Classification and Diagnosis of Mammary Tumors in Dogs Using Deep Learning Techniques

Abstract

Mammary tumors are commonly found in domestic animals and significantly affect animal health. In this context, the analysis of mammary tumor cells in domestic animals is crucial for the diagnosis, monitoring, and treatment of cancer. These tumors can also lead to the death of animals. Therefore, academic studies are needed to prevent and early diagnose mammary cancer in animals. In this study, an artificial intelligence-supported system for early diagnosis of whether mammary tumor sections taken from domestic dogs will cause cancer was developed. The proposed system consists of image processing and classification stages. The data for the study was provided by the Faculty of Veterinary Medicine at Burdur Mehmet Akif Ersoy University. In the image processing stage, various data preprocessing techniques and deep learning-based convolutional neural networks were used. Then, benign and malignant mammary tumors were classified to diagnose cancer. Data preprocessing techniques such as data augmentation, normalization and image filtering techniques were used to improve the performance of the deep learning-based image processing algorithm. The Xception model achieved a 98.9% success rate in tumor diagnosis. The study is believed to have made a significant contribution to the literature by using current methods and having a unique data set.