{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T21:22:37Z","timestamp":1770240157685,"version":"3.49.0"},"reference-count":39,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T00:00:00Z","timestamp":1770163200000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Deanship of Graduate Studies and Scientific Research at Najran University, Kingdom of Saudi Arabia Easy Track Research funding program","award":["NU\/EFP\/MRC\/13\/200"],"award-info":[{"award-number":["NU\/EFP\/MRC\/13\/200"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Blood cell classification through microscopic image analysis is a critical yet challenging task in hematological diagnostics. Traditional manual examination is time-consuming, prone to human error, and often requires extensive expertise. While existing automated solutions using conventional deep learning approaches show promise, they frequently struggle with capturing both local cellular details and global contextual features necessary for accurate classification.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Aim<\/jats:title>\n                    <jats:p>This study proposes a novel approach to automate blood cell type classification by developing a hybrid deep learning architecture that effectively combines the strengths of both convolutional neural networks (CNNs) and transformer models to enhance diagnostic accuracy and reliability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methodology<\/jats:title>\n                    <jats:p>We present a customized CoAtNet architecture that hierarchically integrates convolutional and transformer layers. The model comprises five progressive stages: two initial CNN stages with MBConv blocks for local feature extraction, followed by three transformer stages for global context modeling. The architecture employs relative attention mechanisms and features an adaptive channel scaling strategy [64\u2192768] with multi-head attention (heads: 1\u21928). The model was trained using the AdamW optimizer with decoupled weight decay (1e\u22125) and a carefully crafted regularization strategy combining dropout and batch normalization. We utilized a publicly available Kaggle blood cell image dataset comprising 9,957 images across four distinct blood cell classes. The dataset was split into 6,770 images for training, 1,693 for validation, and 1,494 for testing.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The proposed model achieved remarkable performance with 99% classification accuracy on the test dataset, significantly outperforming traditional CNN-only and transformer-only architectures.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The model demonstrated robust performance across different blood cell subtypes, with high precision and recall values. The exceptional accuracy of 99% demonstrates the effectiveness of combining local and global feature processing through the integration of CNNs and transformers.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.7717\/peerj-cs.3570","type":"journal-article","created":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T08:37:06Z","timestamp":1770194226000},"page":"e3570","source":"Crossref","is-referenced-by-count":0,"title":["Bridging AI and hematology: a novel hybrid model for accurate blood cell type classification"],"prefix":"10.7717","volume":"12","author":[{"given":"Osama M.","family":"Alshehri","sequence":"first","affiliation":[{"name":"Department of Clinical Laboratory Sciences, College of Applied Medical Sciences, Najran University, Najran, Saudi Arabia"}]},{"given":"Ahmad","family":"Shaf","sequence":"additional","affiliation":[{"name":"Computer Science, COMSATS Institute of Information Technology, Sahiwal, Pakistan"}]},{"given":"Muhammad","family":"Irfan","sequence":"additional","affiliation":[{"name":"Electrical Engineering Department, College of Engineering, Najran University, Najran, Saudi Arabia"}]},{"given":"Mohammed M.","family":"Jalal","sequence":"additional","affiliation":[{"name":"Department of Medical Laboratory Technology, Faculty of Applied Medical Sciences, University of Tabuk, Tabuk, Saudi Arabia"}]},{"given":"Malik A.","family":"Altayar","sequence":"additional","affiliation":[{"name":"Department of Medical Laboratory Technology, Faculty of Applied Medical Sciences, University of Tabuk, Tabuk, Saudi Arabia"}]},{"given":"Mohammed H.","family":"Abu-Alghayth","sequence":"additional","affiliation":[{"name":"Department of Medical Laboratory Sciences, College of Applied Medical Sciences, University of Bisha, Bisha, Saudi Arabia"}]},{"given":"Tareg M.","family":"Belali","sequence":"additional","affiliation":[{"name":"Department of Medical Laboratory Sciences, College of Applied Medical Sciences, University of Bisha, Bisha, Saudi Arabia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2445-0519","authenticated-orcid":true,"given":"Tariq","family":"Ali","sequence":"additional","affiliation":[{"name":"Artificial Intelligence and Sensing Technologies (AIST) Research Center, University of Tabuk, Tabuk, Saudi Arabia"}]},{"given":"Humood Al","family":"Shmrany","sequence":"additional","affiliation":[{"name":"Department of Medical Laboratory, College of Applied Medical Sciences, Prince Sattam Bin Abdulaziz University, Alkharj, Saudi Arabia"}]}],"member":"4443","published-online":{"date-parts":[[2026,2,4]]},"reference":[{"issue":"3","key":"10.7717\/peerj-cs.3570\/ref-1","doi-asserted-by":"publisher","first-page":"103341","DOI":"10.1016\/j.bspc.2021.103341","article-title":"Automated classification of acute leukemia on a heterogeneous dataset using machine learning and deep learning techniques","volume":"72","author":"Abhishek","year":"2022","journal-title":"Biomedical Signal Processing and Control"},{"issue":"4","key":"10.7717\/peerj-cs.3570\/ref-2","doi-asserted-by":"publisher","first-page":"1473","DOI":"10.1007\/s10439-009-9866-z","article-title":"Classification of leukemia blood samples using neural networks","volume":"38","author":"Adjouadi","year":"2010","journal-title":"Annals of Biomedical Engineering"},{"key":"10.7717\/peerj-cs.3570\/ref-3","first-page":"1","article-title":"Diagnosis of leukemia disease through deep learning using microscopic images","author":"Ain","year":"2022"},{"issue":"18","key":"10.7717\/peerj-cs.3570\/ref-4","doi-asserted-by":"publisher","first-page":"2093","DOI":"10.3390\/diagnostics14182093","article-title":"An innovative hybrid model for automatic detection of white blood cells in clinical laboratories","volume":"14","author":"Aksoy","year":"2024","journal-title":"Diagnostics"},{"issue":"1","key":"10.7717\/peerj-cs.3570\/ref-5","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1186\/s12880-024-01254-z","article-title":"Deep learning-based image annotation for leukocyte segmentation and classification of blood cell morphology","volume":"24","author":"Anand","year":"2024","journal-title":"BMC Medical Imaging"},{"issue":"2","key":"10.7717\/peerj-cs.3570\/ref-6","doi-asserted-by":"publisher","first-page":"322","DOI":"10.3390\/electronics12020322","article-title":"A customized efficient deep learning model for the diagnosis of acute leukemia cells based on lymphocyte and monocyte images","volume":"12","author":"Ansari","year":"2023","journal-title":"Electronics"},{"issue":"3","key":"10.7717\/peerj-cs.3570\/ref-7","doi-asserted-by":"publisher","first-page":"567","DOI":"10.3233\/xst-211055","article-title":"Leukemia classification using the deep learning method of CNN","volume":"30","author":"Arivuselvam","year":"2022","journal-title":"Journal of X-ray Science and Technology"},{"key":"10.7717\/peerj-cs.3570\/ref-8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2022\/2801227","article-title":"A deep learning framework for leukemia cancer detection in microscopic blood samples using squeeze and excitation learning","volume":"2022","author":"Bukhari","year":"2022","journal-title":"Mathematical Problems in Engineering"},{"issue":"26","key":"10.7717\/peerj-cs.3570\/ref-9","doi-asserted-by":"publisher","first-page":"37243","DOI":"10.1007\/s11042-022-13543-2","article-title":"A novel deep learning framework (DLF) for classification of acute lymphoblastic leukemia","volume":"81","author":"Chand","year":"2022","journal-title":"Multimedia Tools and Applications"},{"issue":"1","key":"10.7717\/peerj-cs.3570\/ref-10","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1186\/s12911-025-03027-2","article-title":"Advancing blood cell detection and classification: performance evaluation of modern deep learning models","volume":"25","author":"Choudhary","year":"2025","journal-title":"BMC Medical Informatics and Decision Making"},{"key":"10.7717\/peerj-cs.3570\/ref-11","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2106.04803","article-title":"CoAtNet: marrying convolution and attention for all data sizes","author":"Dai","year":"2021"},{"issue":"22","key":"10.7717\/peerj-cs.3570\/ref-12","doi-asserted-by":"publisher","first-page":"81741","DOI":"10.1109\/access.2022.3196037","article-title":"A systematic review on recent advancements in deep and machine learning based detection and classification of acute lymphoblastic leukemia","volume":"10","author":"Das","year":"2022","journal-title":"IEEE Access"},{"issue":"115311","key":"10.7717\/peerj-cs.3570\/ref-13","doi-asserted-by":"publisher","first-page":"115311","DOI":"10.1016\/j.eswa.2021.115311","article-title":"An efficient deep convolutional neural network based detection and classification of acute lymphoblastic leukemia","volume":"183","author":"Das","year":"2021","journal-title":"Expert Systems with Applications"},{"key":"10.7717\/peerj-cs.3570\/ref-14","doi-asserted-by":"publisher","first-page":"67","DOI":"10.2147\/sccaa.s262880","article-title":"Role of stem-cell transplantation in leukemia treatment","volume":"13","author":"Dessie","year":"2020","journal-title":"Stem Cells Cloning"},{"issue":"2","key":"10.7717\/peerj-cs.3570\/ref-15","doi-asserted-by":"publisher","first-page":"196","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"},{"issue":"20","key":"10.7717\/peerj-cs.3570\/ref-16","doi-asserted-by":"publisher","first-page":"22231","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 and Applications"},{"key":"10.7717\/peerj-cs.3570\/ref-17","first-page":"219","article-title":"An effective leukemia prediction technique using supervised machine learning classification algorithm","volume-title":"Advances in Intelligent Systems and Computing","author":"Hossain","year":"2021"},{"key":"10.7717\/peerj-cs.3570\/ref-18","doi-asserted-by":"publisher","first-page":"904292","DOI":"10.3389\/fonc.2022.904292","article-title":"Disease burden, risk factors, and trends of leukaemia: a global analysis","volume":"12","author":"Huang","year":"2022","journal-title":"Frontiers in Oncology"},{"issue":"9","key":"10.7717\/peerj-cs.3570\/ref-19","doi-asserted-by":"publisher","first-page":"1926","DOI":"10.3390\/jcm10091926","article-title":"Advances in the diagnosis and treatment of pediatric acute lymphoblastic leukemia","volume":"10","author":"Inaba","year":"2021","journal-title":"Journal of Clinical Medicine"},{"issue":"6","key":"10.7717\/peerj-cs.3570\/ref-20","doi-asserted-by":"publisher","first-page":"779","DOI":"10.1016\/s1470-2045(16)30029-8","article-title":"An international prognostic index for patients with chronic lymphocytic leukaemia (CLL-IPI): a meta-analysis of individual patient data","volume":"17","author":"International CLL-IPI Working Group","year":"2016","journal-title":"The Lancet Oncology"},{"key":"10.7717\/peerj-cs.3570\/ref-21","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"},{"issue":"1","key":"10.7717\/peerj-cs.3570\/ref-22","doi-asserted-by":"publisher","first-page":"82441","DOI":"10.1109\/access.2025.3563256","article-title":"Swin transformer and momentum contrast (MoCo) in leukemia diagnostics: a new paradigm in AI-driven blood cell cancer classification","volume":"13","author":"Jain","year":"2025","journal-title":"IEEE Access"},{"issue":"1","key":"10.7717\/peerj-cs.3570\/ref-23","doi-asserted-by":"publisher","first-page":"17447","DOI":"10.1038\/s41598-024-67826-9","article-title":"An attention-based deep learning for acute lymphoblastic leukemia classification","volume":"14","author":"Jawahar","year":"2024","journal-title":"Scientific Reports"},{"key":"10.7717\/peerj-cs.3570\/ref-24","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"},{"issue":"8","key":"10.7717\/peerj-cs.3570\/ref-25","doi-asserted-by":"publisher","first-page":"1186","DOI":"10.1002\/cncr.33477","article-title":"Acute myeloid leukemia: treatment and research outlook for 2021 and the MD anderson approach","volume":"127","author":"Kantarjian","year":"2021","journal-title":"Cancer"},{"key":"10.7717\/peerj-cs.3570\/ref-26","first-page":"520","article-title":"DinoBloom: a foundation model for generalizable cell embeddings in hematology","volume-title":"Lecture Notes in Computer Science","author":"Koch","year":"2024"},{"issue":"21","key":"10.7717\/peerj-cs.3570\/ref-27","doi-asserted-by":"publisher","first-page":"30121","DOI":"10.1007\/s11042-022-12539-2","article-title":"Automatic classification of white blood cells using deep features based convolutional neural network","volume":"81","author":"Meenakshi","year":"2022","journal-title":"Multimedia Tools and Applications"},{"issue":"7","key":"10.7717\/peerj-cs.3570\/ref-28","doi-asserted-by":"publisher","first-page":"501","DOI":"10.1002\/cyto.a.24839","article-title":"Comprehensive data analysis of white blood cells with classification and segmentation by using deep learning approaches","volume":"105","author":"\u00d6zcan","year":"2024","journal-title":"Cytometry Part A"},{"key":"10.7717\/peerj-cs.3570\/ref-29","first-page":"1344","article-title":"Hybrid vision transformer and CNN for leukemia detection in blood smear images","author":"Preethika","year":"2025"},{"issue":"105236","key":"10.7717\/peerj-cs.3570\/ref-30","doi-asserted-by":"publisher","first-page":"105236","DOI":"10.1016\/j.compbiomed.2022.105236","article-title":"LeuFeatx: deep learning-based feature extractor for the diagnosis of acute leukemia from microscopic images of peripheral blood smear","volume":"142","author":"Rastogi","year":"2022","journal-title":"Computers in Biology and Medicine"},{"issue":"19","key":"10.7717\/peerj-cs.3570\/ref-31","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":"Saeed","year":"2022","journal-title":"Electronics"},{"issue":"4","key":"10.7717\/peerj-cs.3570\/ref-32","doi-asserted-by":"publisher","first-page":"3143","DOI":"10.1007\/s40747-021-00564-x","article-title":"Categorizing white blood cells by utilizing deep features of proposed 4B-AdditionNet-based CNN network with ant colony optimization","volume":"8","author":"Shahzad","year":"2022","journal-title":"Complex & Intelligent Systems"},{"issue":"4","key":"10.7717\/peerj-cs.3570\/ref-33","doi-asserted-by":"publisher","first-page":"506","DOI":"10.1158\/2159-8290.cd-19-1011","article-title":"Advances in the treatment of acute myeloid leukemia: new drugs and new challenges","volume":"10","author":"Short","year":"2020","journal-title":"Cancer Discovery"},{"issue":"1","key":"10.7717\/peerj-cs.3570\/ref-34","doi-asserted-by":"publisher","first-page":"1165","DOI":"10.32604\/cmes.2025.067150","article-title":"A hybrid CNN-transformer framework for normal blood cell classification: towards automated hematological analysis","volume":"144","author":"Soomro","year":"2025","journal-title":"CMES Computer Modeling in Engineering and Sciences"},{"issue":"3","key":"10.7717\/peerj-cs.3570\/ref-35","doi-asserted-by":"publisher","first-page":"8063","DOI":"10.1007\/s11042-023-15923-8","article-title":"Machine learning in detection and classification of leukemia using C-NMC_Leukemia","volume":"83","author":"Talaat","year":"2023","journal-title":"Multimedia Tools and Applications"},{"key":"10.7717\/peerj-cs.3570\/ref-36","first-page":"181","article-title":"Enhancing blood cell classification by applying big transfer and (xai)","author":"Tanim","year":"2024"},{"issue":"6","key":"10.7717\/peerj-cs.3570\/ref-37","doi-asserted-by":"publisher","first-page":"e577","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 Journal"},{"issue":"3","key":"10.7717\/peerj-cs.3570\/ref-38","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1016\/j.engappai.2018.04.024","article-title":"Leukemia diagnosis in blood slides using transfer learning in CNNs and SVM for classification","volume":"72","author":"Vogado","year":"2018","journal-title":"Engineering Applications of Artificial Intelligence"},{"issue":"1","key":"10.7717\/peerj-cs.3570\/ref-39","doi-asserted-by":"publisher","first-page":"409","DOI":"10.32604\/cmc.2023.032432","article-title":"Automated artificial intelligence empowered white blood cells classification model","volume":"75","author":"Yamin","year":"2023","journal-title":"Computers, Materials & Continua"}],"container-title":["PeerJ Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/peerj.com\/articles\/cs-3570.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3570.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3570.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3570.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T08:37:09Z","timestamp":1770194229000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/articles\/cs-3570"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,4]]},"references-count":39,"alternative-id":["10.7717\/peerj-cs.3570"],"URL":"https:\/\/doi.org\/10.7717\/peerj-cs.3570","archive":["CLOCKSS","LOCKSS","Portico"],"relation":{},"ISSN":["2376-5992"],"issn-type":[{"value":"2376-5992","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,4]]},"article-number":"e3570"}}