RESUMEN
Successful identification of estrum or other stages in a cycling bitch often requires a combination of methods, including assessment of its behavior, exfoliative vaginal cytology, vaginoscopy, and hormonal assays. Vaginoscopy is a handy and inexpensive tool for the assessment of the breeding period. The present study introduces an innovative method for identifying the stages in the estrous cycle of female canines. With a dataset of 210 vaginoscopic images covering four reproductive stages, this approach extracts deep features using the inception v3 and Residual Networks (ResNet) 152 models. Binary gray wolf optimization (BGWO) is applied for feature optimization, and classification is performed with the extreme gradient boosting (XGBoost) algorithm. Both models are compared with the support vector machine (SVM) with the Gaussian and linear kernel, k-nearest neighbor (KNN), and convolutional neural network (CNN), based on performance metrics such as accuracy, specificity, F1 score, sensitivity, precision, matthew correlation coefficient (MCC), and runtime. The outcomes demonstrate the superiority of the deep model of ResNet 152 with XGBoost classifier, achieving an average model accuracy of 90.37%. The method gave a specific accuracy of 90.91%, 96.38%, 88.37%, and 88.24% in predicting the proestrus, estrus, diestrus, and anestrus stages, respectively. When performing deep feature analysis using inception v3 with the same classifiers, the model achieved an accuracy of 89.41%, which is comparable to the results obtained with the ResNet model. The proposed model offers a reliable system for identifying the optimal mating period, providing breeders and veterinarians with an efficient tool to enhance the success of their breeding programs.
Asunto(s)
Aprendizaje Profundo , Animales , Femenino , Perros , Ciclo Estral/fisiología , Vagina , Máquina de Vectores de Soporte , Estro/fisiologíaRESUMEN
INTRODUCTION: The Paris System (TPS) has recently been used in classification of urinary tract cytological specimens. Upper urinary tract (UUT) specimens are cytologically challenging. The utility of TPS was investigated in evaluating UUT specimens and its correlation with subsequent histological follow-up. METHOD: From 2014 to 2017, 324 cytology cases of UUT from 179 patients were retrieved. Concurrent or subsequent biopsy or resection within a 2-month period was available in 125 cases from 74 patients. RESULT: None of the cases with a cytology of low-grade urothelial neoplasm was found to have a high-grade urothelial carcinoma (HGUC) on biopsy. Among the 19 atypical urothelial cells (AUC) cytology cases, the histology is heterogeneous (seven benign, one atypia, five low-grade lesion, and six HGUC). The risk of HGUC for each cytological diagnostic category are 0% for non-diagnostic/unsatisfactory, 6% for negative for HGUC, 27.3% for AUC, 0% for low-grade urothelial neoplasm, 48% for suspicious for HGUC and 95% for positive HGUC. When we considered cytology cases with suspicious or positive for HGUC interpretations as positive, the performance of TPS in predicting high grade urothelial carcinoma on histology had values of: 78.6% sensitivity, 86% specificity, 80.5% positive predictive value and 84.5% negative predictive value. CONCLUSION: More than one-third of the UUT cytological cases were classified as AUC and approximately 1/15 as suspicious or positive for HGUC. Based on UUT cytology specimens, the risk of malignancy of each cytological diagnostic category of TPS was comparable to those reported in the literature. The use of TPS in evaluating UUT cytology specimens was specific and sensitive in identifying patients with HGUC by histology.