{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T00:29:20Z","timestamp":1793320160052,"version":"4.5.0"},"reference-count":37,"publisher":"Public Library of Science (PLoS)","issue":"5","license":[{"start":{"date-parts":[[2025,5,8]],"date-time":"2025-05-08T00:00:00Z","timestamp":1746662400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Research, Development, and Innovation Authority","award":["13292-psu-2023-PSNU-R-3-1-EF-"],"award-info":[{"award-number":["13292-psu-2023-PSNU-R-3-1-EF-"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Medical image segmentation has numerous applications in diagnosing different diseases. Various types of diseases are found in white blood and Red blood cells. This paper represents the segmentation of WBCs from blood smear images. It is a complex and challenging task due to the frequent overlapping and variants in size and shape of WBCs with each other and RBCs. This overlapping is due to the rough border of the immature cells. The paper describes a new approach to WBC segmentation using UNet++, the marker watershed algorithm, and Neural Ordinary Differential Equations (ODE). This technique uses UNet++\u2009for pre-segmentation, followed by the marker watershed method, which has been integrated using ODE to deepen the segmentation process. This novel integration enhances clinical applications in automated blood cell analysis, diagnostic imaging, and disease monitoring, improving accuracy and robustness. The ODE is used after the convolution operation to reduce the error at each step, preventing the massive propagation of error in the forward and the backpropagation. The White blood cells are segmented from the input smear images using ALL_IDB1 and ALL_IDB2 datasets, which are further used in the experiment section. UNet\u2009++\u2009is used to generate the pre-segmented probabilistic grayscale images. Some white blood cells are connected and make groups appearing in the grayscale images. These groups of WBCs are separated using a technique called the marker watershed, which gives us the final segmented result. The experimentation results show that the mean intersection over union (Jaccard method), the Dice similarity coefficient, and the mean pixel accuracy are 97.73%, 98.36%, and 98.97%, respectively. The structure and size of the white blood cells vary from red blood cells and platelets, which makes this work different from others. Furthermore, the combination of UNet++, marker watershed, and Neural Ordinary Differential Equation makes the proposed system unique from existing systems. This work can be further investigated to reduce computational complexity and memory space for optimizing deployment on low-resource devices, such as smart healthcare systems. Techniques like model pruning, quantization, or learned information distillation might be explored to create a lightweight version of the model without much loss in accuracy. Such developments would make possible mass uses of automated white blood cell segmentation in portable, low-cost health devices for point-of-care remote diagnostics and monitoring.<\/jats:p>","DOI":"10.1371\/journal.pone.0320596","type":"journal-article","created":{"date-parts":[[2025,5,8]],"date-time":"2025-05-08T13:46:42Z","timestamp":1746712002000},"page":"e0320596","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":11,"title":["Deep learning based semantic segmentation of leukemia effected white blood cell"],"prefix":"10.1371","volume":"20","author":[{"given":"Zahoor","family":"Jan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3563-5981","authenticated-orcid":true,"given":"Muhammad","family":"Shabir","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2344-1522","authenticated-orcid":true,"given":"Haleem","family":"Farman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6330-2554","authenticated-orcid":true,"given":"Afzal","family":"Rahman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Moustafa","family":"M. Nasralla","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,5,8]]},"reference":[{"key":"pone.0320596.ref001","doi-asserted-by":"crossref","first-page":"132097","DOI":"10.1109\/ACCESS.2021.3114059","article-title":"Automated Diagnosis of Leukemia: A Comprehensive Review","volume":"9","author":"A Shah","year":"2021","journal-title":"IEEE Access"},{"issue":"4","key":"pone.0320596.ref002","doi-asserted-by":"crossref","first-page":"1629","DOI":"10.3390\/s22041629","article-title":"Multi-Method Diagnosis of Blood Microscopic Sample for Early Detection of Acute Lymphoblastic Leukemia Based on Deep Learning and Hybrid Techniques","volume":"22","author":"I Abunadi","year":"2022","journal-title":"Sensors (Basel)"},{"key":"pone.0320596.ref003","doi-asserted-by":"crossref","DOI":"10.7717\/peerj-cs.713","article-title":"A machine-learning scraping tool for data fusion in the analysis of sentiments about pandemics for supporting business decisions with human-centric AI explanations","volume":"7","author":"SA Kumar","year":"2021","journal-title":"PeerJ Comput Sci"},{"key":"pone.0320596.ref004","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1016\/j.compeleceng.2017.12.009","article-title":"Deep learning in big data Analytics: A comparative study","volume":"75","author":"B Jan","year":"2019","journal-title":"Computers & Electrical Engineering"},{"issue":"2","key":"pone.0320596.ref005","doi-asserted-by":"crossref","first-page":"2463","DOI":"10.32604\/cmc.2021.014904","article-title":"Optimized Predictive Framework for Healthcare Through Deep Learning","volume":"67","author":"Y Shahzad","year":"2021","journal-title":"Computers, Materials & Continua"},{"issue":"4","key":"pone.0320596.ref006","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1007\/s11032-025-01561-5","article-title":"Identification of a gene coding for a pentatricopeptide repeat protein as a candidate responsible for the Ms2, a novel restorer-of-fertility locus in onion (Allium cepa L.)","volume":"45","author":"G Kim","year":"2025","journal-title":"Mol Breed"},{"issue":"2","key":"pone.0320596.ref007","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1007\/s10015-021-00719-6","article-title":"Application of neural ordinary differential equations to the prediction of multi-agent systems","volume":"27","author":"S Herzog","year":"2021","journal-title":"Artif Life Robotics"},{"issue":"11","key":"pone.0320596.ref008","doi-asserted-by":"crossref","first-page":"959","DOI":"10.3923\/jas.2010.959.966","article-title":"An Automated White Blood Cell Nucleus Localization and Segmentation using Image Arithmetic and Automatic Threshold","volume":"10","author":"HT Madhloom","year":"2010","journal-title":"J Applied Sciences"},{"issue":"6","key":"pone.0320596.ref009","first-page":"1633","article-title":"\u201cColor image segmentation and multi-level thresholding by maximization of conditional entropy\u201d","volume":"1","author":"R. Kumar","year":"2007","journal-title":"International J. Comput. Inf. Eng"},{"issue":"1","key":"pone.0320596.ref010","doi-asserted-by":"crossref","first-page":"13249","DOI":"10.1038\/s41598-024-63831-0","article-title":"Efficient deep learning-based approach for malaria detection using red blood cell smears","volume":"14","author":"M Mujahid","year":"2024","journal-title":"Sci Rep"},{"issue":"2","key":"pone.0320596.ref011","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1002\/jemt.23172","article-title":"Automated techniques for blood vessels segmentation through fundus retinal images: A review","volume":"82","author":"S Akbar","year":"2019","journal-title":"Microsc Res Tech"},{"key":"pone.0320596.ref012","first-page":"619","volume-title":"\u201cTeager energy based blood cell segmentation,\u201d in 14th International Conference on Digital Signal Processing Proceedings, Santorini","author":"BR Kumar","year":"2002"},{"key":"pone.0320596.ref013","first-page":"103","volume-title":"\u201cMorphological classification of blood leucocytes by microscope images,\u201d in IEEE International Conference onComputational Intelligence for Measurement Systems and Applications","author":"V Piuri","year":"2004"},{"key":"pone.0320596.ref014","unstructured":"Sinha N. and Ramakrishnan A. G. Blood Cell Segmentation using EM Algorithm. in 3rd Indian Conference Vision, Graphics and Image Processing (ICVGIP-02), India. 2002, pp. 445\u201350."},{"key":"pone.0320596.ref015","first-page":"105","volume-title":"\u201cInteractive graph cuts for optimal boundary & region segmentation of objects in N-D images,\u201d in Proceedings Eighth IEEE International Conference on Computer Vision., Vancouver, BC","author":"YY Boykov","year":"2001"},{"key":"pone.0320596.ref016","first-page":"309","article-title":"\u201cGrabCut\u201d","author":"C Rother","year":"2004","journal-title":"ACM SIGGRAPH 2004 Papers"},{"key":"pone.0320596.ref017","doi-asserted-by":"crossref","DOI":"10.1007\/b97541","article-title":"Geometric Level Set Methods in Imaging, Vision, and Graphics","author":"S Osher","year":"2003"},{"issue":"6","key":"pone.0320596.ref018","doi-asserted-by":"crossref","first-page":"583","DOI":"10.1109\/34.87344","article-title":"Watersheds in digital spaces: an efficient algorithm based on immersion simulations","volume":"13","author":"L Vincent","year":"1991","journal-title":"IEEE Trans Pattern Anal Machine Intell"},{"issue":"11","key":"pone.0320596.ref019","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"Y Lecun","year":"1998","journal-title":"Proc IEEE"},{"key":"pone.0320596.ref020","doi-asserted-by":"crossref","first-page":"43369","DOI":"10.1109\/ACCESS.2019.2908685","article-title":"Dense Convolutional Networks for Semantic Segmentation","volume":"7","author":"C Han","year":"2019","journal-title":"IEEE Access"},{"issue":"9","key":"pone.0320596.ref021","doi-asserted-by":"crossref","first-page":"2464","DOI":"10.3788\/OPE.20132109.2464","article-title":"Segmentation of cell images based on improved graph MST and skeleton distance mapping","volume":"21","author":"\u738b\u536b\u661f WANG Wei-xing","year":"2013","journal-title":"\u5149\u5b66 \u7cbe\u5bc6\u5de5\u7a0b"},{"issue":"05","key":"pone.0320596.ref022","doi-asserted-by":"crossref","first-page":"1650016","DOI":"10.1142\/S1793545816500164","article-title":"Automatic counting method for complex overlapping erythrocytes based on seed prediction in microscopic imaging","volume":"09","author":"X Wei","year":"2016","journal-title":"J Innov Opt Health Sci"},{"key":"pone.0320596.ref023","doi-asserted-by":"crossref","first-page":"7235795","DOI":"10.1155\/2018\/7235795","article-title":"Simultaneous Segmentation of Leukocyte and Erythrocyte in Microscopic Images Using a Marker-Controlled Watershed Algorithm","volume":"2018","author":"H Miao","year":"2018","journal-title":"Comput Math Methods Med"},{"issue":"1","key":"pone.0320596.ref024","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1007\/s10462-020-09854-1","article-title":"Deep semantic segmentation of natural and medical images: a review","volume":"54","author":"S Asgari Taghanaki","year":"2020","journal-title":"Artif Intell Rev"},{"key":"pone.0320596.ref025","doi-asserted-by":"crossref","first-page":"102385","DOI":"10.1016\/j.bspc.2020.102385","article-title":"Segmentation of leukocyte by semantic segmentation model: A deep learning approach","volume":"65","author":"R M.Roy","year":"2021","journal-title":"Biomedical Signal Processing and Control"},{"key":"pone.0320596.ref026","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1016\/j.neucom.2019.02.003","article-title":"Survey on semantic segmentation using deep learning techniques","volume":"338","author":"F Lateef","year":"2019","journal-title":"Neurocomputing"},{"issue":"5","key":"pone.0320596.ref027","doi-asserted-by":"crossref","first-page":"1031","DOI":"10.1007\/s11760-020-01828-8","article-title":"Fully convolutional network with attention modules for semantic segmentation","volume":"15","author":"Y Huang","year":"2021","journal-title":"SIViP"},{"issue":"1","key":"pone.0320596.ref028","doi-asserted-by":"crossref","first-page":"231","DOI":"10.1007\/s10278-019-00200-8","article-title":"Cell Nuclei Segmentation in Cytological Images Using Convolutional Neural Network and Seeded Watershed Algorithm","volume":"33","author":"M Kowal","year":"2020","journal-title":"J Digit Imaging"},{"issue":"1","key":"pone.0320596.ref029","doi-asserted-by":"crossref","first-page":"21177","DOI":"10.1038\/s41598-022-25250-x","article-title":"Power mean based image segmentation in the presence of noise","volume":"12","author":"A Rahman","year":"2022","journal-title":"Sci Rep"},{"issue":"13","key":"pone.0320596.ref030","doi-asserted-by":"crossref","first-page":"17849","DOI":"10.1007\/s11042-022-12285-5","article-title":"A robust algorithm for white blood cell nuclei segmentation","volume":"81","author":"M Makem","year":"2022","journal-title":"Multimed Tools Appl"},{"issue":"15","key":"pone.0320596.ref031","first-page":"1","article-title":"\u201cExplainable CAD System for Classification of Acute Lymphoblastic Leukemia Based on a Robust White Blood Cell Segmentation\u201d","author":"JL Diaz Resendiz","year":"2023","journal-title":"Cancers (Basel)"},{"key":"pone.0320596.ref032","doi-asserted-by":"crossref","first-page":"1101357","DOI":"10.3389\/fmicb.2023.1101357","article-title":"Rapid discrimination of Shigella spp. and Escherichia coli via label-free surface enhanced Raman spectroscopy coupled with machine learning algorithms","volume":"14","author":"W Liu","year":"2023","journal-title":"Front Microbiol"},{"key":"pone.0320596.ref033","doi-asserted-by":"crossref","first-page":"981019","DOI":"10.3389\/fpubh.2022.981019","article-title":"Comparative studies of deep learning segmentation models for left ventricle segmentation","volume":"10","author":"MA Shoaib","year":"2022","journal-title":"Front Public Health"},{"key":"pone.0320596.ref034","doi-asserted-by":"crossref","first-page":"908143","DOI":"10.3389\/fnagi.2022.908143","article-title":"Soft Attention Based DenseNet Model for Parkinson\u2019s Disease Classification Using SPECT Images","volume":"14","author":"M Thakur","year":"2022","journal-title":"Front Aging Neurosci"},{"issue":"1","key":"pone.0320596.ref035","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1109\/TFUZZ.2024.3369944","article-title":"A Novel Centralized Federated Deep Fuzzy Neural Network with Multi-objectives Neural Architecture Search for Epistatic Detection","volume":"33","author":"X Wu","year":"2025","journal-title":"IEEE Trans Fuzzy Syst"},{"key":"pone.0320596.ref036","first-page":"770","article-title":"Deep Residual Learning for Image Recognition","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"H Kaiming","year":"2016"},{"issue":"1","key":"pone.0320596.ref037","article-title":"Quantum image edge extraction based on classical Sobel operator for NEQR","volume":"18","author":"P Fan","year":"2018","journal-title":"Quantum Inf Process"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0320596","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,8]],"date-time":"2025-05-08T13:46:53Z","timestamp":1746712013000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0320596"}},"subtitle":[],"editor":[{"given":"Caihong","family":"Mu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,5,8]]},"references-count":37,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2025,5,8]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0320596","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,8]]}}}