Artery Deposition Detection Using Image Segmentation And CNN&RNN Classification

Abstract

Cardiovascular diseases remain one of the leading causes of mortality worldwide, with arterial plaque accumulation playing a critical role in conditions such as heart attacks and strokes. Early identification of artery deposition is essential for timely diagnosis and effective treatment. Conventional diagnostic approaches primarily depend on manual examination of medical images, which can be labor-intensive, time-consuming, and susceptible to human error. To overcome these limitations, this study proposes an automated artery deposition detection framework based on a hybrid deep learning architecture that integrates Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN).The proposed system employs CNN to extract meaningful spatial features from medical images, including arterial structure, texture characteristics, and plaque formations. These extracted features are then passed to an RNN model, implemented using Long Short-Term Memory (LSTM) or Gated Recurrent Units (GRU), to capture sequential patterns and temporal dependencies within image sequences. This combined architecture enables effective analysis of both structural and temporal characteristics associated with artery conditions.The methodology consists of several stages: dataset acquisition, image preprocessing, feature extraction through CNN, sequential modeling using RNN, and final classification of artery deposition patterns. Model performance is evaluated using standard metrics such as accuracy, precision, recall, and F1-score to ensure reliable detection capability.