BioAug-Net: a bioimage sensor-driven attention-augmented segmentation framework with physiological coupling for early prostate cancer detection in T2-weighted MRI

Abstract Accurate segmentation of the prostate peripheral zone (PZ) in T2-weighted MRI is critical for the early detection of prostate cancer. Existing segmentation methods are hindered by significant inter-observer variability (37.4 ± 5.6%), poor boundary localization, and the presence of motion ar...

Full description

Saved in:
Bibliographic Details
Main Authors: Muhammad Arshad, Chengliang Wang, Muhammad Wajeeh Us Sima, Jamshed Ali Shaikh, Hanen Karamti, Raed Alharthi, Julius Selecky
Format: Article
Language:English
Published: BMC 2025-07-01
Series:BioData Mining
Subjects:
Online Access:https://doi.org/10.1186/s13040-025-00467-4
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849237678950711296
author Muhammad Arshad
Chengliang Wang
Muhammad Wajeeh Us Sima
Jamshed Ali Shaikh
Hanen Karamti
Raed Alharthi
Julius Selecky
author_facet Muhammad Arshad
Chengliang Wang
Muhammad Wajeeh Us Sima
Jamshed Ali Shaikh
Hanen Karamti
Raed Alharthi
Julius Selecky
author_sort Muhammad Arshad
collection DOAJ
description Abstract Accurate segmentation of the prostate peripheral zone (PZ) in T2-weighted MRI is critical for the early detection of prostate cancer. Existing segmentation methods are hindered by significant inter-observer variability (37.4 ± 5.6%), poor boundary localization, and the presence of motion artifacts, along with challenges in clinical integration. In this study, we propose BioAug-Net, a novel framework that integrates real-time physiological signal feedback with MRI data, leveraging transformer-based attention mechanisms and a probabilistic clinical decision support system (PCDSS). BioAug-Net features a dual-branch asymmetric attention mechanism: one branch processes spatial MRI features, while the other incorporates temporal sensor signals through a BiGRU-driven adaptive masking module. Additionally, a Markov Decision Process-based PCDSS maps segmentation outputs to clinical PI-RADS scores, with uncertainty quantification. We validated BioAug-Net on a multi-institutional dataset (n=1,542) and demonstrated state-of-the-art performance, achieving a Dice Similarity Coefficient of 89.7% (p < 0.001), sensitivity of 91.2% (p < 0.001), specificity of 88.4% (p < 0.001), and HD95 of 2.14 mm (p < 0.001), outperforming U-Net, Attention U-Net, and TransUNet. Sensor integration improved segmentation accuracy by 12.6% (p < 0.001) and reduced inter-observer variation by 48.3% (p < 0.001). Radiologist evaluations (n=3) confirmed a 15.0% reduction in diagnosis time (p = 0.003) and an increase in inter-reader agreement from K = 0.68 to K = 0.82 (p = 0.001). Our results show that BioAug-Net offers a clinically viable solution for early prostate cancer detection through enhanced physiological coupling and explainable AI diagnostics.
format Article
id doaj-art-371cf78268624ac2985aa8e2b167ec81
institution Kabale University
issn 1756-0381
language English
publishDate 2025-07-01
publisher BMC
record_format Article
series BioData Mining
spelling doaj-art-371cf78268624ac2985aa8e2b167ec812025-08-20T04:01:53ZengBMCBioData Mining1756-03812025-07-0118114910.1186/s13040-025-00467-4BioAug-Net: a bioimage sensor-driven attention-augmented segmentation framework with physiological coupling for early prostate cancer detection in T2-weighted MRIMuhammad Arshad0Chengliang Wang1Muhammad Wajeeh Us Sima2Jamshed Ali Shaikh3Hanen Karamti4Raed Alharthi5Julius Selecky6Department of Computer Science and Technology, College of Computer Science, Chongqing UniversityDepartment of Computer Science and Technology, College of Computer Science, Chongqing UniversityDepartment of Computer Science and Technology, College of Computer Science, Chongqing UniversityDepartment of Computer Science and Technology, College of Computer Science, Chongqing UniversityDepartment of Computer Sciences, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman UniversityDepartment of Computer Science and Engineering, University of Hafr Al-BatinDepartment of Information Management and Business Systems, Comenius University BratislavaAbstract Accurate segmentation of the prostate peripheral zone (PZ) in T2-weighted MRI is critical for the early detection of prostate cancer. Existing segmentation methods are hindered by significant inter-observer variability (37.4 ± 5.6%), poor boundary localization, and the presence of motion artifacts, along with challenges in clinical integration. In this study, we propose BioAug-Net, a novel framework that integrates real-time physiological signal feedback with MRI data, leveraging transformer-based attention mechanisms and a probabilistic clinical decision support system (PCDSS). BioAug-Net features a dual-branch asymmetric attention mechanism: one branch processes spatial MRI features, while the other incorporates temporal sensor signals through a BiGRU-driven adaptive masking module. Additionally, a Markov Decision Process-based PCDSS maps segmentation outputs to clinical PI-RADS scores, with uncertainty quantification. We validated BioAug-Net on a multi-institutional dataset (n=1,542) and demonstrated state-of-the-art performance, achieving a Dice Similarity Coefficient of 89.7% (p < 0.001), sensitivity of 91.2% (p < 0.001), specificity of 88.4% (p < 0.001), and HD95 of 2.14 mm (p < 0.001), outperforming U-Net, Attention U-Net, and TransUNet. Sensor integration improved segmentation accuracy by 12.6% (p < 0.001) and reduced inter-observer variation by 48.3% (p < 0.001). Radiologist evaluations (n=3) confirmed a 15.0% reduction in diagnosis time (p = 0.003) and an increase in inter-reader agreement from K = 0.68 to K = 0.82 (p = 0.001). Our results show that BioAug-Net offers a clinically viable solution for early prostate cancer detection through enhanced physiological coupling and explainable AI diagnostics.https://doi.org/10.1186/s13040-025-00467-4Prostate cancerBioimage processingT2-weighted MRIImage segmentationAttention mechanismClinical decision support system
spellingShingle Muhammad Arshad
Chengliang Wang
Muhammad Wajeeh Us Sima
Jamshed Ali Shaikh
Hanen Karamti
Raed Alharthi
Julius Selecky
BioAug-Net: a bioimage sensor-driven attention-augmented segmentation framework with physiological coupling for early prostate cancer detection in T2-weighted MRI
BioData Mining
Prostate cancer
Bioimage processing
T2-weighted MRI
Image segmentation
Attention mechanism
Clinical decision support system
title BioAug-Net: a bioimage sensor-driven attention-augmented segmentation framework with physiological coupling for early prostate cancer detection in T2-weighted MRI
title_full BioAug-Net: a bioimage sensor-driven attention-augmented segmentation framework with physiological coupling for early prostate cancer detection in T2-weighted MRI
title_fullStr BioAug-Net: a bioimage sensor-driven attention-augmented segmentation framework with physiological coupling for early prostate cancer detection in T2-weighted MRI
title_full_unstemmed BioAug-Net: a bioimage sensor-driven attention-augmented segmentation framework with physiological coupling for early prostate cancer detection in T2-weighted MRI
title_short BioAug-Net: a bioimage sensor-driven attention-augmented segmentation framework with physiological coupling for early prostate cancer detection in T2-weighted MRI
title_sort bioaug net a bioimage sensor driven attention augmented segmentation framework with physiological coupling for early prostate cancer detection in t2 weighted mri
topic Prostate cancer
Bioimage processing
T2-weighted MRI
Image segmentation
Attention mechanism
Clinical decision support system
url https://doi.org/10.1186/s13040-025-00467-4
work_keys_str_mv AT muhammadarshad bioaugnetabioimagesensordrivenattentionaugmentedsegmentationframeworkwithphysiologicalcouplingforearlyprostatecancerdetectionint2weightedmri
AT chengliangwang bioaugnetabioimagesensordrivenattentionaugmentedsegmentationframeworkwithphysiologicalcouplingforearlyprostatecancerdetectionint2weightedmri
AT muhammadwajeehussima bioaugnetabioimagesensordrivenattentionaugmentedsegmentationframeworkwithphysiologicalcouplingforearlyprostatecancerdetectionint2weightedmri
AT jamshedalishaikh bioaugnetabioimagesensordrivenattentionaugmentedsegmentationframeworkwithphysiologicalcouplingforearlyprostatecancerdetectionint2weightedmri
AT hanenkaramti bioaugnetabioimagesensordrivenattentionaugmentedsegmentationframeworkwithphysiologicalcouplingforearlyprostatecancerdetectionint2weightedmri
AT raedalharthi bioaugnetabioimagesensordrivenattentionaugmentedsegmentationframeworkwithphysiologicalcouplingforearlyprostatecancerdetectionint2weightedmri
AT juliusselecky bioaugnetabioimagesensordrivenattentionaugmentedsegmentationframeworkwithphysiologicalcouplingforearlyprostatecancerdetectionint2weightedmri