{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T12:37:48Z","timestamp":1787315868196,"version":"build-2736575974"},"reference-count":26,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T00:00:00Z","timestamp":1767916800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Taif University, Saudi Arabia","award":["TU-DSPP-2025-55"],"award-info":[{"award-number":["TU-DSPP-2025-55"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background\/Objectives: Conventional workflows, peripheral blood smears, and bone marrow assessment supplemented by LDI-PCR, molecular cytogenetics, and array-CGH, are expert-driven in the face of biological and imaging variability. Methods: We propose an AI pipeline that integrates convolutional neural networks (CNNs) and transfer learning-based models with two explainable AI (XAI) approaches, LIME and Grad-Cam, to deliver both high diagnostic accuracy and transparent rationale. Seven public sources were curated into a unified benchmark (66,550 images) covering ALL, AML, CLL, CML, and healthy controls; images were standardized, ROI-cropped, and split with stratification (80\/10\/10). We fine-tuned multiple backbones (DenseNet-121, MobileNetV2, VGG16, InceptionV3, ResNet50, Xception, and a custom CNN) and evaluated the accuracy and F1-score, benchmarking against the recent literature. Results: On the five-class task (ALL\/AML\/CLL\/CML\/Healthy), MobileNetV2 achieved 97.9% accuracy\/F1, with DenseNet-121 reaching 97.66% F1. On ALL subtypes (Benign, Early, Pre, Pro) and across tasks, DenseNet121 and MobileNetV2 were the most reliable, achieving state-of-the-art accuracy with the strongest, nucleus-centric explanations. Conclusions: XAI analyses (LIME, Grad-CAM) consistently localized leukemic nuclei and other cell-intrinsic morphology, aligning saliency with clinical cues and model performance. Compared with baselines, our approach matched or exceeded accuracy while providing stronger, corroborated interpretability on a substantially larger and more diverse dataset.<\/jats:p>","DOI":"10.3390\/diagnostics16020212","type":"journal-article","created":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T09:25:02Z","timestamp":1767950702000},"page":"212","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Demystifying Deep Learning Decisions in Leukemia Diagnostics Using Explainable AI"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9999-2561","authenticated-orcid":false,"given":"Shahd H.","family":"Altalhi","sequence":"first","affiliation":[{"name":"Department of Computer Science, College of Computers and Information Technology, Taif University, Taif 21944, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7785-6980","authenticated-orcid":false,"given":"Salha M.","family":"Alzahrani","sequence":"additional","affiliation":[{"name":"Department of Computer Science, College of Computers and Information Technology, Taif University, Taif 21944, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,1,9]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Ansari, S., Navin, A.H., Babazadeh Sangar, A., Vaez Gharamaleki, J., and Danishvar, S. (2023). Acute Leukemia Diagnosis Based on Images of Lymphocytes and Monocytes Using Type-II Fuzzy Deep Network. Electronics, 12.","DOI":"10.3390\/electronics12051116"},{"key":"ref_2","first-page":"593","article-title":"A New Method for Diagnosis of Leukemia Utilizing a Hybrid DL-ML Approach for Binary and Multi-Class Classification on a Limited-Sized Database","volume":"139","author":"Deshpande","year":"2024","journal-title":"Comput. Model. Eng. Sci."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Alzahrani, A.K., Alsheikhy, A.A., Shawly, T., Azzahrani, A., and Said, Y. (2023). A Novel Deep Learning Segmentation and Classification Framework for Leukemia Diagnosis. Algorithms, 16.","DOI":"10.3390\/a16120556"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Elsayed, B., Elhadary, M., Elshoeibi, R.M., Elshoeibi, A.M., Badr, A., Metwally, O., ElSherif, R.A., Salem, M.E., Khadadah, F., and Alshurafa, A. (2023). Deep learning enhances acute lymphoblastic leukemia diagnosis and classification using bone marrow images. Front. Oncol., 13.","DOI":"10.3389\/fonc.2023.1330977"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Kaur, M., AlZubi, A.A., Jain, A., Singh, D., Yadav, V., and Alkhayyat, A. (2023). DSCNet: Deep Skip Connections-Based Dense Network for ALL Diagnosis Using Peripheral Blood Smear Images. Diagnostics, 13.","DOI":"10.3390\/diagnostics13172752"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Alkhalaf, S., Alturise, F., Bahaddad, A.A., Elnaim, B.M.E., Shabana, S., Abdel-Khalek, S., and Mansour, R.F. (2023). Adaptive Aquila Optimizer with Explainable Artificial Intelligence-Enabled Cancer Diagnosis on Medical Imaging. Cancers, 15.","DOI":"10.3390\/cancers15051492"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"104722","DOI":"10.1016\/j.bspc.2023.104722","article-title":"Automated detection and classification of leukemia on a subject-independent test dataset using deep transfer learning supported by Grad-CAM visualization","volume":"83","author":"Abhishek","year":"2023","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_8","first-page":"1","article-title":"Explainable AI for binary and multi-class classification of leukemia using a modified transfer learning ensemble model","volume":"17","author":"Deshpande","year":"2024","journal-title":"Int. J. Smart Sens. Intell. Syst."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"424","DOI":"10.1182\/blood-2016-08-733196","article-title":"Diagnosis and management of AML in adults: 2017 ELN recommendations from an international expert panel","volume":"129","author":"Estey","year":"2017","journal-title":"Blood"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"17415","DOI":"10.1007\/s00521-023-08607-9","article-title":"Refinement of ensemble strategy for acute lymphoblastic leukemia microscopic images using hybrid CNN-GRU-BiLSTM and MSVM classifier","volume":"35","author":"Mohammed","year":"2023","journal-title":"Neural Comput. Appl."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"101244","DOI":"10.1016\/j.imu.2023.101244","article-title":"A mobile application based on efficient lightweight CNN model for classification of B-ALL cancer from non-cancerous cells: A design and implementation study","volume":"39","author":"Hosseini","year":"2023","journal-title":"Inform. Med. Unlocked"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Sulaiman, A., Kaur, S., Gupta, S., Alshahrani, H., Reshan, M.S.A., Alyami, S., and Shaikh, A. (2023). ResRandSVM: Hybrid Approach for Acute Lymphocytic Leukemia Classification in Blood Smear Images. Diagnostics, 13.","DOI":"10.3390\/diagnostics13122121"},{"key":"ref_13","first-page":"422","article-title":"A New Model for Blood Cancer Classification Based on Deep Learning Techniques","volume":"14","author":"Mohamed","year":"2023","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Diaz Resendiz, J.L., Ponomaryov, V., Reyes Reyes, R., and Sadovnychiy, S. (2023). Explainable CAD System for Classification of Acute Lymphoblastic Leukemia Based on a Robust White Blood Cell Segmentation. Cancers, 15.","DOI":"10.3390\/cancers15133376"},{"key":"ref_15","first-page":"221","article-title":"Evaluation of Heat Map Methods Using Cell Morphology for Classifying Acute Lymphoblastic Leukemia Cells","volume":"28","year":"2024","journal-title":"Comput. Sist."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Genovese, A., Piuri, V., and Scotti, F. (2023, January 4\u201310). ALL-IDB Patches: Whole Slide Imaging for Acute Lymphoblastic Leukemia Detection Using Deep Learning. Proceedings of the 2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops, ICASSPW, Rhodes Island, Greece.","DOI":"10.1109\/ICASSPW59220.2023.10193429"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"54758","DOI":"10.1109\/ACCESS.2024.3388715","article-title":"Feature Fusion Based Ensemble of Deep Networks for Acute Leukemia Diagnosis Using Microscopic Smear Images","volume":"12","author":"Himel","year":"2024","journal-title":"IEEE Access"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Raza, M.U., Nawaz, A., Liu, X.T., Chen, Z.Z., Leung, V.C.M., Chen, J., and Li, J.Q. (2023, January 9\u201311). Visual Explanations: Activation-based Acute Lymphoblastic Leukemia Cell Classification. Proceedings of the 2023 IEEE International Conference on Development and Learning, ICDL, Macau, China.","DOI":"10.1109\/ICDL55364.2023.10364466"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Ghnemat, R., Alodibat, S., and Abu Al-Haija, Q. (2023). Explainable Artificial Intelligence (XAI) for Deep Learning Based Medical Imaging Classification. J. Imaging, 9.","DOI":"10.3390\/jimaging9090177"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"542","DOI":"10.1016\/j.csbj.2024.08.005","article-title":"Unveiling the black box: A systematic review of Explainable Artificial Intelligence in medical image analysis","volume":"24","author":"Muhammad","year":"2024","journal-title":"Comput. Struct. Biotechnol. J."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"102239","DOI":"10.1016\/j.displa.2022.102239","article-title":"A review of visualisation-as-explanation techniques for convolutional neural networks and their evaluation","volume":"73","author":"Mohamed","year":"2022","journal-title":"Displays"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"966","DOI":"10.3390\/biomedinformatics4020054","article-title":"Advancing Early Leukemia Diagnostics: A Comprehensive Study Incorporating Image Processing and Transfer Learning","volume":"4","author":"Haque","year":"2024","journal-title":"BioMedInformatics"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Shlens, J., and Le, Q.V. (2019). RandAugment: Practical automated data augmentation with a reduced search space. arXiv.","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref_24","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., and Lopez-Paz, D. (2018). mixup: Beyond Empirical Risk Minimization. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Yun, S., Han, D., Oh, S.J., Chun, S., Choe, J., and Yoo, Y. (2019). CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features. arXiv.","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref_26","unstructured":"Hendrycks, D., Mu, N., Cubuk, E.D., Zoph, B., Gilmer, J., and Lakshminarayanan, B. (2020). AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty. arXiv."}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/2\/212\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T09:31:41Z","timestamp":1767951101000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/2\/212"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,9]]},"references-count":26,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["diagnostics16020212"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics16020212","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,9]]}}}