{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T05:10:58Z","timestamp":1778735458825,"version":"3.51.4"},"reference-count":33,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T00:00:00Z","timestamp":1778716800000},"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. Oncol."],"abstract":"<jats:p>Acute myeloid leukemia (AML) is a life-threatening hematological malignancy that requires accurate and timely diagnosis for effective clinical management. However, conventional cytomorphological analysis is time-consuming, subjective, and highly dependent on expert interpretation. Existing artificial intelligence-based approaches are often limited by severe class imbalance and inadequate feature representation, which restrict their generalization capability. To address these challenges, this study proposes a robust and high-performance AML classification framework based on hybrid feature fusion and deep learning. The proposed approach integrates handcrafted features with deep representations extracted from DenseNet201 and MobileNetV2 to form the Hybrid AML Descriptor Network (HADNet), which is further combined with the Transformer-based Tri block Convolutional Multi head Attention Network (TCMA-Net) classifier to capture both local and global contextual information. In addition, a Synthetic Acquisition Artifact Augmentation (S3A) strategy is introduced to mitigate class imbalance by generating realistic variations in illumination and noise. Extensive experiments were conducted on the AML cytomorphology Ludwig Maximilian University (LMU) dataset, where the proposed framework achieved a testing accuracy of 99.20%, outperforming traditional machine learning models and deep learning baselines. The effectiveness of the approach is further validated through ablation studies and external evaluation on the acute lymphoblastic leukemia (ALL) dataset, demonstrating strong robustness and generalization across different data distributions. Overall, the results indicate that the integration of handcrafted and deep features significantly enhances classification performance, stability, and reliability. The proposed framework provides a promising solution for automated AML diagnosis and has the potential to support clinical decision-making systems.<\/jats:p>","DOI":"10.3389\/fonc.2026.1774702","type":"journal-article","created":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T04:26:59Z","timestamp":1778732819000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Hybrid handcrafted and deep feature fusion for automated acute myeloid leukemia classification using TCMA-Net on a class-balanced dataset"],"prefix":"10.3389","volume":"16","author":[{"given":"Osama M.","family":"Alshehri","sequence":"first","affiliation":[{"name":"Department of Clinical Laboratory Sciences, College of Applied Medical Sciences, Najran University","place":["Najran, Saudi Arabia"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zohaib","family":"Mushtaq","sequence":"additional","affiliation":[{"name":"Department of Electrical, Electronics and Computer Systems, University of Sargodha","place":["Sargodha, Pakistan"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad","family":"Taha","sequence":"additional","affiliation":[{"name":"Department of Electronics Engineering, Islamia University of Bahawalpur","place":["Bahawalpur, Pakistan"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maham","family":"Ijaz","sequence":"additional","affiliation":[{"name":"Department of Food Science and Technology, Islamia University of Bahawalpur","place":["Bahawalpur, Pakistan"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad","family":"Irfan","sequence":"additional","affiliation":[{"name":"Electrical Engineering Department, College of Engineering, Najran University","place":["Najran, Saudi Arabia"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Malik A.","family":"Altayar","sequence":"additional","affiliation":[{"name":"Department of Medical Laboratory Technology, Faculty of Applied Medical Sciences, University of Tabuk","place":["Tabuk, Saudi Arabia"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohammed M.","family":"Jalal","sequence":"additional","affiliation":[{"name":"Department of Medical Laboratory Technology, Faculty of Applied Medical Sciences, University of Tabuk","place":["Tabuk, Saudi Arabia"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohammed H.","family":"Abu-Alghayth","sequence":"additional","affiliation":[{"name":"Department of Medical Laboratory Sciences, College of Applied Medical Sciences, University of Bisha","place":["Bisha, Saudi Arabia"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Humood","family":"Al Shmrany","sequence":"additional","affiliation":[{"name":"Department of Medical Laboratory, College of Applied Medical Sciences, Prince Sattam bin Abdulaziz University","place":["Alkharj, Saudi Arabia"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Elhashimi","family":"Eltayb Hassan","sequence":"additional","affiliation":[{"name":"Department of Clinical Laboratory Science, College of Applied Medical Sciences, Najran University","place":["Najran, Saudi Arabia"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,5,14]]},"reference":[{"key":"B1","volume-title":"Bone marrow: What it is and why it is important","year":"2024"},{"key":"B2","volume-title":"Leukemia: Symptoms, signs, causes, types and treatment","year":"2024"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1038\/bcj.2017.53","article-title":"Acute lymphoblastic leukemia: A comprehensive review and 2017 update","volume":"7","author":"Terwilliger","year":"2017","journal-title":"Blood Cancer J"},{"key":"B4","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1182\/asheducation-2004.1.98","article-title":"Acute myeloid leukemia","volume":"2004","author":"Stone","year":"2004","journal-title":"Hematology"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1007\/s00277-012-1460-z","article-title":"Immunological aspects in chronic lymphocytic leukemia (CLL) development","volume":"91","author":"Garc\u00eda-Mu\u00f1oz","year":"2012","journal-title":"Ann Hematol"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.2147\/JBM.S382090","article-title":"Chronic myeloid leukemia, from pathophysiology to treatment-free remission: A narrative literature review","volume":"14","author":"Rinaldi","year":"2023","journal-title":"J Blood Med"},{"key":"B7","volume-title":"Acute myeloid leukemia (AML): symptoms, treatment and prognosis","year":"2024"},{"key":"B8","volume-title":"What is the impact of AML on the immune system","year":"2023"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.20.00475","article-title":"Immune biology of acute myeloid leukemia: Implications for immunotherapy","volume":"39","author":"Khaldoyanidi","year":"2021","journal-title":"J Clin Oncol"},{"key":"B10","volume-title":"Can acute myeloid leukemia (AML) be prevented","year":"2024"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1016\/j.tips.2024.03.005","article-title":"AML treatment: Conventional chemotherapy and emerging novel agents","volume":"45","author":"Forsberg","year":"2024","journal-title":"Trends Pharmacol Sci"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1080\/16078454.2022.2158015","article-title":"Acute myeloid leukemia: Challenges for diagnosis and treatment in Latin America","volume":"28","author":"G\u00f3mez-De Le\u00f3n","year":"2023","journal-title":"Hematology"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2025.112244","article-title":"Enhanced detection of acute leukemia: A hybrid machine learning framework with adaptive weight-optimized level set evolution","volume":"161","author":"Das","year":"2025","journal-title":"Eng Appl Artif Intell"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1007\/s11760-021-01976-5","article-title":"Acute myelogenous leukemia detection using optimal neural network based on fractional black-widow model","volume":"16","author":"Ramya","year":"2022","journal-title":"Signal Image Video Process"},{"key":"B15","doi-asserted-by":"publisher","first-page":"16988","DOI":"10.1038\/s41598-023-44210-7","article-title":"Morphological diagnosis of hematologic Malignancy using feature fusion-based deep convolutional neural network","volume":"13","author":"Yadav","year":"2023","journal-title":"Sci Rep"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.105813","article-title":"A blood cell classification method based on MAE and active learning","volume":"90","author":"Lu","year":"2024","journal-title":"BioMed Signal Process Control"},{"key":"B17","doi-asserted-by":"publisher","first-page":"23782","DOI":"10.1038\/s41598-025-05585-x","article-title":"Multiclass leukemia cell classification using hybrid deep learning and machine learning with CNN-based feature extraction","volume":"15","author":"Kasim","year":"2025","journal-title":"Sci Rep"},{"key":"B18","doi-asserted-by":"crossref","DOI":"10.1109\/ICOEI.2017.8300983","article-title":"Detection of leukemia and its types using image processing and machine learning","author":"Jagadev","year":"2017"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.105741","article-title":"Classification of acute myeloid leukemia M1 and M2 subtypes using machine learning","volume":"147","author":"Liu","year":"2022","journal-title":"Comput Biol Med"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.3390\/bioengineering7040120","article-title":"Detection and classification of immature leukocytes for diagnosis of acute myeloid leukemia using random forest algorithm","volume":"7","author":"Dasariraju","year":"2020","journal-title":"Bioengineering"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics13020196","article-title":"Classification of atypical white blood cells in acute myeloid leukemia using a two-stage hybrid model based on deep convolutional autoencoder and deep convolutional neural network","volume":"13","author":"Elhassan","year":"2023","journal-title":"Diagnostics"},{"key":"B22","doi-asserted-by":"crossref","DOI":"10.1109\/ATSIP62566.2024.10638869","article-title":"Semantic segmentation of myeloid cells on blood smears","author":"Lazouni","year":"2024"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3386591","article-title":"Multivariate technique for detecting variations in high-dimensional imagery","volume":"12","author":"Sanusi","year":"2024","journal-title":"IEEE Access"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3149637","article-title":"Feature extraction of white blood cells using CMYK-moment localization and deep learning in acute myeloid leukemia blood smear microscopic images","volume":"10","author":"Elhassan","year":"2022","journal-title":"IEEE Access"},{"key":"B25","doi-asserted-by":"publisher","first-page":"87","DOI":"10.5815\/ijigsp.2024.04.07","article-title":"Computerized acute myeloid leukemia classification using hybrid dilated dense squeeze network from peripheral B stain analysis","volume":"16","author":"Prasad Palli","year":"2024","journal-title":"Int J Image Graphics Signal Process"},{"key":"B26","doi-asserted-by":"publisher","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":"B27","article-title":"Aml-cytomorphology lmu","year":"2018"},{"key":"B28","first-page":"1","article-title":"DenseNet201 based feature extraction for remote sensing image classification in land cover monitoring","author":"Aluvala","year":"2023"},{"key":"B29","doi-asserted-by":"crossref","DOI":"10.1109\/ICREST51555.2021.9331214","article-title":"Transfer learning approach for plant leaf disease detection using CNN with pre-trained feature extraction method Mobilnetv2","author":"Moyazzoma","year":"2021"},{"key":"B30","volume-title":"chi2 \u2014 scikit-learn 1.7.2 documentation","year":"2024"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-024-19899-x","article-title":"ConcatNeXt: An automated blood cell classification with a new deep convolutional neural network","volume":"84","author":"Erten","year":"2024","journal-title":"Multimedia Tools Appl"},{"key":"B32","first-page":"71","article-title":"Deep learning-based leukemia diagnosis from bone marrow images","volume-title":"Information and Communication Technologies","author":"Zhinin-Vera","year":"2024"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1177\/20552076261428734","article-title":"Multiscale contextual attention network for robust diagnosis of acute lymphoblastic leukemia in blood smears: Implications for clinical adoption and the role of medical science liaisons","volume":"12","author":"Waqar","year":"2026","journal-title":"DIGITAL Health"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1774702\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T04:27:10Z","timestamp":1778732830000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1774702\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,14]]},"references-count":33,"alternative-id":["10.3389\/fonc.2026.1774702"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2026.1774702","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,14]]},"article-number":"1774702"}}