Identification of at-risk prostate cancer patients using Fourier Transform Infrared Spectroscopy and Machine Learning

Aug 5, 2026

Fourier Transform Infrared Spectroscopy (FTIR) supports histopathological assessment by enabling diagnostic and prognostic insights from label-free chemical imaging of biomedical tissue. A stratification protocol is presented to identify prostate cancer patients at risk of poor outcomes using infrared hyperspectral data paired with machine learning. The approach is validated on a large cohort (n=183) with biopsy cores (n=1440), using patient age and PSA as the only additional clinical inputs. Identified outcome groups closely align with groups separated by tumour stage.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages9

Reading Time23 min

AccessFree to download

Abstract

Introduction

Clinical context for prostate cancer treatment decisions

Limits of histopathological assessment

Infrared spectroscopy and hyperspectral chemical fingerprints

Prior work with spectroscopy and machine learning

Study aim: prognostic stratification using FTIR and ML

The University of Manchester Research Identification of at-risk prostate cancer patients using Fourier Transform Infrared Spectroscopy and Machine Learning DOI: 10.1117/12.3048498 Document Version Accepted author manuscript Link to publication record in Manchester Research Explorer Citation for published version (APA): Ferguson, D. , Sachdeva, A. , Hart, C. A. , Sanchez, D. F. , Oliveira, P. , Brown, M. , Clarke, N. , & Gardner, P. (2025) . Identification of at-risk prostate cancer patients using Fourier Transform Infrared Spectroscopy and Machine Learning. In R. R. Alfano, A. B. Seddon, L. Shi, & B. Wu (Eds. ), Optical Biopsy XXIII: Toward Real-Time Spectroscopic Imaging and Diagnosis Article 1331103 (Progress in Biomedical Optics and Imaging-Proceedings of SPIE; Vol. 13311) . SPIE. [https://doi.org/10.1117/12.3048498](https://doi.org/10.1117/12.3048498) Published in: Optical Biopsy XXIII Citing this paper Please note that where the full-text provided on Manchester Research Explorer is the Author Accepted Manuscript or Proof version this may differ from the final Published version. If citing, it is advised that you check and use the publisher's definitive version. General rights Copyright and moral rights for the publications made accessible in the Research Explorer are retained by the authors and/or other copyright owners and it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights. Takedown policy If you believe that this document breaches copyright please refer to the University of Manchester’s Takedown Procedures [[http://man.ac.uk/04Y6Bo](http://man.ac.uk/04Y6Bo)] or [contact openresearch@manchester.ac.uk](contact openresearch@manchester.ac.uk) providing relevant details, so we can investigate your claim. Download date:31 . Dec. 2025 Identification of at-risk prostate cancer patients using Fourier Transform Infrared Spectroscopy and Machine Learning Dougal Ferguson*ab, Ashwin Sachdevac,d, Claire A. Hartc, Diego F. Sancheze, Pedro Oliveiraf, Mick Brownc, Noel Clarked,g, and Peter Gardnerab a Photon Science Institute, University of Manchester; b Department of Chemical Engineering , School of Engineering, University of Manchester; c Division of Cancer Sciences, University of Manchester; d Department of Surgery, The Christie Hospital NHS Foundation Trust; e Cancer Research UK Manchester Institute, Wilmslow Road, Manchester; f Department of Pathology, The Christie Hospital NHS Foundation Trust; g Department of Urology, Salford Royal Hospital. ABSTRACT Fourier Transform Infrared Spectroscopy (FTIR) has been shown to be a useful tool to complement the histopathological assessment of biomedical tissue samples, allowing for diagnostic and prognostic applications based solely on chemical imaging of the tissues. This technique can be used to assist in determining the prognosis of prostate cancer patients, aiding the treatment decision protocols employed by clinicians. We report a stratification protocol to identify at-risk prostate cancer patients with poor outcomes from a large patient study (n=183) through the usage of label-free chemical imaging (without chemical de-waxing or staining) of numerous prostate cancer biopsy cores (n=1440) paired with machine learning techniques, without consideration of additional clinical variates beyond patient age and PSA levels. Distinctly different patient outcome groups are identified using infrared hyperspectral data, closely matching patient groups separated by tumour stage. Keywords: Fourier transform infrared (FT-IR) spectroscopy, mid-infrared, chemical imaging, spectral histopathology, prostate cancer, diagnostics, machine learning, patient outcome. 1. INTRODUCTION In determining prostate cancer treatment decisions, clinicians consider multiple clinical variates: cancer type, size, grading, patient health, and metastatic stage. Gold standard histopathological asse

FAQs

What technique does the study use to analyze prostate biopsy tissue?

It uses Fourier Transform Infrared Spectroscopy (FTIR) with label-free infrared hyperspectral chemical imaging to characterize tissue composition.

How are at-risk prostate cancer patients identified in this work?

A stratification protocol combines machine learning with infrared hyperspectral data, and models trained on patient outcome information to separate poor-outcome groups.

Which clinical variables are included alongside spectral data?

Only patient age and PSA levels are used; no other clinical variates are considered.

Aug 5, 2026

Upload by River Wang