Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Prediction of post-treatment recurrence in early-stage breast cancer using deep-learning with mid-infrared chemical histopathological imaging

Keogan, Abigail ; Nguyen, Thi Nguyet Que ; Bouzy, Pascaline ; Stone, Nicholas ; Jirström, Karin LU orcid ; Rahman, Arman ; Gallagher, William M. and Meade, Aidan (2025) In NPJ precision oncology 9(1).
Abstract
Predicting long-term recurrence of disease in breast cancer (BC) patients remains a significant challenge for patients with early stage disease who are at low to intermediate risk of relapse as determined using current clinical tools. Prognostic assays which utilize bulk transcriptomics ignore the spatial context of the cellular material and are, therefore, of limited value in the development of mechanistic models. In this study, Fourier-transform infrared (FTIR) chemical images of BC tissue were used to train deep learning models to predict future disease recurrence. A number of deep learning models were employed, with champion models employing two-dimensional and two-dimensional-separable convolutional networks found to have predictive... (More)
Predicting long-term recurrence of disease in breast cancer (BC) patients remains a significant challenge for patients with early stage disease who are at low to intermediate risk of relapse as determined using current clinical tools. Prognostic assays which utilize bulk transcriptomics ignore the spatial context of the cellular material and are, therefore, of limited value in the development of mechanistic models. In this study, Fourier-transform infrared (FTIR) chemical images of BC tissue were used to train deep learning models to predict future disease recurrence. A number of deep learning models were employed, with champion models employing two-dimensional and two-dimensional-separable convolutional networks found to have predictive performance of a ROC AUC of approximately 0.64, which compares well to other clinically used prognostic assays in this space. All-digital chemical imaging may therefore provide a label-free platform for histopathological prognosis in breast cancer, opening new horizons for future deployment of these technologies. (Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
in
NPJ precision oncology
volume
9
issue
1
article number
18
publisher
Springer Nature
external identifiers
  • pmid:39825009
  • scopus:85218102656
ISSN
2397-768X
DOI
10.1038/s41698-024-00772-x
language
English
LU publication?
yes
id
fe6632a7-ef2b-4730-b750-043f80298260
date added to LUP
2025-01-19 09:02:41
date last changed
2025-04-04 14:08:59
@article{fe6632a7-ef2b-4730-b750-043f80298260,
  abstract     = {{Predicting long-term recurrence of disease in breast cancer (BC) patients remains a significant challenge for patients with early stage disease who are at low to intermediate risk of relapse as determined using current clinical tools. Prognostic assays which utilize bulk transcriptomics ignore the spatial context of the cellular material and are, therefore, of limited value in the development of mechanistic models. In this study, Fourier-transform infrared (FTIR) chemical images of BC tissue were used to train deep learning models to predict future disease recurrence. A number of deep learning models were employed, with champion models employing two-dimensional and two-dimensional-separable convolutional networks found to have predictive performance of a ROC AUC of approximately 0.64, which compares well to other clinically used prognostic assays in this space. All-digital chemical imaging may therefore provide a label-free platform for histopathological prognosis in breast cancer, opening new horizons for future deployment of these technologies.}},
  author       = {{Keogan, Abigail and Nguyen, Thi Nguyet Que and Bouzy, Pascaline and Stone, Nicholas and Jirström, Karin and Rahman, Arman and Gallagher, William M. and Meade, Aidan}},
  issn         = {{2397-768X}},
  language     = {{eng}},
  month        = {{01}},
  number       = {{1}},
  publisher    = {{Springer Nature}},
  series       = {{NPJ precision oncology}},
  title        = {{Prediction of post-treatment recurrence in early-stage breast cancer using deep-learning with mid-infrared chemical histopathological imaging}},
  url          = {{http://dx.doi.org/10.1038/s41698-024-00772-x}},
  doi          = {{10.1038/s41698-024-00772-x}},
  volume       = {{9}},
  year         = {{2025}},
}