{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T17:41:03Z","timestamp":1779212463975,"version":"3.51.4"},"reference-count":36,"publisher":"Public Library of Science (PLoS)","issue":"3","license":[{"start":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T00:00:00Z","timestamp":1773705600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Cutaneous leishmaniasis (CL) is a neglected tropical and zoonotic disease affecting both human and animal health, for which microscopic examination of Giemsa-stained slides remains the diagnostic reference standard despite being time-consuming and operator-dependent. In this study, we developed a lightweight, calibration-aware deep learning framework for automated amastigote detection and slide-level diagnostic probability estimation from microscopy images. A U-Net architecture with a MobileNetV2 encoder was employed for pixel-level parasite segmentation using a weakly supervised pseudo-labeling strategy on a single-center dataset comprising 292 field-of-view images. Slide-level diagnostic probabilities were derived via probability pooling and subsequently refined using post-hoc calibration techniques, including isotonic regression, Platt scaling, and temperature scaling. Model performance was evaluated on an independent test set using segmentation metrics (Dice coefficient and Intersection-over-Union) and diagnostic reliability metrics (AUROC, Brier score, and Expected Calibration Error). The proposed framework achieved a Dice coefficient of 0.901 and an IoU of 0.820 for segmentation against pseudo-label references, with strong discriminative performance at the slide level (AUROC\u2009=\u20090.978). Isotonic regression markedly improved probability reliability, reducing the Brier score from 0.089 to 0.030 and the Expected Calibration Error from 0.120 to 0.023 without significantly affecting discrimination. Statistical analyses confirmed the robustness of the calibration improvements. Overall, the results demonstrate that isotonic calibration enhances the interpretability and reliability of deep-learning-based CL diagnostics. The proposed lightweight framework provides a robust foundation for microscopy-based screening and supports future validation across broader datasets and One Health\u2013oriented diagnostic applications.<\/jats:p>","DOI":"10.1371\/journal.pone.0344561","type":"journal-article","created":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T17:37:22Z","timestamp":1773769042000},"page":"e0344561","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":1,"title":["A lightweight deep learning framework for reliable microscopy-based diagnosis of cutaneous leishmaniasis"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-4550-5445","authenticated-orcid":true,"given":"Nisreen Osman","family":"E. Ahmed","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Samuel","family":"Mwalili","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Murtada K.","family":"Elbashir","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2026,3,17]]},"reference":[{"key":"pone.0344561.ref001","doi-asserted-by":"crossref","first-page":"100239","DOI":"10.1016\/j.microb.2025.100239","article-title":"Leishmaniasis: A multifaceted approach to diagnosis, maladies, drug repurposing and way forward","volume":"6","author":"N Makarani","year":"2025","journal-title":"The Microbe"},{"key":"pone.0344561.ref002","author":"World Health Organization","year":"2023"},{"issue":"4","key":"pone.0344561.ref003","doi-asserted-by":"crossref","first-page":"363","DOI":"10.1093\/labmed\/lmac134","article-title":"Review of the Clinical Presentation, Pathology, Diagnosis, and Treatment of Leishmaniasis","volume":"54","author":"BA Mathison","year":"2023","journal-title":"Lab Med"},{"issue":"6","key":"pone.0344561.ref004","doi-asserted-by":"crossref","first-page":"823","DOI":"10.1007\/s40257-022-00726-8","article-title":"Cutaneous Leishmaniasis: A 2022 Updated Narrative Review into Diagnosis and Management Developments","volume":"23","author":"HJC de Vries","year":"2022","journal-title":"Am J Clin Dermatol"},{"key":"pone.0344561.ref005","author":"JSM Limon","year":"2017"},{"issue":"10174","key":"pone.0344561.ref006","doi-asserted-by":"crossref","first-page":"872","DOI":"10.1016\/S0140-6736(18)33057-5","article-title":"Leishmaniasis\u2014authors\u2019 reply","volume":"393","author":"S Burza","year":"2019","journal-title":"Lancet"},{"key":"pone.0344561.ref007","article-title":"Cutaneous and Mucocutaneous Leishmaniasis","author":"I Abad\u00edas-Granado","year":"2021","journal-title":"Actas Dermosifiliogr (Engl Ed)"},{"issue":"1","key":"pone.0344561.ref008","doi-asserted-by":"crossref","first-page":"551","DOI":"10.1186\/s12879-024-09428-4","article-title":"A deep learning-based model for detecting Leishmania amastigotes in microscopic slides: a new approach to telemedicine","volume":"24","author":"A Sadeghi","year":"2024","journal-title":"BMC Infect Dis"},{"issue":"7553","key":"pone.0344561.ref009","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"Y LeCun","year":"2015","journal-title":"Nature"},{"key":"pone.0344561.ref010","first-page":"53","article-title":"Leishmaniasis Parasite Segmentation and Classification Using Deep Learning","volume-title":"Lecture Notes in Computer Science","author":"M G\u00f3rriz","year":"2018"},{"issue":"1","key":"pone.0344561.ref011","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1186\/s12879-022-07029-7","article-title":"A machine learning-based system for detecting leishmaniasis in microscopic images","volume":"22","author":"M Zare","year":"2022","journal-title":"BMC Infect Dis"},{"key":"pone.0344561.ref012","doi-asserted-by":"crossref","first-page":"23","DOI":"10.21037\/jmai-23-67","article-title":"Skin cancer detection using multi-scale deep learning and transfer learning","volume":"6","author":"M Hajiarbabi","year":"2023","journal-title":"J Med Artif Intell"},{"issue":"1","key":"pone.0344561.ref013","doi-asserted-by":"crossref","first-page":"75","DOI":"10.30699\/fhi.v10i1.278","article-title":"Presumptive Diagnosis of Cutaneous Leishmaniasis","volume":"10","author":"CA Arce-Lopera","year":"2021","journal-title":"Front Health Infor"},{"issue":"1","key":"pone.0344561.ref014","doi-asserted-by":"crossref","first-page":"12","DOI":"10.3390\/biomedicines12010012","article-title":"Automated Identification of Cutaneous Leishmaniasis Lesions Using Deep-Learning-Based Artificial Intelligence","volume":"12","author":"C Leal JF de","year":"2023","journal-title":"Biomedicines"},{"issue":"1","key":"pone.0344561.ref015","doi-asserted-by":"crossref","first-page":"12","DOI":"10.3390\/diagnostics14010012","article-title":"Assessment of Deep Learning Models for Cutaneous Leishmania Parasite Diagnosis Using Microscopic Images","volume":"14","author":"AM Abdelmula","year":"2023","journal-title":"Diagnostics (Basel)"},{"issue":"1","key":"pone.0344561.ref016","doi-asserted-by":"crossref","first-page":"1177","DOI":"10.1021\/acsomega.4c08735","article-title":"Human-Validated Neural Networks for Precise Amastigote Categorization and Quantification to Accelerate Drug Discovery in Leishmaniasis","volume":"10","author":"AG Sorrilha-Rodrigues","year":"2024","journal-title":"ACS Omega"},{"issue":"14","key":"pone.0344561.ref017","doi-asserted-by":"crossref","first-page":"8076","DOI":"10.3390\/app13148076","article-title":"Detection of Human Visceral Leishmaniasis Parasites in Microscopy Images from Bone Marrow Parasitological Examination","volume":"13","author":"C Gon\u00e7alves","year":"2023","journal-title":"Applied Sciences"},{"issue":"24","key":"pone.0344561.ref018","doi-asserted-by":"crossref","first-page":"8180","DOI":"10.3390\/s24248180","article-title":"Enhanced Detection of Leishmania Parasites in Microscopic Images Using Machine Learning Models","volume":"24","author":"M Contreras-Ram\u00edrez","year":"2024","journal-title":"Sensors (Basel)"},{"key":"pone.0344561.ref019","doi-asserted-by":"crossref","first-page":"101078","DOI":"10.1016\/j.imu.2022.101078","article-title":"Optimized real-time diagnosis of neglected tropical diseases by automatic recognition of skin lesions","volume":"33","author":"N Steyve","year":"2022","journal-title":"Informatics in Medicine Unlocked"},{"key":"pone.0344561.ref020","first-page":"270","article-title":"Deep learning model for cutaneous leishmaniasis detection and classification using YOLOv5","author":"AM Noureldeen","year":"2023","journal-title":"African Journal of Advanced Pure and Applied Sciences (AJAPAS)"},{"key":"pone.0344561.ref021","doi-asserted-by":"crossref","first-page":"110313","DOI":"10.1016\/j.compbiomed.2025.110313","article-title":"A new diagnostic method and tool for cutaneous leishmaniasis based on artificial intelligence techniques","volume":"192","author":"S Gadri","year":"2025","journal-title":"Comput Biol Med"},{"key":"pone.0344561.ref022","article-title":"A Comparative Study of Confidence Calibration in Deep Learning: from Computer Vision to Medical Imaging","author":"R Gao","year":"2022"},{"key":"pone.0344561.ref023","doi-asserted-by":"crossref","first-page":"107096","DOI":"10.1016\/j.compbiomed.2023.107096","article-title":"Calibrating ensembles for scalable uncertainty quantification in deep learning-based medical image segmentation","volume":"163","author":"T Buddenkotte","year":"2023","journal-title":"Comput Biol Med"},{"issue":"3","key":"pone.0344561.ref024","doi-asserted-by":"crossref","first-page":"180","DOI":"10.1007\/s42452-025-06587-0","article-title":"Post hoc calibration of medical segmentation models","volume":"7","author":"AJ Rousseau","year":"2023","journal-title":"Discov Appl Sci"},{"issue":"337","key":"pone.0344561.ref025","doi-asserted-by":"crossref","first-page":"140","DOI":"10.1080\/01621459.1972.10481216","article-title":"The Isotonic Regression Problem and its Dual","volume":"67","author":"RE Barlow","year":"1972","journal-title":"Journal of the American Statistical Association"},{"issue":"5","key":"pone.0344561.ref026","first-page":"00405175241296807","article-title":"Confidence calibration and uncertainty estimation in convolutional neural network for fabric defect segmentation: A benchmark study","volume":"95","author":"Z Chen","journal-title":"Textile Research Journal"},{"key":"pone.0344561.ref027","first-page":"234","article-title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","volume-title":"Lecture Notes in Computer Science","author":"O Ronneberger","year":"2015"},{"key":"pone.0344561.ref028","doi-asserted-by":"crossref","unstructured":"Sandler M, Howard A, Zhu M, Zhmoginov A, Chen L-C. MobileNetV2: Inverted Residuals and Linear Bottlenecks. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2018. 4510\u201320. http:\/\/dx.doi.org\/10.1109\/cvpr.2018.00474","DOI":"10.1109\/CVPR.2018.00474"},{"issue":"9","key":"pone.0344561.ref029","doi-asserted-by":"crossref","first-page":"963","DOI":"10.3390\/diagnostics14090963","article-title":"Artificial Intelligence in Cutaneous Leishmaniasis Diagnosis: Current Developments and Future Perspectives","volume":"14","author":"H Talimi","year":"2024","journal-title":"Diagnostics"},{"issue":"1","key":"pone.0344561.ref030","doi-asserted-by":"crossref","first-page":"402","DOI":"10.26599\/TST.2024.9010001","article-title":"Convolutional Neural Network Image Classification Based on Different Color Spaces","volume":"30","author":"Z Xian","year":"2025","journal-title":"Tsinghua Sci Technol"},{"key":"pone.0344561.ref031","first-page":"116250","article-title":"UIEC^2-Net: CNN-based underwater image enhancement using two color space","volume":"96","author":"Y Wang","year":"2021","journal-title":"Signal Processing: Image Communication"},{"key":"pone.0344561.ref032","article-title":"Deep learning using rectified linear units (ReLU). arXiv preprint","author":"AF Agarap","year":"2018"},{"key":"pone.0344561.ref033","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1016\/S0020-0255(96)00200-9","article-title":"The generalized sigmoid activation function: Competitive supervised learning","volume":"99","author":"S Narayan","year":"1997","journal-title":"Information Sciences"},{"key":"pone.0344561.ref034","unstructured":"Ruby U, Yendapalli V. Binary cross-entropy with deep learning technique for image classification. 2020."},{"issue":"4","key":"pone.0344561.ref035","doi-asserted-by":"crossref","first-page":"427","DOI":"10.1016\/j.ipm.2009.03.002","article-title":"A systematic analysis of performance measures for classification tasks","volume":"45","author":"M Sokolova","year":"2009","journal-title":"Information Processing & Management"},{"key":"pone.0344561.ref036","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1533\/9781908818652.35","article-title":"Blood biomarkers: overview of existing serum test strategies for disease severity, risk for progression, therapeutic benchmark targets","volume-title":"Translational Biology in Medicine","author":"M Montano","year":"2014"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0344561","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T17:37:30Z","timestamp":1773769050000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0344561"}},"subtitle":[],"editor":[{"given":"Elham","family":"Kazemirad","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2026,3,17]]},"references-count":36,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0344561","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,17]]}}}