{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T22:19:24Z","timestamp":1793139564303,"version":"4.5.0"},"reference-count":31,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T00:00:00Z","timestamp":1760313600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004054","name":"King Abdulaziz University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004054","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Cell Dev. Biol."],"abstract":"<jats:p>Acute Lymphoblastic Leukemia (ALL) is a prevalent malignancy particularly among children. It poses diagnostic challenges due to its morphological similarities with normal cells and the limitations of conventional methods like bone marrow biopsies, which are invasive and resource-intensive. This study introduces Causal-Former-HMC, a novel hybrid AI architecture integrating convolutional neural networks, vision transformers, and a causal graph learner with counterfactual reasoning to enhance diagnostic precision and interpretability from peripheral blood smear (PBS) images. We utilized two robust datasets: the ALL Image collection, comprising 89 patients and 3,256 PBS images (504 benign, 2,752 malignant across Pro B, Pre B, and Early Pre B subtypes), and C-NMC dataset, containing 15,135 segmented cell images from 118 patients (7,272 leukemic, 3,389 normal). To address class imbalance, we implemented class-aware data augmentation, standardizing image counts across classes and resizing to 128 \u00d7 128 pixels for compatibility with our model. The proposed model is evaluated via stratified 5-fold cross-validation with Nadam, SGD, and Radam (fractional) optimizers, Causal-Former-HMC achieved perfect classification accuracy (100%) and macro-averaged F1-scores on the ALL dataset, and up to 98.5% accuracy with 0.9975 ROC-AUC on the C-NMC dataset hence demonstrating superior generalization. Interpretability was ensured through advanced explainable AI techniques, including Grad-CAM, LIME, Integrated Gradients, and SHAP, which consistently highlighted attention to clinically relevant features such as nuclear contour irregularities and chromatin condensation. These results underscore the potential of the model to deliver non-invasive, accurate and transparent diagnostics that pave the way for its integration into clinical hematology workflows and advancing AI-driven leukemia screening paradigms. Index Terms\u2014Acute Lymphoblastic Leukemia (ALL); Causal-Former-HMC; Hybrid Deep Learning; Peripheral Blood Smear Classification; Explainable AI in Medical Imaging.<\/jats:p>","DOI":"10.3389\/fcell.2025.1674393","type":"journal-article","created":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T05:27:37Z","timestamp":1760333257000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["CausalFormer-HMC: a hybrid memory-driven transformer with causal reasoning and counterfactual explainability for leukemia diagnosis"],"prefix":"10.3389","volume":"13","author":[{"given":"Fares","family":"Jammal","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohamed","family":"Dahab","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,10,13]]},"reference":[{"key":"B23","doi-asserted-by":"publisher","first-page":"105762","DOI":"10.1016\/j.compeleceng.2024.109446","article-title":"A review on leukemia detection and classification using Artificial Intelligence-based techniques","volume":"147","author":"Aby","year":"2022","journal-title":"Comput. Biol. Med."},{"key":"B1","doi-asserted-by":"publisher","first-page":"3168","DOI":"10.3390\/electronics11193168","article-title":"A deep learning-based approach for the diagnosis of acute lymphoblastic leukemia","volume":"11","author":"Ahmed","year":"2022","journal-title":"Electronics"},{"key":"B24","doi-asserted-by":"publisher","first-page":"e234","DOI":"10.1186\/s12885-024-12646-3","article-title":"Evaluation of a machine-learning model based on laboratory parameters for the prediction of acute leukaemia subtypes: a multicentre model development","volume":"6","author":"Alcazer","year":"2024","journal-title":"Lancet Digital Health"},{"key":"B13","doi-asserted-by":"publisher","first-page":"1402926","DOI":"10.3389\/fdata.2024.1402926","article-title":"Artificial intelligence for the detection of acute myeloid leukemia from microscopic blood images; a systematic review and meta-analysis","volume":"7","author":"Al-Obeidat","year":"2025","journal-title":"Front. Big Data"},{"key":"B28","doi-asserted-by":"publisher","first-page":"322","DOI":"10.3390\/applbiosci4010009","article-title":"A customized efficient deep learning model for the diagnosis of acute leukemia cells based on lymphocyte and monocyte images","volume":"23","author":"Ansari","year":"2023","journal-title":"Sensors"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.34740\/kaggle\/dsv\/2175623","article-title":"Acute lymphoblastic leukemia (ALL) image dataset","author":"Aria","year":"2021"},{"key":"B4","doi-asserted-by":"publisher","first-page":"10930728","DOI":"10.3390\/diagnostics13071330","article-title":"Artificial intelligence-based management of adult chronic myeloid leukemia: where are We and where are We going?","volume":"6","author":"Bain","year":"2024","journal-title":"Front. Hematol."},{"key":"B5","doi-asserted-by":"publisher","first-page":"100234","DOI":"10.1016\/j.modpat.2023.100234","article-title":"The significance of International Federation of Gynecology and Obstetrics grading in Microsatellite instability-high and POLE-Mutant Endometrioid Endometrial Carcinoma","volume":"36","author":"Bain","year":"2023","journal-title":"Mod. Pathol."},{"key":"B6","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1016\/j.pcl.2014.09.004","article-title":"Biology of childhood acute lymphoblastic leukemia","volume":"62","author":"Bhojwani","year":"2015","journal-title":"Pediatr. Clin. N. Am."},{"key":"B7","doi-asserted-by":"publisher","first-page":"034502","DOI":"10.1117\/1.JMI.11.3.034502","article-title":"Quantifying lung fissure integrity using a three-dimensional patch-based convolutional neural network on CT images for emphysema treatment planning","volume":"11","author":"Chaurasia","year":"2024","journal-title":"J. Med. Imaging"},{"key":"B8","doi-asserted-by":"publisher","first-page":"100397","DOI":"10.1016\/j.array.2025.100397","article-title":"Deep learning-based detection and classification of acute lymphoblastic leukemia with explainable AI techniques","volume":"25","author":"Chen","year":"2025","journal-title":"Array"},{"key":"B26","doi-asserted-by":"publisher","first-page":"58580","DOI":"10.1038\/s41598-024-59259-1","article-title":"Deep learning assists in acute leukemia detection and cell classification via flow cytometry using the acute leukemia orientation tube","volume":"14","author":"Cheng","year":"2024","journal-title":"Sci. Rep."},{"key":"B2","doi-asserted-by":"publisher","first-page":"107437","DOI":"10.1016\/j.leukres.2024.107437","article-title":"Artificial intelligence-based prediction models for acute myeloid leukemia using real-life data: a DATAML registry study","volume":"136","author":"Didi","year":"2024","journal-title":"Leukemia Res."},{"key":"B10","article-title":"LEU3: an attention Augmented-based model for acute lymphoblastic leukemia classification","volume-title":"Proc. IEEE","author":"Dutta","year":"2023"},{"key":"B11","doi-asserted-by":"publisher","first-page":"7184","DOI":"10.1182\/blood-2023-187037","article-title":"Deep learning models for the diagnosis of acute lymphoblastic leukemia from bone marrow images: a comprehensive literature review","volume":"140","author":"Elsayed","year":"2022","journal-title":"Blood"},{"key":"B12","doi-asserted-by":"publisher","first-page":"1330977","DOI":"10.3389\/fonc.2023.1330977","article-title":"Deep learning enhances acute lymphoblastic leukemia diagnosis and classification using bone marrow images","volume":"13","author":"Elsayed","year":"2023","journal-title":"Front. Oncol."},{"key":"B15","doi-asserted-by":"publisher","first-page":"1891","DOI":"10.1182\/blood.2023020794","article-title":"Diagnosis, prognostic factors, and assessment of ALL in adults: 2024 ELN recommendations from a European expert panel","volume":"143","author":"G\u00f6kbuget","year":"2024","journal-title":"Blood"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.7937\/tcia.2019.dc64i46r","article-title":"ALL Challenge dataset of ISBI 2019","author":"Gupta","year":"2019","journal-title":"Cancer Imaging Archive"},{"key":"B17","doi-asserted-by":"publisher","first-page":"101788","DOI":"10.1016\/j.media.2020.101788","article-title":"GCTI-SN: Geometry-inspired chemical and tissue invariant stain normalization of microscopic medical images","volume":"65","author":"Gupta","year":"2020","journal-title":"Med. Image Anal."},{"key":"B9","doi-asserted-by":"publisher","first-page":"106943","DOI":"10.1016\/j.medengphy.2022.103793","article-title":"C-NMC: B-lineage acute lymphoblastic leukemia: a blood cancer dataset","volume":"222","author":"Gupta","year":"2022","journal-title":"Comput. Methods Programs Biomed."},{"key":"B18","doi-asserted-by":"publisher","first-page":"e11888852","DOI":"10.7717\/peerj-cs.1852","article-title":"ALL-Net: integrating CNN and explainable-AI for enhanced diagnosis and interpretation of acute lymphoblastic leukemia","volume":"10","author":"Gupta","year":"2024","journal-title":"PeerJ Comput. Sci."},{"key":"B19","doi-asserted-by":"publisher","first-page":"67826","DOI":"10.1038\/s41598-024-58452-6","article-title":"An attention-based deep learning for acute lymphoblastic leukemia classification","volume":"14","author":"Huang","year":"2024","journal-title":"Sci. Rep."},{"key":"B20","doi-asserted-by":"publisher","first-page":"2040","DOI":"10.3390\/diagnostics15162040","article-title":"Neuro-bridge-X: a neuro-Symbolic vision transformer with meta-XAI for interpretable leukemia diagnosis from peripheral blood smears","volume":"15","author":"Jammal","year":"2025","journal-title":"Diagnostics"},{"key":"B21","doi-asserted-by":"publisher","first-page":"29541","DOI":"10.1109\/access.2023.3260065","article-title":"Pattern recognition of acute lymphoblastic leukemia (ALL) using computational deep learning","volume":"11","author":"Jiwani","year":"2023","journal-title":"IEEE Access"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3260065","article-title":"Deep learning algorithms for early diagnosis of acute lymphoblastic leukemia","author":"Jiwani","year":"2024","journal-title":"arXiv Prepr. arXiv:2407.10251"},{"key":"B27","doi-asserted-by":"publisher","first-page":"3812","DOI":"10.3390\/s22103812","article-title":"A new self-calibration and Compensation method for Installation Errors of Uniaxial rotation module Inertial Navigation system","volume":"22","author":"Rahman","year":"2022","journal-title":"Sensors"},{"key":"B14","doi-asserted-by":"publisher","first-page":"34567","DOI":"10.1007\/s11042-023-15683-5","article-title":"Machine learning in detection and classification of leukemia using C-NMC_Leukemia","volume":"82","author":"Talaat","year":"2023","journal-title":"Multimedia Tools Appl."},{"key":"B25","doi-asserted-by":"publisher","first-page":"102876","DOI":"10.1016\/j.media.2023.102876","article-title":"Deep learning for leukemia classification using microscopic blood images","volume":"89","author":"Wang","year":"2023","journal-title":"Med. Image Anal."},{"key":"B29","doi-asserted-by":"publisher","first-page":"83","DOI":"10.3322\/caac.21219","article-title":"Childhood and adolescent cancer statistics","volume":"64","author":"Ward","year":"2014","journal-title":"CA A Cancer J. Clin."},{"key":"B30","doi-asserted-by":"publisher","first-page":"987654","DOI":"10.2196\/36490","article-title":"A review of artificial intelligence applications in hematology Management: current practices and future Prospects","volume":"5","author":"Wu","year":"2022","journal-title":"Front. Artif. Intell."},{"key":"B31","doi-asserted-by":"publisher","first-page":"12646","DOI":"10.1186\/s12885-024-12256-z","article-title":"Artificial intelligence reveals the predictions of hematological indexes in children with acute leukemia","volume":"24","author":"Wu","year":"2024","journal-title":"BMC Cancer"}],"container-title":["Frontiers in Cell and Developmental Biology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcell.2025.1674393\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T05:27:38Z","timestamp":1760333258000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcell.2025.1674393\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,13]]},"references-count":31,"alternative-id":["10.3389\/fcell.2025.1674393"],"URL":"https:\/\/doi.org\/10.3389\/fcell.2025.1674393","relation":{},"ISSN":["2296-634X"],"issn-type":[{"value":"2296-634X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,13]]},"article-number":"1674393"}}