Elif Habibe Aktekin, Mert Burkay Çöteli, Ayşe Erbay, Nalan Yazici
{"title":"A prospective study for the examination of peripheral blood smear samples in pediatric population using artificial intelligence.","authors":"Elif Habibe Aktekin, Mert Burkay Çöteli, Ayşe Erbay, Nalan Yazici","doi":"10.55730/1300-0144.5982","DOIUrl":null,"url":null,"abstract":"<p><strong>Background/aim: </strong>Peripheral blood smear (PBS) and bone marrow aspiration are gold standards of manual microscopy diagnostics for blood cell disorders. Nowadays, data-driven artificial intelligence (AI) techniques open new perspectives in digital hematology. This study proposes an AI learning technique for the classification of blood cells over PBS samples while increasing the sensitivity and specificity rates of the experts as a decision support system of a prediagnostic tool.</p><p><strong>Materials and methods: </strong>The methodology of this study comprises three steps for the creation of an effective learning technique for blood cell disorders. First is the digitization of PBS samples in 100x optical-digital magnification using Mantiscope which is a cloud-based slide scanner system. The second is collection of pediatric hematology experts' annotations and the last one is data augmentation to increase the data variation and size. The data consists of 372 individuals, an approximate number of 12,000 annotated images with 500,000 blood cell objects. A subjective test is also performed to observe the interobserver variability.</p><p><strong>Results: </strong>We measured sensitivity and specificity for 28 cell types for the resulting decision support system. We obtained sensitivity 98% for myeloblast, 94% for basophil and 90% for lymphoblast, specificity 99% for basophil, eosinophil, monocyte, hypersegmented neutrophil, band neutrophil and reactive neutrophil in leukocyte subtypes. When erythrocyte measurements were evaluated, it was found that the sensitivity was 93% for normoblast, 81% for target cell and pencil cell, 80% for sickle cell, specificity was 99% for normoblast, pencil cell, echinocyte, and sickle cell.</p><p><strong>Conclusion: </strong>It is observed that sensitivity and specificity greater than 90% can be obtained for some specific cell types with this clinical study. It is seen that data augmentation increases the effectiveness of the learning method in terms of leukocytes by improving the measurement metrics. This could be a valuable technique to evaluate acute leukemias and hemolytic disorders.</p>","PeriodicalId":23361,"journal":{"name":"Turkish Journal of Medical Sciences","volume":"55 2","pages":"386-397"},"PeriodicalIF":1.2000,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12058009/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Turkish Journal of Medical Sciences","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.55730/1300-0144.5982","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/1/1 0:00:00","PubModel":"eCollection","JCR":"Q2","JCRName":"MEDICINE, GENERAL & INTERNAL","Score":null,"Total":0}
引用次数: 0
Abstract
Background/aim: Peripheral blood smear (PBS) and bone marrow aspiration are gold standards of manual microscopy diagnostics for blood cell disorders. Nowadays, data-driven artificial intelligence (AI) techniques open new perspectives in digital hematology. This study proposes an AI learning technique for the classification of blood cells over PBS samples while increasing the sensitivity and specificity rates of the experts as a decision support system of a prediagnostic tool.
Materials and methods: The methodology of this study comprises three steps for the creation of an effective learning technique for blood cell disorders. First is the digitization of PBS samples in 100x optical-digital magnification using Mantiscope which is a cloud-based slide scanner system. The second is collection of pediatric hematology experts' annotations and the last one is data augmentation to increase the data variation and size. The data consists of 372 individuals, an approximate number of 12,000 annotated images with 500,000 blood cell objects. A subjective test is also performed to observe the interobserver variability.
Results: We measured sensitivity and specificity for 28 cell types for the resulting decision support system. We obtained sensitivity 98% for myeloblast, 94% for basophil and 90% for lymphoblast, specificity 99% for basophil, eosinophil, monocyte, hypersegmented neutrophil, band neutrophil and reactive neutrophil in leukocyte subtypes. When erythrocyte measurements were evaluated, it was found that the sensitivity was 93% for normoblast, 81% for target cell and pencil cell, 80% for sickle cell, specificity was 99% for normoblast, pencil cell, echinocyte, and sickle cell.
Conclusion: It is observed that sensitivity and specificity greater than 90% can be obtained for some specific cell types with this clinical study. It is seen that data augmentation increases the effectiveness of the learning method in terms of leukocytes by improving the measurement metrics. This could be a valuable technique to evaluate acute leukemias and hemolytic disorders.
期刊介绍:
Turkish Journal of Medical sciences is a peer-reviewed comprehensive resource that provides critical up-to-date information on the broad spectrum of general medical sciences. The Journal intended to publish original medical scientific papers regarding the priority based on the prominence, significance, and timeliness of the findings. However since the audience of the Journal is not limited to any subspeciality in a wide variety of medical disciplines, the papers focusing on the technical details of a given medical subspeciality may not be evaluated for publication.