{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,27]],"date-time":"2026-09-27T15:12:40Z","timestamp":1790521960917,"version":"4.1.0"},"reference-count":40,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T00:00:00Z","timestamp":1765843200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:p>Acute lymphoblastic leukemia (ALL) is a malignant blood disorder that primarily affects white blood cells, particularly in children, where early and accurate diagnosis is critical for effective treatment and recovery. This study introduces a novel deep learning framework, termed XIncept-ALL, for automated detection and classification of ALL severity levels. The model integrates pre-trained InceptionV3 and Xception networks through feature fusion blocks, enabling robust representation learning. To enhance performance, data auto-augmentation techniques were applied to address class imbalance and reduce overfitting. Furthermore, Grad-CAM visualizations were employed to highlight discriminative regions of ALL cell images, providing interpretability of the model's predictions and validating that the network focuses on clinically relevant features. The proposed system was evaluated using a newly developed private dataset, Pak-ALL, collected from Pakistani hospitals, along with additional datasets from reliable web sources. Extracted features were classified using an XGBoost classifier into four categories: Benign, Early, Pre, and Pro. Extensive experiments demonstrated the superior performance of the proposed framework, achieving an average accuracy of 99.5% on a challenging external dataset (Iranian dataset). The results highlight the efficiency, scalability, and practicality of the XIncept-ALL model for medical image analysis. By offering both improved classification accuracy and interpretable decision support via Grad-CAM, the proposed approach represents a significant advancement toward reliable computer-aided diagnostic systems for ALL, with strong potential to support clinical decision-making and improve patient outcomes.<\/jats:p>","DOI":"10.3389\/fmed.2025.1694024","type":"journal-article","created":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T05:17:01Z","timestamp":1765862221000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["An explainable deep learning-based feature fusion model for acute lymphoblastic leukemia diagnosis and severity assessment"],"prefix":"10.3389","volume":"12","author":[{"given":"Hajra","family":"Khan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammad Zaheer","family":"Sajid","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nauman Ali","family":"Khan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammad Fareed","family":"Hamid","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ayman","family":"Youssef","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Areesha","family":"Rehman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nour","family":"Aburaed","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,12,16]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"43","DOI":"10.5120\/ijais2015451461","article-title":"Leukaemia detection using digital image processing techniques","volume":"10","author":"Vaghela","year":"2015","journal-title":"Int J Appl Inf Syst"},{"key":"B2","doi-asserted-by":"publisher","first-page":"3113","DOI":"10.1007\/s11517-020-02282-x","article-title":"A convolutional neural network\u2013based learning approach to acute lymphoblastic leukaemia detection with automated feature extraction","volume":"58","author":"Anwar","year":"2020","journal-title":"Med Biol Eng Comput"},{"key":"B3","first-page":"147","article-title":"White blood cells segmentation and classification to detect acute leukaemia","volume":"2","author":"Joshi","year":"2013","journal-title":"Int J Emerg Trends Technol Comput Sci"},{"key":"B4","volume-title":"Contemporary Medical-Surgical Nursing","author":"Daniels","year":"2012"},{"key":"B5","doi-asserted-by":"publisher","first-page":"1091","DOI":"10.6004\/jnccn.2017.0147","article-title":"NCCN guidelines insights: acute lymphoblastic leukemia, version 1","volume":"15","author":"Brown","year":"2017","journal-title":"J Natl Compr Canc Netw"},{"key":"B6","doi-asserted-by":"crossref","first-page":"522","DOI":"10.1109\/ICOEI.2017.8300983","article-title":"Detection of leukemia and its types using image processing and machine learning","volume-title":"2017 International Conference on Trends in Electronics and Informatics (ICEI)","author":"Jagadev","year":"2017"},{"key":"B7","doi-asserted-by":"publisher","first-page":"49","DOI":"10.4103\/2228-7477.150428","article-title":"Recognition of acute lymphoblastic leukemia cells in microscopic images using k-means clustering and support vector machine classifier","volume":"5","author":"Amin","year":"2015","journal-title":"J Med Signals Sens"},{"key":"B8","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1111\/ijlh.12818","article-title":"Image processing and machine learning in the morphological analysis of blood cells","volume":"40","author":"Rodellar","year":"2018","journal-title":"Int J Lab Hematol"},{"key":"B9","doi-asserted-by":"publisher","first-page":"2631","DOI":"10.1007\/s11517-020-02245-2","article-title":"Identification of significant risks in pediatric acute lymphoblastic leukemia (ALL) through machine learning (ML) approach","volume":"58","author":"Mahmood","year":"2020","journal-title":"Med Biol Eng Comput"},{"key":"B10","doi-asserted-by":"publisher","first-page":"1005","DOI":"10.3389\/fbioe.2020.01005","article-title":"Automated detection of acute lymphoblastic leukemia from microscopic images based on human visual perception","volume":"8","author":"Bodzas","year":"2020","journal-title":"Front Bioeng Biotechnol"},{"key":"B11","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1109\/ICCRE.2018.8376476","article-title":"White blood cell classification and counting using convolutional neural network","volume-title":"2018 3rd International Conference on Control and Robotics Engineering (ICCRE)","author":"Macawile","year":"2018"},{"key":"B12","doi-asserted-by":"publisher","first-page":"382","DOI":"10.1016\/j.bbe.2019.01.005","article-title":"Comparison of traditional image processing and deep learning approaches for classification of white blood cells in peripheral blood smear images","volume":"39","author":"Hegde","year":"2019","journal-title":"Biocybern Biomed Eng"},{"key":"B13","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1007\/978-981-13-3600-3_13","article-title":"White blood cell classification using convolutional neural network","volume-title":"Soft Computing and Signal Processing.","author":"Sharma","year":"2019"},{"key":"B14","doi-asserted-by":"crossref","DOI":"10.1117\/12.2311282","article-title":"Automatic white blood cell classification using pre-trained deep learning models: ResNet and inception","volume-title":"Proceedings Volume 10696, Tenth International Conference on Machine Vision (ICMV 2017).","author":"Habibzadeh","year":"2018"},{"key":"B15","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1016\/j.procs.2019.08.145","article-title":"Modeling of the acute lymphoblastic leukemia detection based on the principal object characteristics of the color image","volume":"157","author":"Muntasa","year":"2019","journal-title":"Procedia Comput Sci"},{"key":"B16","doi-asserted-by":"publisher","first-page":"e6125289","DOI":"10.1155\/2018\/6125289","article-title":"Computer-aided diagnosis of acute lymphoblastic leukaemia","volume":"2018","author":"Shafique","year":"2018","journal-title":"Comput Math Methods Med"},{"key":"B17","doi-asserted-by":"crossref","first-page":"1144","DOI":"10.1109\/CoDIT.2019.8820299","article-title":"Automatic acute lymphoblastic leukemia detection and comparative analysis from images","volume-title":"2019 6th International Conference on Control, Decision and Information Technologies (CoDIT)","author":"Bhuiyan","year":"2019"},{"key":"B18","doi-asserted-by":"publisher","first-page":"1783","DOI":"10.1007\/s11517-019-01984-1","article-title":"Detection of acute lymphoblastic leukemia using image segmentation and data mining algorithms","volume":"57","author":"Acharya","year":"2019","journal-title":"Med Biol Eng Comput"},{"key":"B19","doi-asserted-by":"publisher","first-page":"1064","DOI":"10.3390\/diagnostics10121064","article-title":"An aggregated-based deep learning method for leukemic B-lymphoblast classification","volume":"10","author":"Kasani","year":"2020","journal-title":"Diagnostics"},{"key":"B20","doi-asserted-by":"publisher","first-page":"2536","DOI":"10.1038\/s41598-020-59215-9","article-title":"Efficient classification of white blood cell leukemia with improved swarm optimization of deep features","volume":"10","author":"Sahlol","year":"2020","journal-title":"Sci Rep"},{"key":"B21","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1109\/ICPC2T48082.2020.9071471","article-title":"Leukemia disease detection and classification using machine learning approaches: a review","volume-title":"2020 First International Conference on Power, Control and Computing Technologies (ICPC2T)","author":"Ratley","year":"2020"},{"key":"B22","doi-asserted-by":"publisher","first-page":"717","DOI":"10.1111\/ijlh.13089","article-title":"Machine learning applications in the diagnosis of leukemia: current trends and future directions","volume":"41","author":"Salah","year":"2019","journal-title":"Int J Lab Hematol"},{"key":"B23","doi-asserted-by":"publisher","first-page":"3113","DOI":"10.1007\/s11517-020-02282-x","article-title":"A convolutional neural network\u2013based learning approach to acute lymphoblastic leukaemia detection with automated feature extraction","volume":"58","author":"Anwar","year":"2020","journal-title":"Med Biol Eng Comput"},{"key":"B24","doi-asserted-by":"publisher","first-page":"348","DOI":"10.3390\/life13020348","article-title":"Gaussian blurring technique for detecting and classifying acute lymphoblastic leukemia cancer cells from microscopic biopsy images","volume":"13","author":"Devi","year":"2023","journal-title":"Life"},{"key":"B25","doi-asserted-by":"publisher","first-page":"10662","DOI":"10.3390\/app112210662","article-title":"An attention-based convolutional neural network for acute lymphoblastic leukemia classification","volume":"11","author":"Zakir Ullah","year":"2021","journal-title":"Appl Sci"},{"key":"B26","doi-asserted-by":"publisher","first-page":"1812","DOI":"10.3390\/healthcare10101812","article-title":"Customized deep learning classifier for detection of acute lymphoblastic leukemia using blood smear images","volume":"10","author":"Sampathila","year":"2022","journal-title":"Healthcare"},{"key":"B27","doi-asserted-by":"publisher","first-page":"1083649","DOI":"10.3389\/fncom.2022.1083649","article-title":"An efficient computer vision-based approach for acute lymphoblastic leukemia prediction","volume":"16","author":"Almadhor","year":"2022","journal-title":"Front Comput Neurosci"},{"key":"B28","doi-asserted-by":"publisher","first-page":"1005","DOI":"10.3389\/fbioe.2020.01005","article-title":"Automated detection of acute lymphoblastic leukemia from microscopic images based on human visual perception","volume":"8","author":"Bodzas","year":"2020","journal-title":"Front Bioeng Biotechnol"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.5220\/0010257406850692","article-title":"Classification of normal versus leukemic cells with data augmentation and convolutional neural networks","author":"de Oliveira","year":"2021","journal-title":"16th International Conference on Computer Vision Theory and Applications (VISIGRAPP), Vol. 4"},{"key":"B30","doi-asserted-by":"publisher","first-page":"623","DOI":"10.1007\/s10278-022-00600-3","article-title":"Optimizing a deep residual neural network with genetic algorithm for acute lymphoblastic leukemia classification","volume":"35","author":"Rodrigues","year":"2022","journal-title":"J Digit Imaging"},{"key":"B31","doi-asserted-by":"publisher","first-page":"3376","DOI":"10.3390\/cancers15133376","article-title":"Explainable CAD system for classification of acute lymphoblastic leukemia based on a robust white blood cell segmentation","volume":"15","author":"Diaz Resendiz","year":"2023","journal-title":"Cancers"},{"key":"B32","doi-asserted-by":"publisher","first-page":"105894","DOI":"10.1016\/j.compbiomed.2022.105894","article-title":"ALNett: a cluster layer deep convolutional neural network for acute lymphoblastic leukemia classification","volume":"148","author":"Jawahar","year":"2022","journal-title":"Comput. Biol. Med"},{"key":"B33","doi-asserted-by":"publisher","first-page":"1026","DOI":"10.3390\/diagnostics13061026","article-title":"Hybrid techniques for the diagnosis of acute lymphoblastic leukemia based on fusion of CNN features","volume":"13","author":"Ahmed","year":"2023","journal-title":"Diagnostics"},{"key":"B34","doi-asserted-by":"publisher","first-page":"35475","DOI":"10.1007\/s11042-023-15113-6","article-title":"Classification of acute lymphoblastic leukemia using improved ANFIS","volume":"82","author":"Rejula","year":"2023","journal-title":"Multimed Tools Appl"},{"key":"B35","doi-asserted-by":"publisher","first-page":"644","DOI":"10.3390\/bioengineering11070644","article-title":"Automatic detection of Acute Leukemia (ALL and AML) utilizing customized deep graph convolutional neural networks","volume":"11","author":"Zare","year":"2024","journal-title":"Bioengineering"},{"key":"B36","doi-asserted-by":"publisher","first-page":"5520","DOI":"10.3390\/s22155520","article-title":"BO-ALLCNN: Bayesian-based optimized CNN for acute lymphoblastic leukemia detection in microscopic blood smear images","volume":"22","author":"Atteia","year":"2022","journal-title":"Sensors"},{"key":"B37","first-page":"2818","article-title":"Rethinking the inception architecture for computer vision","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Szegedy","year":"2016"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3368031","article-title":"A framework for early detection of acute lymphoblastic leukemia and its subtypes from peripheral blood smear images using deep ensemble learning technique","author":"Perveen","year":"2024","journal-title":"IEEE Access"},{"key":"B39","first-page":"1251","article-title":"Xception: deep learning with depthwise separable convolutions","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Chollet","year":"2017"},{"key":"B40","doi-asserted-by":"publisher","first-page":"109335","DOI":"10.1109\/ACCESS.2020.3001159","article-title":"HCF: a hybrid CNN framework for behavior detection of distracted drivers","volume":"8","author":"Huang","year":"2020","journal-title":"IEEE Access"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1694024\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T05:17:04Z","timestamp":1765862224000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1694024\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,16]]},"references-count":40,"alternative-id":["10.3389\/fmed.2025.1694024"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2025.1694024","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,16]]},"article-number":"1694024"}}