for AI Research in Digital Diagnostics (iCAIRD), which is funded by Innovate UK on behalf of UK Research and Innovation (UKRI) (project number 104690).

PY - 2025

Y1 - 2025

N2 - Background: Cancer remains one of the leading causes of morbidity and mortality worldwide. Comprehensive datasets that combine histopathological images with genetic and survival data across various tumour sites are essential for advancing computational pathology and personalised medicine. Results: We present SurGen, a dataset comprising 1,020 H&E-stained whole-slide images (WSIs) from 843 colorectal cancer cases. The dataset includes detailed annotations for key genetic mutations (KRAS, NRAS, BRAF) and mismatch repair status, as well as survival data for 426 cases. We illustrate SurGen’s utility with a proof-of-concept model that predicts mismatch repair status directly from WSIs, achieving a test area under the receiver operating characteristic curve of 0.8273. These preliminary results underscore the dataset’s potential to facilitate research in biomarker discovery, prognostic modelling, and advanced machine learning applications in colorectal cancer and beyond. Conclusions: SurGen offers a valuable resource for the scientific community, enabling studies that require high-quality WSIs linked with comprehensive clinical and genetic information on colorectal cancer. Our initial findings affirm the dataset’s capacity to advance diagnostic precision and foster the development of personalised treatment strategies in colorectal oncology.

AB - Background: Cancer remains one of the leading causes of morbidity and mortality worldwide. Comprehensive datasets that combine histopathological images with genetic and survival data across various tumour sites are essential for advancing computational pathology and personalised medicine. Results: We present SurGen, a dataset comprising 1,020 H&E-stained whole-slide images (WSIs) from 843 colorectal cancer cases. The dataset includes detailed annotations for key genetic mutations (KRAS, NRAS, BRAF) and mismatch repair status, as well as survival data for 426 cases. We illustrate SurGen’s utility with a proof-of-concept model that predicts mismatch repair status directly from WSIs, achieving a test area under the receiver operating characteristic curve of 0.8273. These preliminary results underscore the dataset’s potential to facilitate research in biomarker discovery, prognostic modelling, and advanced machine learning applications in colorectal cancer and beyond. Conclusions: SurGen offers a valuable resource for the scientific community, enabling studies that require high-quality WSIs linked with comprehensive clinical and genetic information on colorectal cancer. Our initial findings affirm the dataset’s capacity to advance diagnostic precision and foster the development of personalised treatment strategies in colorectal oncology.

KW - Whole-slide image (WSI)

KW - Hematoxylin and eosin (H&E) stain

KW - Mismatch repair (MMR)

KW - Microsatellite instability (MSI)

KW - KRAS mutation

KW - NRAS mutation

KW - BRAF mutation

KW - Colorectal cancer

KW - Digital pathology

KW - Dataset

UR - https://www.scopus.com/pages/publications/105020612965

U2 - 10.1093/gigascience/giaf086

DO - 10.1093/gigascience/giaf086

M3 - Article

SN - 2047-217X

VL - 14

SP - 1

EP - 16

JO - GigaScience

JF - GigaScience

M1 - giaf086

ER -

SurGen: 1020 H&E-stained whole slide images with survival and genetic markers

Abstract

Keywords

Access to Document

Handle.net

Other files and links

Fingerprint

ICAIRD: I-CAIRD: Industrial Centre for AI Research in Digital Diagnostics

ICAIRD: I-CAIRD: Industrial Centre for AI Research in Digital Diagnostics

Supporting data for "SurGen: 1020 H&E-stained Whole Slide Images With Survival and Genetic Markers"