TFinder App: Artificial intelligence to diagnose tick fever agents and assess parasitemia/bacteremia in bovine blood smears

IF 2 2区农林科学 Q2 PARASITOLOGY

Veterinary parasitology Pub Date : 2025-02-01 DOI:10.1016/j.vetpar.2025.110415

Artur Siqueira Nunes Trindade , Igor Maciel Lopes de Moraes , Luccas Lourenzzo Lima Lins Leal , Vanessa Ferreira Salvador , Luciana Maffini Heller , Dina Maria Beltran Zapa , Lidia Mendes de Aquino , Lorena Lopes Ferreira , Welber Daniel Zanetti Lopes

{"title":"TFinder App: Artificial intelligence to diagnose tick fever agents and assess parasitemia/bacteremia in bovine blood smears","authors":"Artur Siqueira Nunes Trindade , Igor Maciel Lopes de Moraes , Luccas Lourenzzo Lima Lins Leal , Vanessa Ferreira Salvador , Luciana Maffini Heller , Dina Maria Beltran Zapa , Lidia Mendes de Aquino , Lorena Lopes Ferreira , Welber Daniel Zanetti Lopes","doi":"10.1016/j.vetpar.2025.110415","DOIUrl":null,"url":null,"abstract":"<div><div>Due to the importance of diagnosing tick fever (TF) agents and their parasitemia in the field to provide appropriate treatment, the objective of this study was to develop an application capable of detecting the presence or absence of these hemopathogens and calculating parasitemia/bacteremia. Therefore, to create the TFinder app, blood smears from the tip of the tail of cattle naturally infected with TF were prepared to train the artificial neural network (ANN) for Anaplasma marginale and Babesia spp. The ANN was trained with images from different microscope fields and angles. For the validation stage of the ANN, new blood smear images from different animals were inserted. The diagnosis of presence or absence and calculation of parasitemia/bacteremia performed by a human being were compared with that of the ANN. The ANN was trained with 8100 and 2871 images of blood smears containing parasitized erythrocytes with A. marginale and Babesia spp. respectively. In the validation stage, it was used a total of new 1000 for A. marginale and 750 for Babesia spp. There was a strong positive correlation between the A. marginale bacteremia (r = 0.9484; R² = 0.8996; p < 0.0001) values obtained by the human and TFinder app, the same occurred for Babesia spp. parasitemia (r = 0.9650; R² = 0.9314; p < 0.0001). The sensitivity, specificity, and accuracy of TFinder app for the presence or absence of A. marginale were 97.7 %, 86.5 %, and 95.4 %, respectively. While for A. marginale bacteremia it was 89.6 %, 98.7 %, and 98.1 %, respectively. For Babesia spp., the sensitivity, specificity, and accuracy of presence and absence were 98.0 %, 91.1 %, and 96.9 %, respectively. The calculation of Babesia spp. parasitemia was 84.3 %, 99.7 % and 98.9 %, respectively. TFinder app can be used to diagnose and calculate the parasitemia/bacteremia of TF agents in bovine blood smear images.</div></div>","PeriodicalId":23716,"journal":{"name":"Veterinary parasitology","volume":"334 ","pages":"Article 110415"},"PeriodicalIF":2.0000,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Veterinary parasitology","FirstCategoryId":"97","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0304401725000263","RegionNum":2,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"PARASITOLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

Due to the importance of diagnosing tick fever (TF) agents and their parasitemia in the field to provide appropriate treatment, the objective of this study was to develop an application capable of detecting the presence or absence of these hemopathogens and calculating parasitemia/bacteremia. Therefore, to create the TFinder app, blood smears from the tip of the tail of cattle naturally infected with TF were prepared to train the artificial neural network (ANN) for Anaplasma marginale and Babesia spp. The ANN was trained with images from different microscope fields and angles. For the validation stage of the ANN, new blood smear images from different animals were inserted. The diagnosis of presence or absence and calculation of parasitemia/bacteremia performed by a human being were compared with that of the ANN. The ANN was trained with 8100 and 2871 images of blood smears containing parasitized erythrocytes with A. marginale and Babesia spp. respectively. In the validation stage, it was used a total of new 1000 for A. marginale and 750 for Babesia spp. There was a strong positive correlation between the A. marginale bacteremia (r = 0.9484; R² = 0.8996; p < 0.0001) values obtained by the human and TFinder app, the same occurred for Babesia spp. parasitemia (r = 0.9650; R² = 0.9314; p < 0.0001). The sensitivity, specificity, and accuracy of TFinder app for the presence or absence of A. marginale were 97.7 %, 86.5 %, and 95.4 %, respectively. While for A. marginale bacteremia it was 89.6 %, 98.7 %, and 98.1 %, respectively. For Babesia spp., the sensitivity, specificity, and accuracy of presence and absence were 98.0 %, 91.1 %, and 96.9 %, respectively. The calculation of Babesia spp. parasitemia was 84.3 %, 99.7 % and 98.9 %, respectively. TFinder app can be used to diagnose and calculate the parasitemia/bacteremia of TF agents in bovine blood smear images.

查看原文本刊更多论文

求助全文

约1分钟内获得全文求助全文

来源期刊

Veterinary parasitology 农林科学-寄生虫学

CiteScore

5.30

自引率

7.70%

发文量

126

审稿时长

36 days

期刊介绍： The journal Veterinary Parasitology has an open access mirror journal,Veterinary Parasitology: X, sharing the same aims and scope, editorial team, submission system and rigorous peer review. This journal is concerned with those aspects of helminthology, protozoology and entomology which are of interest to animal health investigators, veterinary practitioners and others with a special interest in parasitology. Papers of the highest quality dealing with all aspects of disease prevention, pathology, treatment, epidemiology, and control of parasites in all domesticated animals, fall within the scope of the journal. Papers of geographically limited (local) interest which are not of interest to an international audience will not be accepted. Authors who submit papers based on local data will need to indicate why their paper is relevant to a broader readership. Parasitological studies on laboratory animals fall within the scope of the journal only if they provide a reasonably close model of a disease of domestic animals. Additionally the journal will consider papers relating to wildlife species where they may act as disease reservoirs to domestic animals, or as a zoonotic reservoir. Case studies considered to be unique or of specific interest to the journal, will also be considered on occasions at the Editors'' discretion. Papers dealing exclusively with the taxonomy of parasites do not fall within the scope of the journal.