Artery Deposition Analysis using Segmentation and CNN Classification


Huge Price Drop : 50% Discount
Source Code + Demo Video

100 in stock

SKU: Artery deposition analysis Category:



Artery disease is canopy term for any disorder that distress health of an individual. This disease can be classified using the Electrocardiography (ECG) signal. ECG is preferred to the display condition of the patient and for the diagnosis and treatment of various types of cardiac diseases. The variations in P-wave, QRS complex and T-wave parameters in ECG are used to identify the type of illness of the artery deposition. Some artery diseases are not served through other may prove fatal. Thus, there is need for classification of different artery diseases. To classify artery diseases, it is intended to implement the CNN algorithm in the proposed work.


Coronary artery disease (CAD) is one of the most dangerous diseases in the world. According to the WHO, around 17.7 million people died from CHD in 2015. CHD includes hyperlipidemia, myocardial infarction, and angina pectoris. In general, medical experts arrive at diagnoses based on electrocardiography, sonography, angiography, and blood test results. CHD is not easily diagnosed during the early disease stage, but for effective treatment, its early diagnosis is important. However, diagnoses are made based on medical experts’ personal experiences and understanding of the disease, which increase the risks of errors, delay appropriate treatment, increase treatment times, and substantially increase costs. In order to solve these problems, many studies have been conducted on clinical decision support systems using various techniques, such as data mining and machine learning. Of the machine learning techniques that have been used to predict CHD, neural network (NN) is popularly used to improve performance accuracy. NN is good at generalizing data without domain knowledge of CHD prior to training. In addition, by analyzing complex data, NN makes it possible to discover new patterns and information related to CHD.


Wavelet coefficients are calculated using iterative time discrete operations with the non-ideal high and low pass filters. Therefore, aliasing can appear. Inverse DWT cancels aliasing, but only if the wavelet coefficients were not processed. Separable 2D DWT efficiently detects horizontal and vertical edges. But, if the edges are under an acute angle, unwanted checkerboard artifacts appear. One of the possible solutions for mentioned problems is the wavelet packet transform.


In the proposed system ECG signal is given as input the given signal is segmented into large number of samples the segmentation part is done to analyze the signal properly afterward the partitioned signal is decomposed in decomposition (interpolation and decimation) is carried out the obtained output is trained in 1d CNN in a particular format the training parameter is tested with the patient parameter, and the classification results are obtained which specifies the heartbeats are normal or abnormal.





  • Detection of artery complication is reduced
  • The accuracy of the results will be maximum


  • Biomedical application
  • Diagnosis application


  • Python 2.7 Version
  • ANACONDA Software


In this paper, the proposed system gives the error rate to small. For a signal of 1minute record having a larger number of samples which means while training the CNN the correctness of classification is higher and normal and abnormal will be classified very easily and with greater accuracy. Such a compact implementation for each patient over a simple CNN not only negates the necessity to extract hand-crafted manual features, or any kind of pre- and post processing, also makes it a primary choice for implementation for artery monitoring and anomaly detection. The obtained accuracy is nearly 90% Besides the rapidity and computational effectiveness accomplished, distinct patients can be treated once the CNN is trained, long ECG records can be classified in a reckless and accurate manner for specific patient uniquely.


There are no reviews yet.

Be the first to review “Artery Deposition Analysis using Segmentation and CNN Classification”

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.