Breast cancer classification from mammographic images using Inception V4 model
Kh.S. Abdiyeva, O.R. Yusupov, Ziyodullo Malikov · 2024
Significant scientific and research efforts are being made worldwide with the goal of developing new calculation algorithms and enhancing image analysis and classification algorithms for intelligent oncological disease diagnostic systems based on medical images. One of the key problems is treating patient illnesses quickly, diagnosing them correctly, analyzing them thoroughly and quickly, and conserving material resources. Doctors can determine the best course of treatment and make an accurate clinical diagnosis with the aid of computer-aided medical image analysis. The method of preference for medical image analysis and classification is convolutional neural networks (CNN). In intelligent diagnostic systems based on digital mammograms, this paper investigates the classification algorithm based on the Inception V4 model for identifying breast cancer. Breast cancer has recently held the top spot among all oncological disorders worldwide [ 1 ]. Artificial intelligence (AI) techniques are frequently used in the modern healthcare system for the interpretation and classification of medical images. One of the pioneering methods in this field is the utilization of deep learning models, such as the Inception V4 model, to analyze medical images with high precision and reliability. Inception V4, an evolution of the Inception architecture, is a state-of-the-art convolutional neural network (CNN) known for its exceptional performance in image recognition tasks. Its ability to extract intricate features from complex images makes it a promising candidate for breast cancer classification. By harnessing the power of Inception V4, researchers and medical professionals can enhance the accuracy and efficiency of breast cancer diagnosis, reducing the burden on healthcare systems and improving patient outcomes. This research explores the application of the Inception V4 model in breast cancer classification, aiming to provide a comprehensive understanding of the methodology, challenges, and potential benefits of utilizing deep learning techniques for this critical healthcare task. We will delve into the architecture of the Inception V4 model, the dataset used, the training process, and the evaluation metrics employed.