Development of New Staining Procedures for Diagnosing Cryptosporidium spp. in Fecal Samples by Computerized Image Analysis

Autor(es):Mostrar menos -

Nery Loiola, Saulo Hudson ^[1] ; Galvao, Felipe Lemes ^[2] ; dos Santos, Bianca Martins ^[1] ; Rosa, Stefany Laryssa ^[1] ; Soares, Felipe Augusto ^[1] ; Inacio, Sandra Valeria ^[3] ; Nagase Suzuki, Celso Tetsuo ^[2] ; Sabadini, Edvaldo ^[4] ; Saraiva Bresciani, Katia Denise ^[3] ; Falcao, Alexandre Xavier ^[2] ; Gomes, Jancarlo Ferreira ^{[1, 2]}

Afiliação do(s) autor(es)

^[1] Univ Estadual Campinas, Sch Med Sci, 126 Tessalia Vieira de Camargo St, BR-13083887 Campinas, SP - Brazil

^[2] Univ Estadual Campinas, Inst Comp, 573, IC-3, 5 Saturnino de Brito St, Room 364, BR-13083852 Campinas, SP - Brazil

^[3] Sao Paulo State Univ, UNESP, Sch Vet Med, 793 Clovis Pestana St, BR-16050680 Aracatuba, SP - Brazil

^[4] Univ Estadual Campinas, Inst Chem, 126 Josue de Castro St, BR-13083861 Campinas, SP - Brazil

• Tipo de documento: Artigo Científico
• Fonte: Microscopy and Microanalysis; v. 27, n. 6, p. 1518-1528, DEC 2021.
• Citações Web of Science: 0

Resumo

Interpretation errors may still represent a limiting factor for diagnosing Cryptosporidium spp. oocysts with the conventional staining techniques. Humans and machines can interact to solve this problem. We developed a new temporary staining protocol associated with a computer program for the diagnosis of Cryptosporidium spp. oocysts in fecal samples. We established 62 different temporary staining conditions by studying 20 experimental protocols. Cryptosporidium spp. oocysts were concentrated using the Three Fecal Test (TF-Test (R)) technique and confirmed by the Kinyoun method. Next, we built a bank with 299 images containing oocysts. We used segmentation in superpixels to cluster the patches in the images; then, we filtered the objects based on their typical size. Finally, we applied a convolutional neural network as a classifier. The trichrome modified by Melvin and Brooke, at a concentration use of 25%, was the most efficient dye for use in the computerized diagnosis. The algorithms of this new program showed a positive predictive value of 81.3 and 94.1% sensitivity for the detection of Cryptosporidium spp. oocysts. With the combination of the chosen staining protocol and the precision of the computational algorithm, we improved the Ova and Parasite exam (O\&P) by contributing in advance toward the automated diagnosis. (AU)

• Processo FAPESP: 18/21204-7 - Diagnóstico do protozoário Cryptosporidium spp., por meio de análise automatizada de imagens
• Beneficiário: Saulo Hudson Nery Loiola
• Modalidade de apoio: Bolsas no Brasil - Mestrado