{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T06:34:29Z","timestamp":1791441269311,"version":"4.3.3"},"update-to":[{"DOI":"10.1371\/journal.pntd.0013234","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2025,7,11]],"date-time":"2025-07-11T00:00:00Z","timestamp":1752192000000}}],"reference-count":31,"publisher":"Public Library of Science (PLoS)","issue":"7","license":[{"start":{"date-parts":[[2025,7,3]],"date-time":"2025-07-03T00:00:00Z","timestamp":1751500800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Ghent University - Sandwich BOF Ph.D. Scholarship for Developing Countries","award":["BOF.DCV.2022.0011"],"award-info":[{"award-number":["BOF.DCV.2022.0011"]}]}],"content-domain":{"domain":["www.plosntds.org"],"crossmark-restriction":false},"short-container-title":["PLoS Negl Trop Dis"],"abstract":"\n Background:<\/jats:bold>\n Soil-transmitted helminth (STH) and\n Schistosoma mansoni<\/jats:italic>\n (\n S. mansoni<\/jats:italic>\n ) infections remain significant public health concerns in tropical and subtropical regions. Deep Convolutional Neural Networks (DCNNs) have already shown promising accuracy in identifying STH and\n S. mansoni eggs<\/jats:italic>\n in the same, in-distribution (ID) settings. However, their performance in real-world, out-of-distribution (OOD) scenarios, characterized by variations in image capture devices and the appearance of previously unseen egg types, has not been thoroughly investigated. Assessing the robustness of DCNNs under these challenging conditions is crucial for ensuring their reliability in field diagnostics.\n <\/jats:p>\n \n Methodology:<\/jats:bold>\n Our study addresses the gap in evaluating DCNNs for identifying STH and\n S. mansoni<\/jats:italic>\n eggs by rigorously testing multiple variants of the You Only Look Once (YOLO) version 7 model under two OOD conditions: (\n i<\/jats:italic>\n ) a dataset shift due to a change in the image capture device, and (\n ii<\/jats:italic>\n ) a combination of this device change and the presence of two egg types not occurring during training. We adopted a 2\n \n \n \n \n \n \u00d7<\/mml:mi>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:alternatives>\n <\/jats:inline-formula>\n 3 montage data augmentation strategy to enhance OOD generalization. Additionally, we used the Toolkit for Identifying object Detection Errors (TIDE) and Gradient-weighted Class Activation Mapping (Grad-CAM) to perform a comprehensive analysis of the results.\n <\/jats:p>\n \n Principal findings:<\/jats:bold>\n In ID settings, YOLOv7-E6E outperformed other models, achieving an F1-score of 97.47%. For the OOD scenario involving only a change in the image capture device, the 2\n \n \n \n \n \n \u00d7<\/mml:mi>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:alternatives>\n <\/jats:inline-formula>\n 3 montage strategy significantly enhanced performance, increasing precision by 8%, recall by 14.85%, and\n mAP<\/jats:italic>\n @\n IoU<\/jats:italic>\n 0.5<\/jats:sub>\n by 21.36%. However, for the more complex OOD scenario that involves both a change in the capture device and the introduction of two previously unseen egg types, the proposed augmentation technique, while beneficial, did not fully address the generalization challenges across all YOLOv7 variants, highlighting the necessity of testing beyond ID scenarios, on which state-of-the-art models predominantly focus.\n <\/jats:p>\n \n Conclusions\/significance:<\/jats:bold>\n This study underscores the critical importance of utilizing comprehensive test sets and conducting rigorous OOD evaluations when designing machine learning solutions for STH,\n S. mansoni<\/jats:italic>\n or any other helminth infections. Understanding the true capabilities of DCNNs in real-world settings depends on such thorough testing. Expanding AI-driven diagnostic assessments to account for the complexities encountered in the field is essential for creating robust tools that can significantly contribute to the global elimination of STH and\n S. mansoni<\/jats:italic>\n infections as public health problems by 2030, a goal put forth by the World Health Organization.\n <\/jats:p>","DOI":"10.1371\/journal.pntd.0013234","type":"journal-article","created":{"date-parts":[[2025,7,3]],"date-time":"2025-07-03T13:48:55Z","timestamp":1751550535000},"page":"e0013234","update-policy":"https:\/\/doi.org\/10.1371\/journal.pntd.corrections_policy","source":"Crossref","is-referenced-by-count":7,"title":["Detecting soil-transmitted helminth and Schistosoma mansoni eggs in Kato-Katz stool smear microscopy images: A comprehensive in- and out-of-distribution evaluation of YOLOv7 variants"],"prefix":"10.1371","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1912-5666","authenticated-orcid":true,"given":"Mohammed Aliy","family":"Mohammed","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Esla Timothy","family":"Anzaku","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter Kenneth","family":"Ward","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bruno","family":"Levecke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Janarthanan","family":"Krishnamoorthy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wesley","family":"De Neve","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sofie","family":"Van Hoecke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,7,3]]},"reference":[{"key":"pntd.0013234.ref001","unstructured":"World Health Organization. Ending the neglect to attain the Sustainable Development Goals: A road map for neglected tropical diseases 2021\u20132030. 2021. https:\/\/www.who.int\/publications\/i\/item\/9789240010352"},{"issue":"10440","key":"pntd.0013234.ref002","doi-asserted-by":"crossref","first-page":"2133","DOI":"10.1016\/S0140-6736(24)00757-8","article-title":"Global incidence, prevalence, years lived with disability (YLDs), disability-adjusted life-years (DALYs), and healthy life expectancy (HALE) for 371 diseases and injuries in 204 countries and territories and 811 subnational locations, 1990\u20132021: a systematic analysis for the Global Burden of Disease Study 2021","volume":"403","author":"GBD 2021 Diseases and Injuries Collaborators","year":"2024","journal-title":"Lancet"},{"issue":"3","key":"pntd.0013234.ref003","doi-asserted-by":"crossref","first-page":"290","DOI":"10.1016\/j.cmi.2018.04.028","article-title":"Rapid diagnosis of parasitic diseases: current scenario and future needs","volume":"25","author":"S Mom\u010dilovi\u0107","year":"2019","journal-title":"Clin Microbiol Infect"},{"issue":"4","key":"pntd.0013234.ref004","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0175646","article-title":"Mathematical algorithm for the automatic recognition of intestinal parasites","volume":"12","author":"A Alva","year":"2017","journal-title":"PLoS One"},{"key":"pntd.0013234.ref005","doi-asserted-by":"crossref","first-page":"990304","DOI":"10.3389\/fitd.2022.990304","article-title":"The development of an artificial intelligence-based digital pathology for neglected tropical diseases: a platform specific analysis of the World Health Organization diagnostic target product profile for soil-transmitted helminthiasis","volume":"3","author":"P Ward","year":"2022","journal-title":"Frontiers in Tropical Diseases"},{"key":"pntd.0013234.ref006","volume-title":"Bench aids for intestinal parasites","author":"M Genchi","year":"2019"},{"issue":"5","key":"pntd.0013234.ref007","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pntd.0011071","article-title":"A general framework to support cost-efficient fecal egg count methods and study design choices for large-scale STH deworming programs-monitoring of therapeutic drug efficacy as a case study","volume":"17","author":"LE Coffeng","year":"2023","journal-title":"PLoS Negl Trop Dis"},{"issue":"8","key":"pntd.0013234.ref008","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pntd.0007446","article-title":"Diagnostic performance of a single and duplicate Kato-Katz, Mini-FLOTAC, FECPAKG2 and qPCR for the detection and quantification of soil-transmitted helminths in three endemic countries","volume":"13","author":"P Cools","year":"2019","journal-title":"PLoS Negl Trop Dis"},{"issue":"1","key":"pntd.0013234.ref009","doi-asserted-by":"crossref","DOI":"10.1128\/JCM.01469-17","article-title":"\u201cSmart Diagnosis\u201d of parasitic diseases by use of smartphones","volume":"56","author":"MA Saeed","year":"2017","journal-title":"J Clin Microbiol"},{"issue":"6","key":"pntd.0013234.ref010","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pntd.0010500","article-title":"Affordable artificial intelligence-based digital pathology for neglected tropical diseases: a proof-of-concept for the detection of soil-transmitted helminths and Schistosoma mansoni eggs in Kato-Katz stool thick smears","volume":"16","author":"P Ward","year":"2022","journal-title":"PLoS Negl Trop Dis"},{"issue":"10","key":"pntd.0013234.ref011","article-title":"A comprehensive evaluation of an artificial intelligence based digital pathology to monitor large-scale deworming programs against soil-transmitted helminths: a study protocol","volume":"19","author":"PK Ward","year":"2024","journal-title":"PLoS One"},{"issue":"3","key":"pntd.0013234.ref012","doi-asserted-by":"crossref","first-page":"2013","DOI":"10.1007\/s11831-022-09858-w","article-title":"Advances towards automatic detection and classification of parasites microscopic images using deep convolutional neural network: methods, models and research directions","volume":"30","author":"S Kumar","year":"2023","journal-title":"Arch Comput Methods Eng"},{"key":"pntd.0013234.ref013","doi-asserted-by":"crossref","first-page":"6648038","DOI":"10.1155\/2021\/6648038","article-title":"Deep learning approach for ascaris lumbricoides parasite egg classification","volume":"2021","author":"N Butploy","year":"2021","journal-title":"J Parasitol Res"},{"key":"pntd.0013234.ref014","doi-asserted-by":"crossref","first-page":"100069","DOI":"10.1016\/j.prime.2022.100069","article-title":"A supervised U-Net based color image semantic segmentation for detection & classification of human intestinal parasites","volume":"2","author":"IO Libouga","year":"2022","journal-title":"e-Prime - Adv Electric Eng Electron Energy"},{"issue":"5","key":"pntd.0013234.ref015","doi-asserted-by":"crossref","first-page":"643","DOI":"10.3390\/mi13050643","article-title":"Schistoscope: an automated microscope with artificial intelligence for detection of schistosoma haematobium eggs in resource-limited settings","volume":"13","author":"P Oyibo","year":"2022","journal-title":"Micromachines (Basel)"},{"key":"pntd.0013234.ref016","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1109\/ECTI-CON49241.2020.9158084","article-title":"Automatic detection and characterization of parasite eggs using deep learning methods","volume-title":"2020 17th International Conference on Electrical Engineering\/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON)","author":"A Kitvimonrat","year":"2020"},{"issue":"9","key":"pntd.0013234.ref017","doi-asserted-by":"crossref","first-page":"4212","DOI":"10.1002\/mp.14352","article-title":"FecalNet: automated detection of visible components in human feces using deep learning","volume":"47","author":"Q Li","year":"2020","journal-title":"Med Phys"},{"issue":"8","key":"pntd.0013234.ref018","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pntd.0007577","article-title":"Kankanet: an artificial neural network-based object detection smartphone application and mobile microscope as a point-of-care diagnostic aid for soil-transmitted helminthiases","volume":"13","author":"A Yang","year":"2019","journal-title":"PLoS Negl Trop Dis"},{"issue":"11","key":"pntd.0013234.ref019","doi-asserted-by":"crossref","first-page":"9025","DOI":"10.1007\/s00521-022-06924-z","article-title":"Automated diagnosis of schistosomiasis by using faster R-CNN for egg detection in microscopy images prepared by the Kato\u2013Katz technique","volume":"34","author":"BAS Oliveira","year":"2022","journal-title":"Neural Comput Appl"},{"key":"pntd.0013234.ref020","doi-asserted-by":"crossref","first-page":"4283","DOI":"10.1109\/ICIP46576.2022.9897858","volume-title":"2022 IEEE International Conference on Image Processing (ICIP)","author":"J Ruiz-Santaquiteria","year":"2022"},{"issue":"9","key":"pntd.0013234.ref021","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pntd.0009677","article-title":"Mobile microscopy and telemedicine platform assisted by deep learning for the quantification of Trichuris trichiura infection","volume":"15","author":"E Dacal","year":"2021","journal-title":"PLoS Negl Trop Dis"},{"key":"pntd.0013234.ref022","doi-asserted-by":"crossref","first-page":"4306","DOI":"10.1109\/ICIP46576.2022.9897267","volume-title":"2022 IEEE International Conference on Image Processing (ICIP)","author":"N Anantrasirichai","year":"2022"},{"key":"pntd.0013234.ref023","doi-asserted-by":"crossref","first-page":"57815","DOI":"10.1109\/ACCESS.2024.3386826","article-title":"A comprehensive systematic review of YOLO for medical object detection (2018 to 2023)","volume":"12","author":"MG Ragab","year":"2024","journal-title":"IEEE Access"},{"key":"pntd.0013234.ref024","doi-asserted-by":"crossref","unstructured":"Wang CY, Bochkovskiy A, Liao HYM. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. 2023. https:\/\/github.com\/WongKinYiu\/yolov7","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"pntd.0013234.ref025","unstructured":"Elgendy M. Deep Learning for Vision Systems; 2020. https:\/\/www.oreilly.com\/library\/view\/deep-learning-for\/9781617296192\/"},{"key":"pntd.0013234.ref026","unstructured":"UGent-imec. JupyterHub at imec. https:\/\/doc.ilabt.imec.be\/ilabt\/jupyter\/index.html"},{"key":"pntd.0013234.ref027","first-page":"558","article-title":"TIDE: a general toolbox for identifying object detection errors","volume-title":"Lecture notes in computer science","author":"D Bolya","year":"2020"},{"issue":"2","key":"pntd.0013234.ref028","doi-asserted-by":"crossref","first-page":"336","DOI":"10.1007\/s11263-019-01228-7","article-title":"Grad-CAM: visual explanations from deep networks via gradient-based localization","volume":"128","author":"RR Selvaraju","year":"2019","journal-title":"Int J Comput Vis"},{"key":"pntd.0013234.ref029","unstructured":"Tommy ngX. YOLOv7-GradCAM: Implementing GradCAM visualization; 2022. https:\/\/github.com\/tommyngx\/yolov7-GradCAM"},{"key":"pntd.0013234.ref030","article-title":"Generalized out-of-distribution detection: a survey","author":"J Yang","year":"2021","journal-title":"Comput Vis Pattern Recognit"},{"key":"pntd.0013234.ref031","doi-asserted-by":"crossref","DOI":"10.2166\/9781780407159","article-title":"Helminths: handbook for identification and counting of parasitic helminth eggs in urban wastewater","volume":"13","author":"C Lard\u00edn","year":"2014","journal-title":"wio"}],"updated-by":[{"DOI":"10.1371\/journal.pntd.0013234","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2025,7,11]],"date-time":"2025-07-11T00:00:00Z","timestamp":1752192000000}}],"container-title":["PLOS Neglected Tropical Diseases"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pntd.0013234","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,11]],"date-time":"2025-07-11T18:00:45Z","timestamp":1752256845000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pntd.0013234"}},"subtitle":[],"editor":[{"given":"Luis","family":"Marcos","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,7,3]]},"references-count":31,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2025,7,3]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pntd.0013234","relation":{},"ISSN":["1935-2735"],"issn-type":[{"value":"1935-2735","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,3]]}}}