![]() First, the variety of staining methods and quality of smear preparation for microscopic blood smear images makes it difficult to devise universal features using traditional approaches. 5 Nevertheless, progress toward a clinically applicable system was slow because of several challenges. 3, 4 Therefore, researchers from engineering and computer science have performed extensive studies for an automated microscopic examination during the past decade. However, RDTs provide insufficient information about species, life-cycle stages, and quantification of parasitemia, which are pivotal for clinical management. Economical and reliable rapid diagnostic tests (RDTs) can replace thick smears as a screening tool in resource-limited settings. 4 Both situations prompted efforts to seek more efficient and accurate diagnostic tools. This expertise is rare not only in resource-limited countries, where malaria poses a significant burden, but also in countries close to malaria elimination where the microscopists lack experience. 3 However, conventional microscopic diagnosis is labor intensive and dependent on techniques and experience. 3, 4 Thick blood smears are used for screening, whereas thin blood smears are used for confirming the species and measuring parasite density. The criterion standard for malaria diagnosis is microscopic examination. Although Taiwan has been certified malaria free for more than 5 decades, imported cases, mostly from Africa and Southeast Asia and caused by Plasmodium falciparum, still occur every year. 1 Most patients were in the World Health Organization African region (92%) and South-East Asian region (5%). In 2017, an estimated 219 million cases of malaria and 435 000 malaria-related deaths occurred worldwide. Malaria, a mosquito-borne disease caused by Plasmodium species, is a severe and reemerging global health issue despite years of effort in global malaria control. For detecting P falciparum infection on blood smear images, the algorithm had expert-level performance (sensitivity, 0.995 specificity, 0.900 AUC, 0.997 ), especially in detecting ring form (sensitivity, 0.968 specificity, 0.960 AUC, 0.995 ) compared with experienced microscopists (mean sensitivity, 0.995 mean specificity, 0.955 ).Ĭonclusions and Relevance The findings suggest that a clinically validated expert-level malaria detection algorithm can be developed by using reliable data sets. For clinical validation, the average precision was 0.885 for detecting P falciparum–infected blood cells and 0.838 for ring form. Results The TIME data sets contained 8145 images of 36 blood smears from patients with suspected malaria (30 P falciparum–positive and 6 P falciparum–negative smears) that had reliable annotations. Main Outcomes and Measures Performance on detecting Plasmodium falciparum–infected blood cells was measured by average precision, and performance on detecting P falciparum infection at the image level was measured using sensitivity, specificity, and area under the receiver operating characteristic curve (AUC). A diagnostic challenge using another independent data set within TIME was performed to compare the algorithm performance against that of human experts as clinical validation. With TIME, a convolutional neural network–based object detection algorithm was developed for identification of malaria-infected red blood cells. These smear images were annotated by 4 clinical laboratory scientists who worked in medical centers in Taiwan and trained for malaria microscopic diagnosis at the national reference laboratory of the Taiwan Centers for Disease Control. Objective To assess an expert-level malaria detection algorithm using a publicly available benchmark image data set.ĭesign, Setting, and Participants In this diagnostic study, clinically validated malaria image data sets, the Taiwan Images for Malaria Eradication (TIME), were created by digitizing thin blood smears acquired from patients with malaria selected from the biobank of the Taiwan Centers for Disease Control from January 1, 2003, to December 31, 2018. Importance Decades of effort have been devoted to establishing an automated microscopic diagnosis of malaria, but there are challenges in achieving expert-level performance in real-world clinical settings because publicly available annotated data for benchmark and validation are required. Shared Decision Making and Communication.Scientific Discovery and the Future of Medicine.Health Care Economics, Insurance, Payment.Clinical Implications of Basic Neuroscience.Challenges in Clinical Electrocardiography.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |