Breast Cancer Diagnosis and HER2+ Versus Triple Negative Discrimination by Infrared Spectral Histopathology

Breast cancer is a heterogeneous disease comprising distinct molecular subtypes that require accurate diagnosis for effective treatment. Conventional diagnostic methods primarily rely on histologic evaluation, which limits access to molecular-level information. Here, we present a label-free strategy combining Fourier-transform infrared (FTIR) imaging with machine learning for breast cancer diagnosis and subtype classification from tissue sections. A two-step approach was developed: first, to discriminate benign from malignant breast tissues, and second, to differentiate HER2+ from triple negative breast cancer (TNBC) subtypes. Using a cohort of 61 patients, LightGBM-based models reached sensitivities above 84% in distinguishing benign from malignant lesions, with ensemble learning achieving 100% accuracy across independent test sets, and 87.5% when including luminal tumors not used during training. Subtype classification proved more challenging but integrating the tumor microenvironment into the models improved performance, reaching sensitivities of 85.7% for HER2+ and 83.3% for TNBC patients. This study demonstrates, for the first time, the potential of FTIR imaging combined with AI to distinguish between HER2+ and TNBC subtypes directly from tissue sections. These findings highlight the relevance of spectral histopathology for rapid, nondestructive, and accurate breast cancer diagnosis, paving the way for integration into clinical workflows.

Authors

Institutions

Publication Details

Journal
Analytical Chemistry
Published
2026-06-09
DOI
https://doi.org/10.1021/acs.analchem.6c00639
Primary Topic
Infrared Thermography in Medicine
Type
article
Field-Weighted Citation Impact
0.00

Funders

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

Breast Cancer Diagnosis and HER2+ Versus Triple Negative Discrimination by Infrared Spectral Histopathology

Stéphane Potteaux, S. Kane, L. Bolko, Olivier Piot et al.
Analytical Chemistry
Infrared Thermography in Medicine
article

Breast Cancer Diagnosis and HER2+ Versus Triple Negative Discrimination by Infrared Spectral Histopathology

Stéphane Potteaux, S. Kane, L. Bolko, Olivier Piot, Cédric Lerévérend, Caroline Fichel, Jean‐Hugues Salmon, Valérie Untereiner, Laurent Corsois, Cyril Gobinet, Célia Maquin, Vincent Vuiblet, Hayat El Tahech, Jawaheer Hassani, Jacqueline Lehmann-Che, Yacine Merrouche, Sandrine Trévoux
article en

Abstract

Breast cancer is a heterogeneous disease comprising distinct molecular subtypes that require accurate diagnosis for effective treatment. Conventional diagnostic methods primarily rely on histologic evaluation, which limits access to molecular-level information. Here, we present a label-free strategy combining Fourier-transform infrared (FTIR) imaging with machine learning for breast cancer diagnosis and subtype classification from tissue sections. A two-step approach was developed: first, to discriminate benign from malignant breast tissues, and second, to differentiate HER2+ from triple negative breast cancer (TNBC) subtypes. Using a cohort of 61 patients, LightGBM-based models reached sensitivities above 84% in distinguishing benign from malignant lesions, with ensemble learning achieving 100% accuracy across independent test sets, and 87.5% when including luminal tumors not used during training. Subtype classification proved more challenging but integrating the tumor microenvironment into the models improved performance, reaching sensitivities of 85.7% for HER2+ and 83.3% for TNBC patients. This study demonstrates, for the first time, the potential of FTIR imaging combined with AI to distinguish between HER2+ and TNBC subtypes directly from tissue sections. These findings highlight the relevance of spectral histopathology for rapid, nondestructive, and accurate breast cancer diagnosis, paving the way for integration into clinical workflows.

Analytical Chemistry
Inserm (FR), Université Paris Cité (FR), Saint Louis University Hospital (US), Alltech (United States) (US), Délégation Régionale Nord Ouest (FR), Centre d'Etudes Biologiques de Chizé (FR), Centre Hospitalier Universitaire de Reims (FR), Artificial Intelligence Research Institute (ES), Société Française de Rhumatologie (FR), Agence Régionale de Santé Ile-de-France (FR), Institut Jean Godinot (FR), Directorate-General Joint Research Centre (BE), Institut de Recherche en Sciences de la Santé (BF), REGARDS Recherches en Économie Gestion AgroRessources Durabilité Santé (FR), Université de Reims Champagne-Ardenne (FR)
Institut National de la Santé et de la Recherche Médicale, Université de Reims Champagne-Ardenne
Gender equality
Openalex Percentile: Top 6%
Infrared Thermography in Medicine
DOISourceOpenAlex
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.