Classification of carotid artery intima-media thickness ultrasound images with deep learning.

In the entire world, cardiovascular disease (CVD) is one of the main causes of death. Early detection is critical for effective treatment. A common and noninvasive diagnostic method for spotting cardiovascular disease is carotid artery ultrasonography. The research study developed a CNN-based decision support system that employed five machine learning algorithms to predict the cause of heart disease and achieved a 95 percent hit rate. The system has the potential to efficiently diagnose carotid artery conditions and facilitate the development of a multicategory classification algorithm for carotid images. The proposed methodology can serve as a standardized approach for automated segmentation and more precise IMT measurement. With an average recall as well as precision of 0.9422 for validation as well as training data, the CNN algorithm attained an accuracy of 0.9422. The researchers suggest assessing intima media thickness (IMT) of carotid artery in ultrasound images using CNN. This approach may help to detect and diagnose CVD more accurately and efficiently. The suggested method may considerably increase the rate and preciseness of CVD diagnosis and allow for quicker and more efficient treatment. The study has substantial ramifications for improving cardiovascular disease detection and treatment, which could have a big effect on public health. [ABSTRACT FROM AUTHOR]