Image-based consensus molecular subtyping in rectal cancer biopsies and response to neoadjuvant chemoradiotherapy

Maxime W Lafarge; Enric Domingo; Korsuk Sirinukunwattana; Ruby Wood; Leslie Samuel; Graeme Murray; Susan D Richman; Andrew Blake; David Sebag-Montefiore; Simon Gollins; Eckhard Klieser; Daniel Neureiter; Florian Huemer; Richard Greil; Philip Dunne; Philip Quirke; Lukas Weiss; Jens Rittscher; Tim Maughan; Viktor H Koelzer

doi:10.1038/s41698-024-00580-3

Image-based consensus molecular subtyping in rectal cancer biopsies and response to neoadjuvant chemoradiotherapy

Maxime W Lafarge, Enric Domingo, Korsuk Sirinukunwattana, Ruby Wood, Leslie Samuel, Graeme Murray, Susan D Richman, Andrew Blake, David Sebag-Montefiore, Simon Gollins, Eckhard Klieser, Daniel Neureiter, Florian Huemer, Richard Greil, Philip Dunne, Philip Quirke, Lukas Weiss, Jens Rittscher, Tim Maughan, Viktor H Koelzer^* (Corresponding Author)

^*Corresponding author for this work

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

Abstract

The development of deep learning (DL) models to predict the consensus molecular subtypes (CMS) from histopathology images (imCMS) is a promising and cost-effective strategy to support patient stratification. Here, we investigate whether imCMS calls generated from whole slide histopathology images (WSIs) of rectal cancer (RC) pre-treatment biopsies are associated with pathological complete response (pCR) to neoadjuvant long course chemoradiotherapy (LCRT) with single agent fluoropyrimidine. DL models were trained to classify WSIs of colorectal cancers stained with hematoxylin and eosin into one of the four CMS classes using a multi-centric dataset of resection and biopsy specimens (n = 1057 WSIs) with paired transcriptional data. Classifiers were tested on a held out RC biopsy cohort (ARISTOTLE) and correlated with pCR to LCRT in an independent dataset merging two RC cohorts (ARISTOTLE, n = 114 and SALZBURG, n = 55 patients). DL models predicted CMS with high classification performance in multiple comparative analyses. In the independent cohorts (ARISTOTLE, SALZBURG), cases with WSIs classified as imCMS1 had a significantly higher likelihood of achieving pCR (OR = 2.69, 95% CI 1.01-7.17, p = 0.048). Conversely, imCMS4 was associated with lack of pCR (OR = 0.25, 95% CI 0.07-0.88, p = 0.031). Classification maps demonstrated pathologist-interpretable associations with high stromal content in imCMS4 cases, associated with poor outcome. No significant association was found in imCMS2 or imCMS3. imCMS classification of pre-treatment biopsies is a fast and inexpensive solution to identify patient groups that could benefit from neoadjuvant LCRT. The significant associations between imCMS1/imCMS4 with pCR suggest the existence of predictive morphological features that could enhance standard pathological assessment.

Original language	English
Article number	89
Number of pages	11
Journal	NPJ precision oncology
Volume	8
Issue number	1
Early online date	9 Apr 2024
DOIs	https://doi.org/10.1038/s41698-024-00580-3
Publication status	Published - 9 Apr 2024

Bibliographical note

Acknowledgements
The authors thank Aurelien de Reynies for advice on CMS calling in FFPE blocks, Claire Butler and Michael Youdell for excellent managing in S:CORT and the MRC Clinical Trials Unit who provided the clinical data from the FOCUS trial with permission from the FOCUS trial steering group. The S:CORT consortium is a Medical Research Council stratified medicine consortium jointly funded by the MRC and CRUK (MR/M016587/1). The ARISTOTLE trial was funded by Cancer Research UK (CRUK/08/032). This work was supported by the National Institute for Health Research (NIHR) Oxford Biomedical Research Centre. This work was supported by the Research Fund of the Paracelsus Medical University Salzburg, Austria (PMU-FFF R-17/03/090-HUW). Computation used the CTP Lab core resources at the University of Zurich and the Oxford Biomedical Research Computing (BMRC) facility, a joint development between the Wellcome Centre for Human Genetics and the Big Data Institute supported by Health Data Research UK and the NIHR Oxford Biomedical Research Centre. RW is supported through the EPSRC Center for Doctoral Training in Health Data Science (EP/S02428X/1), Oxford CRUK Cancer Centre. JR is supported through the NIHR Oxford Biomedical Research Centre, the Oxford CRUK Cancer Center, and holds an adjunct appointment at the Ludwig Institute of Cancer Research at the University of Oxford. TM gratefully acknowledges funding by the Medical Research Council and Cancer Research UK. VHK gratefully acknowledges funding by the Swiss National Science Foundation (P2SKP3_168322/1 and P2SKP3_168322/2), and the Promedica Foundation (F-87701-41-01). The results published or shown here are based in part upon data generated by the TCGA Research Network established by the NCI and NHGRI. Information about TCGA and the investigators and institutions who constitute the TCGA research network can be found at http://cancergenome.nih.gov. The funders played no role in the analyses performed or the results presented. The views expressed are those of the author(s) and not necessarily those of the NHS, the NIHR or the Department of Health.

Keywords

Traditional research
Tumour biomarkers

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1038/s41698-024-00580-3Licence: CC BY

Lafarge_etal_NPJ_Image_Based_Consensus_VoR
This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
Final published version, 2.39 MBLicence: CC BY

Cite this

Lafarge, M. W., Domingo, E., Sirinukunwattana, K., Wood, R., Samuel, L., Murray, G., Richman, S. D., Blake, A., Sebag-Montefiore, D., Gollins, S., Klieser, E., Neureiter, D., Huemer, F., Greil, R., Dunne, P., Quirke, P., Weiss, L., Rittscher, J., Maughan, T., & Koelzer, V. H. (2024). Image-based consensus molecular subtyping in rectal cancer biopsies and response to neoadjuvant chemoradiotherapy. NPJ precision oncology, 8(1), Article 89. https://doi.org/10.1038/s41698-024-00580-3

Lafarge, MW, Domingo, E, Sirinukunwattana, K, Wood, R, Samuel, L, Murray, G, Richman, SD, Blake, A, Sebag-Montefiore, D, Gollins, S, Klieser, E, Neureiter, D, Huemer, F, Greil, R, Dunne, P, Quirke, P, Weiss, L, Rittscher, J, Maughan, T & Koelzer, VH 2024, 'Image-based consensus molecular subtyping in rectal cancer biopsies and response to neoadjuvant chemoradiotherapy', NPJ precision oncology, vol. 8, no. 1, 89. https://doi.org/10.1038/s41698-024-00580-3

@article{138edb6f2fe44fc78dda01a56104da74,

title = "Image-based consensus molecular subtyping in rectal cancer biopsies and response to neoadjuvant chemoradiotherapy",

abstract = "The development of deep learning (DL) models to predict the consensus molecular subtypes (CMS) from histopathology images (imCMS) is a promising and cost-effective strategy to support patient stratification. Here, we investigate whether imCMS calls generated from whole slide histopathology images (WSIs) of rectal cancer (RC) pre-treatment biopsies are associated with pathological complete response (pCR) to neoadjuvant long course chemoradiotherapy (LCRT) with single agent fluoropyrimidine. DL models were trained to classify WSIs of colorectal cancers stained with hematoxylin and eosin into one of the four CMS classes using a multi-centric dataset of resection and biopsy specimens (n = 1057 WSIs) with paired transcriptional data. Classifiers were tested on a held out RC biopsy cohort (ARISTOTLE) and correlated with pCR to LCRT in an independent dataset merging two RC cohorts (ARISTOTLE, n = 114 and SALZBURG, n = 55 patients). DL models predicted CMS with high classification performance in multiple comparative analyses. In the independent cohorts (ARISTOTLE, SALZBURG), cases with WSIs classified as imCMS1 had a significantly higher likelihood of achieving pCR (OR = 2.69, 95% CI 1.01-7.17, p = 0.048). Conversely, imCMS4 was associated with lack of pCR (OR = 0.25, 95% CI 0.07-0.88, p = 0.031). Classification maps demonstrated pathologist-interpretable associations with high stromal content in imCMS4 cases, associated with poor outcome. No significant association was found in imCMS2 or imCMS3. imCMS classification of pre-treatment biopsies is a fast and inexpensive solution to identify patient groups that could benefit from neoadjuvant LCRT. The significant associations between imCMS1/imCMS4 with pCR suggest the existence of predictive morphological features that could enhance standard pathological assessment.",

keywords = "Traditional research, Tumour biomarkers",

author = "Lafarge, {Maxime W} and Enric Domingo and Korsuk Sirinukunwattana and Ruby Wood and Leslie Samuel and Graeme Murray and Richman, {Susan D} and Andrew Blake and David Sebag-Montefiore and Simon Gollins and Eckhard Klieser and Daniel Neureiter and Florian Huemer and Richard Greil and Philip Dunne and Philip Quirke and Lukas Weiss and Jens Rittscher and Tim Maughan and Koelzer, {Viktor H}",

note = "Acknowledgements The authors thank Aurelien de Reynies for advice on CMS calling in FFPE blocks, Claire Butler and Michael Youdell for excellent managing in S:CORT and the MRC Clinical Trials Unit who provided the clinical data from the FOCUS trial with permission from the FOCUS trial steering group. The S:CORT consortium is a Medical Research Council stratified medicine consortium jointly funded by the MRC and CRUK (MR/M016587/1). The ARISTOTLE trial was funded by Cancer Research UK (CRUK/08/032). This work was supported by the National Institute for Health Research (NIHR) Oxford Biomedical Research Centre. This work was supported by the Research Fund of the Paracelsus Medical University Salzburg, Austria (PMU-FFF R-17/03/090-HUW). Computation used the CTP Lab core resources at the University of Zurich and the Oxford Biomedical Research Computing (BMRC) facility, a joint development between the Wellcome Centre for Human Genetics and the Big Data Institute supported by Health Data Research UK and the NIHR Oxford Biomedical Research Centre. RW is supported through the EPSRC Center for Doctoral Training in Health Data Science (EP/S02428X/1), Oxford CRUK Cancer Centre. JR is supported through the NIHR Oxford Biomedical Research Centre, the Oxford CRUK Cancer Center, and holds an adjunct appointment at the Ludwig Institute of Cancer Research at the University of Oxford. TM gratefully acknowledges funding by the Medical Research Council and Cancer Research UK. VHK gratefully acknowledges funding by the Swiss National Science Foundation (P2SKP3_168322/1 and P2SKP3_168322/2), and the Promedica Foundation (F-87701-41-01). The results published or shown here are based in part upon data generated by the TCGA Research Network established by the NCI and NHGRI. Information about TCGA and the investigators and institutions who constitute the TCGA research network can be found at http://cancergenome.nih.gov. The funders played no role in the analyses performed or the results presented. The views expressed are those of the author(s) and not necessarily those of the NHS, the NIHR or the Department of Health.",

year = "2024",

month = apr,

day = "9",

doi = "10.1038/s41698-024-00580-3",

language = "English",

volume = "8",

journal = "NPJ precision oncology",

issn = "2397-768X",

number = "1",

}

TY - JOUR

T1 - Image-based consensus molecular subtyping in rectal cancer biopsies and response to neoadjuvant chemoradiotherapy

AU - Lafarge, Maxime W

AU - Domingo, Enric

AU - Sirinukunwattana, Korsuk

AU - Wood, Ruby

AU - Samuel, Leslie

AU - Murray, Graeme

AU - Richman, Susan D

AU - Blake, Andrew

AU - Sebag-Montefiore, David

AU - Gollins, Simon

AU - Klieser, Eckhard

AU - Neureiter, Daniel

AU - Huemer, Florian

AU - Greil, Richard

AU - Dunne, Philip

AU - Quirke, Philip

AU - Weiss, Lukas

AU - Rittscher, Jens

AU - Maughan, Tim

AU - Koelzer, Viktor H

N1 - Acknowledgements The authors thank Aurelien de Reynies for advice on CMS calling in FFPE blocks, Claire Butler and Michael Youdell for excellent managing in S:CORT and the MRC Clinical Trials Unit who provided the clinical data from the FOCUS trial with permission from the FOCUS trial steering group. The S:CORT consortium is a Medical Research Council stratified medicine consortium jointly funded by the MRC and CRUK (MR/M016587/1). The ARISTOTLE trial was funded by Cancer Research UK (CRUK/08/032). This work was supported by the National Institute for Health Research (NIHR) Oxford Biomedical Research Centre. This work was supported by the Research Fund of the Paracelsus Medical University Salzburg, Austria (PMU-FFF R-17/03/090-HUW). Computation used the CTP Lab core resources at the University of Zurich and the Oxford Biomedical Research Computing (BMRC) facility, a joint development between the Wellcome Centre for Human Genetics and the Big Data Institute supported by Health Data Research UK and the NIHR Oxford Biomedical Research Centre. RW is supported through the EPSRC Center for Doctoral Training in Health Data Science (EP/S02428X/1), Oxford CRUK Cancer Centre. JR is supported through the NIHR Oxford Biomedical Research Centre, the Oxford CRUK Cancer Center, and holds an adjunct appointment at the Ludwig Institute of Cancer Research at the University of Oxford. TM gratefully acknowledges funding by the Medical Research Council and Cancer Research UK. VHK gratefully acknowledges funding by the Swiss National Science Foundation (P2SKP3_168322/1 and P2SKP3_168322/2), and the Promedica Foundation (F-87701-41-01). The results published or shown here are based in part upon data generated by the TCGA Research Network established by the NCI and NHGRI. Information about TCGA and the investigators and institutions who constitute the TCGA research network can be found at http://cancergenome.nih.gov. The funders played no role in the analyses performed or the results presented. The views expressed are those of the author(s) and not necessarily those of the NHS, the NIHR or the Department of Health.

PY - 2024/4/9

Y1 - 2024/4/9

N2 - The development of deep learning (DL) models to predict the consensus molecular subtypes (CMS) from histopathology images (imCMS) is a promising and cost-effective strategy to support patient stratification. Here, we investigate whether imCMS calls generated from whole slide histopathology images (WSIs) of rectal cancer (RC) pre-treatment biopsies are associated with pathological complete response (pCR) to neoadjuvant long course chemoradiotherapy (LCRT) with single agent fluoropyrimidine. DL models were trained to classify WSIs of colorectal cancers stained with hematoxylin and eosin into one of the four CMS classes using a multi-centric dataset of resection and biopsy specimens (n = 1057 WSIs) with paired transcriptional data. Classifiers were tested on a held out RC biopsy cohort (ARISTOTLE) and correlated with pCR to LCRT in an independent dataset merging two RC cohorts (ARISTOTLE, n = 114 and SALZBURG, n = 55 patients). DL models predicted CMS with high classification performance in multiple comparative analyses. In the independent cohorts (ARISTOTLE, SALZBURG), cases with WSIs classified as imCMS1 had a significantly higher likelihood of achieving pCR (OR = 2.69, 95% CI 1.01-7.17, p = 0.048). Conversely, imCMS4 was associated with lack of pCR (OR = 0.25, 95% CI 0.07-0.88, p = 0.031). Classification maps demonstrated pathologist-interpretable associations with high stromal content in imCMS4 cases, associated with poor outcome. No significant association was found in imCMS2 or imCMS3. imCMS classification of pre-treatment biopsies is a fast and inexpensive solution to identify patient groups that could benefit from neoadjuvant LCRT. The significant associations between imCMS1/imCMS4 with pCR suggest the existence of predictive morphological features that could enhance standard pathological assessment.

AB - The development of deep learning (DL) models to predict the consensus molecular subtypes (CMS) from histopathology images (imCMS) is a promising and cost-effective strategy to support patient stratification. Here, we investigate whether imCMS calls generated from whole slide histopathology images (WSIs) of rectal cancer (RC) pre-treatment biopsies are associated with pathological complete response (pCR) to neoadjuvant long course chemoradiotherapy (LCRT) with single agent fluoropyrimidine. DL models were trained to classify WSIs of colorectal cancers stained with hematoxylin and eosin into one of the four CMS classes using a multi-centric dataset of resection and biopsy specimens (n = 1057 WSIs) with paired transcriptional data. Classifiers were tested on a held out RC biopsy cohort (ARISTOTLE) and correlated with pCR to LCRT in an independent dataset merging two RC cohorts (ARISTOTLE, n = 114 and SALZBURG, n = 55 patients). DL models predicted CMS with high classification performance in multiple comparative analyses. In the independent cohorts (ARISTOTLE, SALZBURG), cases with WSIs classified as imCMS1 had a significantly higher likelihood of achieving pCR (OR = 2.69, 95% CI 1.01-7.17, p = 0.048). Conversely, imCMS4 was associated with lack of pCR (OR = 0.25, 95% CI 0.07-0.88, p = 0.031). Classification maps demonstrated pathologist-interpretable associations with high stromal content in imCMS4 cases, associated with poor outcome. No significant association was found in imCMS2 or imCMS3. imCMS classification of pre-treatment biopsies is a fast and inexpensive solution to identify patient groups that could benefit from neoadjuvant LCRT. The significant associations between imCMS1/imCMS4 with pCR suggest the existence of predictive morphological features that could enhance standard pathological assessment.

KW - Traditional research

KW - Tumour biomarkers

U2 - 10.1038/s41698-024-00580-3

DO - 10.1038/s41698-024-00580-3

M3 - Article

C2 - 38594327

SN - 2397-768X

VL - 8

JO - NPJ precision oncology

JF - NPJ precision oncology

IS - 1

M1 - 89

ER -

Image-based consensus molecular subtyping in rectal cancer biopsies and response to neoadjuvant chemoradiotherapy

Abstract

Bibliographical note

Keywords

UN SDGs

Access to Document

Fingerprint

Cite this