ALL diagnosis: can efficiency and transparency coexist? An explainble deep learning approach

Abstract Acute Lymphoblastic Leukemia (ALL) is a life-threatening malignancy characterized by its aggressive progression and detrimental effects on the hematopoietic system. Early and accurate diagnosis is paramount to optimizing therapeutic interventions and improving clinical outcomes. This study...

Full description

Saved in:
Bibliographic Details
Main Authors: Dost Muhammad, Muhammad Salman, Ayse Keles, Malika Bendechache
Format: Article
Language:English
Published: Nature Portfolio 2025-04-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-97297-5
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849699343450243072
author Dost Muhammad
Muhammad Salman
Ayse Keles
Malika Bendechache
author_facet Dost Muhammad
Muhammad Salman
Ayse Keles
Malika Bendechache
author_sort Dost Muhammad
collection DOAJ
description Abstract Acute Lymphoblastic Leukemia (ALL) is a life-threatening malignancy characterized by its aggressive progression and detrimental effects on the hematopoietic system. Early and accurate diagnosis is paramount to optimizing therapeutic interventions and improving clinical outcomes. This study introduces a novel diagnostic framework that synergizes the EfficientNet-B7 architecture with Explainable Artificial Intelligence (XAI) methodologies to address challenges in performance, computational efficiency, and explainability. The proposed model achieves improved diagnostic performance, with accuracies exceeding 96% on the Taleqani Hospital dataset and 95.50% on the C-NMC-19 and Multi-Cancer datasets. Rigorous evaluation across multiple metrics-including Area Under the Curve (AUC), mean Average Precision (mAP), Accuracy, Precision, Recall, and F1-score-demonstrates the model’s robustness and establishes its superiority over state-of-the-art architectures namely VGG-19, InceptionResNetV2, ResNet50, DenseNet50 and AlexNet . Furthermore, the framework significantly reduces computational overhead, achieving up to 40% faster inference times, thereby enhancing its clinical applicability. To address the opacity inherent in Deep learning (DL) models, the framework integrates advanced XAI techniques, including Gradient-weighted Class Activation Mapping (Grad-CAM), Class Activation Mapping (CAM), Local Interpretable Model-Agnostic Explanations (LIME), and Integrated Gradients (IG), providing transparent and explainable insights into model predictions. This fusion of high diagnostic precision, computational efficiency, and explainability positions the proposed framework as a transformative tool for ALL diagnosis, bridging the gap between cutting-edge AI technologies and practical clinical deployment.
format Article
id doaj-art-6d8d4471b4e84896a89df8392a290441
institution DOAJ
issn 2045-2322
language English
publishDate 2025-04-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-6d8d4471b4e84896a89df8392a2904412025-08-20T03:18:38ZengNature PortfolioScientific Reports2045-23222025-04-0115112010.1038/s41598-025-97297-5ALL diagnosis: can efficiency and transparency coexist? An explainble deep learning approachDost Muhammad0Muhammad Salman1Ayse Keles2Malika Bendechache3CRT-AI and ADAPT Research Centres, School of Computer Science, University of GalwayDepartment of Software Engineering, University of MalakandADAPT Research Centre, School of Computer Science, University of GalwayADAPT Research Centre, School of Computer Science, University of GalwayAbstract Acute Lymphoblastic Leukemia (ALL) is a life-threatening malignancy characterized by its aggressive progression and detrimental effects on the hematopoietic system. Early and accurate diagnosis is paramount to optimizing therapeutic interventions and improving clinical outcomes. This study introduces a novel diagnostic framework that synergizes the EfficientNet-B7 architecture with Explainable Artificial Intelligence (XAI) methodologies to address challenges in performance, computational efficiency, and explainability. The proposed model achieves improved diagnostic performance, with accuracies exceeding 96% on the Taleqani Hospital dataset and 95.50% on the C-NMC-19 and Multi-Cancer datasets. Rigorous evaluation across multiple metrics-including Area Under the Curve (AUC), mean Average Precision (mAP), Accuracy, Precision, Recall, and F1-score-demonstrates the model’s robustness and establishes its superiority over state-of-the-art architectures namely VGG-19, InceptionResNetV2, ResNet50, DenseNet50 and AlexNet . Furthermore, the framework significantly reduces computational overhead, achieving up to 40% faster inference times, thereby enhancing its clinical applicability. To address the opacity inherent in Deep learning (DL) models, the framework integrates advanced XAI techniques, including Gradient-weighted Class Activation Mapping (Grad-CAM), Class Activation Mapping (CAM), Local Interpretable Model-Agnostic Explanations (LIME), and Integrated Gradients (IG), providing transparent and explainable insights into model predictions. This fusion of high diagnostic precision, computational efficiency, and explainability positions the proposed framework as a transformative tool for ALL diagnosis, bridging the gap between cutting-edge AI technologies and practical clinical deployment.https://doi.org/10.1038/s41598-025-97297-5Explainable artificial intelligenceXAI for medical diagnosisEXplainble medical imagingALL detectionDecision support systemResponsible AI
spellingShingle Dost Muhammad
Muhammad Salman
Ayse Keles
Malika Bendechache
ALL diagnosis: can efficiency and transparency coexist? An explainble deep learning approach
Scientific Reports
Explainable artificial intelligence
XAI for medical diagnosis
EXplainble medical imaging
ALL detection
Decision support system
Responsible AI
title ALL diagnosis: can efficiency and transparency coexist? An explainble deep learning approach
title_full ALL diagnosis: can efficiency and transparency coexist? An explainble deep learning approach
title_fullStr ALL diagnosis: can efficiency and transparency coexist? An explainble deep learning approach
title_full_unstemmed ALL diagnosis: can efficiency and transparency coexist? An explainble deep learning approach
title_short ALL diagnosis: can efficiency and transparency coexist? An explainble deep learning approach
title_sort all diagnosis can efficiency and transparency coexist an explainble deep learning approach
topic Explainable artificial intelligence
XAI for medical diagnosis
EXplainble medical imaging
ALL detection
Decision support system
Responsible AI
url https://doi.org/10.1038/s41598-025-97297-5
work_keys_str_mv AT dostmuhammad alldiagnosiscanefficiencyandtransparencycoexistanexplainbledeeplearningapproach
AT muhammadsalman alldiagnosiscanefficiencyandtransparencycoexistanexplainbledeeplearningapproach
AT aysekeles alldiagnosiscanefficiencyandtransparencycoexistanexplainbledeeplearningapproach
AT malikabendechache alldiagnosiscanefficiencyandtransparencycoexistanexplainbledeeplearningapproach