Breast cancer detection based on histological images using fusion of diffusion model outputs

Abstract The precise detection of breast cancer in histopathological images remains a critical challenge in computational pathology, where accurate tissue segmentation significantly enhances diagnostic accuracy. This study introduces a novel approach leveraging a Conditional Denoising Diffusion Prob...

Full description

Saved in:
Bibliographic Details
Main Authors: Younes Akbari, Faseela Abdullakutty, Somaya Al Maadeed, Ahmed Bouridane, Rifat Hamoudi
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-025-05744-0
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849238315896668160
author Younes Akbari
Faseela Abdullakutty
Somaya Al Maadeed
Ahmed Bouridane
Rifat Hamoudi
author_facet Younes Akbari
Faseela Abdullakutty
Somaya Al Maadeed
Ahmed Bouridane
Rifat Hamoudi
author_sort Younes Akbari
collection DOAJ
description Abstract The precise detection of breast cancer in histopathological images remains a critical challenge in computational pathology, where accurate tissue segmentation significantly enhances diagnostic accuracy. This study introduces a novel approach leveraging a Conditional Denoising Diffusion Probabilistic Model (DDPM) to improve breast cancer detection through advanced segmentation and feature fusion. The method employs a conditional channel within the DDPM framework, first trained on a breast cancer histopathology dataset and extended to additional datasets to achieve regional-level segmentation of tumor areas and other tissue regions. These segmented regions, combined with predicted noise from the diffusion model and original images, are processed through an EfficientNet-B0 network to extract enhanced features. A transformer decoder then fuses these features to generate final detection results. Extensive experiments optimizing the network architecture and fusion strategies were conducted, and the proposed method was evaluated across four distinct datasets, achieving a peak accuracy of 92.86% on the BRACS dataset, 100% on the BreCaHAD dataset, 96.66% the ICIAR2018 dataset. This approach represents a significant advancement in computational pathology, offering a robust tool for breast cancer detection with potential applications in broader medical imaging contexts.
format Article
id doaj-art-95768c9c553847748abb1066ebc87be3
institution Kabale University
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-95768c9c553847748abb1066ebc87be32025-08-20T04:01:41ZengNature PortfolioScientific Reports2045-23222025-07-0115111610.1038/s41598-025-05744-0Breast cancer detection based on histological images using fusion of diffusion model outputsYounes Akbari0Faseela Abdullakutty1Somaya Al Maadeed2Ahmed Bouridane3Rifat Hamoudi4Department of Computer Science and Engineering, Qatar UniversityDepartment of Computer Science and Engineering, Qatar UniversityDepartment of Computer Science and Engineering, Qatar UniversityCenter for Data Analytics and Cybernetics, University of SharjahBIMAI-Lab, Biomedically Informed Artificial Intelligence Laboratory, University of SharjahAbstract The precise detection of breast cancer in histopathological images remains a critical challenge in computational pathology, where accurate tissue segmentation significantly enhances diagnostic accuracy. This study introduces a novel approach leveraging a Conditional Denoising Diffusion Probabilistic Model (DDPM) to improve breast cancer detection through advanced segmentation and feature fusion. The method employs a conditional channel within the DDPM framework, first trained on a breast cancer histopathology dataset and extended to additional datasets to achieve regional-level segmentation of tumor areas and other tissue regions. These segmented regions, combined with predicted noise from the diffusion model and original images, are processed through an EfficientNet-B0 network to extract enhanced features. A transformer decoder then fuses these features to generate final detection results. Extensive experiments optimizing the network architecture and fusion strategies were conducted, and the proposed method was evaluated across four distinct datasets, achieving a peak accuracy of 92.86% on the BRACS dataset, 100% on the BreCaHAD dataset, 96.66% the ICIAR2018 dataset. This approach represents a significant advancement in computational pathology, offering a robust tool for breast cancer detection with potential applications in broader medical imaging contexts.https://doi.org/10.1038/s41598-025-05744-0
spellingShingle Younes Akbari
Faseela Abdullakutty
Somaya Al Maadeed
Ahmed Bouridane
Rifat Hamoudi
Breast cancer detection based on histological images using fusion of diffusion model outputs
Scientific Reports
title Breast cancer detection based on histological images using fusion of diffusion model outputs
title_full Breast cancer detection based on histological images using fusion of diffusion model outputs
title_fullStr Breast cancer detection based on histological images using fusion of diffusion model outputs
title_full_unstemmed Breast cancer detection based on histological images using fusion of diffusion model outputs
title_short Breast cancer detection based on histological images using fusion of diffusion model outputs
title_sort breast cancer detection based on histological images using fusion of diffusion model outputs
url https://doi.org/10.1038/s41598-025-05744-0
work_keys_str_mv AT younesakbari breastcancerdetectionbasedonhistologicalimagesusingfusionofdiffusionmodeloutputs
AT faseelaabdullakutty breastcancerdetectionbasedonhistologicalimagesusingfusionofdiffusionmodeloutputs
AT somayaalmaadeed breastcancerdetectionbasedonhistologicalimagesusingfusionofdiffusionmodeloutputs
AT ahmedbouridane breastcancerdetectionbasedonhistologicalimagesusingfusionofdiffusionmodeloutputs
AT rifathamoudi breastcancerdetectionbasedonhistologicalimagesusingfusionofdiffusionmodeloutputs