The CNN-based Coronary Occlusion Site Localization with Effective Preprocessing Method

The CNN-based Coronary Occlusion Site Localization with Effective Preprocessing Method


The Coronary Artery Occlusion (CAO) acutely comes to human, and it highly threats the human’s life. When CAO detected, Percutaneous Coronary Intervention (PCI) should be conducted timely. Before PCI, localizing the CAO is needed firstly, because the heart is covered with various arteries. We handle the three kinds of CAO in this paper and our purpose is not only localization of CAO but also improving the localizing performance via preprocessing method. We improve localization performance from a minimum of 0.150 to a maximum of 0.372 via our noise reduction and pulse extraction based method.


Coronary Artery Occlusion Localization Preprocessing Method

1 Introduction

The Coronary Artery Occlusion (CAO) makes thrombus or embolism and these cause sudden blood flow shutting-down [9]. The physician will conduct Percutaneous Coronary Intervention (PCI) when the patient is suffered from CAO. However, the heart is covered with various arteries such as Left Anterior Descending Artery (LAD), Left Circumflex Artery (LCX), and Right Coronary Artery (RCA) [3, 7]. Also, those arteries show various characteristic with CAO in ECG [2].

For conducting PCI, the physician needs to know the occlusion site of the coronary artery. Taking a CT scan may be more helpful for distinguishing the location, but there is not enough time for CT scan in an emergency situation. On the other hand, ECG can quickly measure the patient’s condition, although only limited information is provided. Thus, we make the best use of ECG for localizing coronary occlusion site.

2 Related work

One of the studies already shows the high performance at detecting coronary site location using decision tree [5]. They deal with classifying LAD, LCX, and RCA, and their average sensitivity and specificity are 72% and 92.5% respectively using improved classification algorithm than their previous work [4]. Sensitivity is a more important indicator than specificity, especially in emergency medicine. However, their sensitivity is 20.5% lower than specificity. This means that only 7.5% of normal patients are missed but CAO patients are missed 28%.

The method for finding patients as much as possible is needed, and accordingly, various studies are already conducted. One of the studies suggests a preprocessing method for better performance in the same classifier [8]. That preprocessing method is dealt with in this research and several experiments for comparing and finding the better method.

3 Proposed approach

In this section, we present our approach for localizing coronary occlusion site. We refer to the preprocessing method in the previous STEMI detection study [8], and classification algorithm from study of Richard et al. [5]. The above algorithm has not only simplified architecture but also improved performance than their previous work for achieving the same purpose [4]. The preprocessing method is constructed with noise reduction and pulse extraction. The noise reduction is conducted via notch filter and high-pass filter. We apply the above preprocessing method before entering the data to the classifier.

We construct the neural network architectures as shown in Figure 1 based on ResNet [6]. We construct two CNN architecture using 1D convolutiona and 2D convolution separately. For comparing the performance, we use two kind of convolution, 1 Dimensional (1D) convolution and 2 Dimensional (2D) convolution. We use both architecture for experiment and then we will select more effective model.

Figure 1: In this figure the ResBlock, FullCon, and Conv means residual block, fully connected layer, and convolutional layer respectively. The residual block is constructed as the right subfigure.

Then, we construct the CAO localization classification algorithm based on previous work [5]. They used the three decision trees as a classifier. The first classifier is used for categorizing LAD or not, and the next two classifiers are used to classifying proximal LAD or non-proximal LAD and LCX or RCA respectively. However, we do not have the detailed label as proximal or non-proximal LAD, so we construct the classification algorithm as shown in Figure 2.

Figure 2: The CAO classification algorithm that constructed with two-stage. We name the classifier that classifies LAD or Non-LAD as stage-1 and the other, for classifying LCX or RCA, as stage-2.

Each stage of Figure 2 is constructed with CNN as shown in Figure 1. We pursue to confirming the effectiveness of our preprocessing method based on denoising and pulse extraction at the above classification algorithm in this paper.

4 Experiments

In this section, we present our dataset that originally provided by Seoul National University Bundang Hospital(SNUBH), and the experimental results. Firstly, we apply the preprocessing method as used in related work that method contains noise reduction and pulse extraction [8]. We call the each dataset as same as previous work. The two dataset, SNUBH-R and SNUBH-BP that as shown in Table 1, are used for experiments. The SNUBH-R contains raw ECG records, and the SNUBH-BP contains extracted pulse after applying both high-pass and notch filter. Then, we conduct the experiments using above dataset and the classifier as shown in Figure 2.

SNUBH-R 419 70 283
SNUBH-BP 4487 715 2591
Table 1: The ECG records are originally provided by SNUBH and it named SNUBH-R. The preprocessed dataset is named as SNUBH-BP.

We use the accuracy, sensitivity, specificity, and Area Under the Receiver Operating characteristics Curve (AUROC) [1] as the performance indicator. The performance measurement is conducted for each of the two stages as the classifier consisted of two stages. The measured performances for each stage are summarized as Table 2 and 3.

CNN Set Accuracy Sensitivity Specificity AUROC
1D-CNN SNUBH-R 0.549 0.039 0.453 0.072 0.631 0.064 0.560 0.046
SNUBH-BP 0.910 0.020 0.895 0.032 0.921 0.024 0.932 0.021
2D-CNN SNUBH-R 0.569 0.032 0.450 0.168 0.658 0.124 0.571 0.042
SNUBH-BP 0.915 0.020 0.898 0.029 0.927 0.027 0.926 0.020
Table 2: Performance of stage-1

When using the SNUBH-BP, dataset after preprocessing, the performance is highly improved than the case of using raw ECG record, SNUBH-R, both in the 1D-CNN and 2D CNN cases. The AUROC is increased 0.372 and 0.355 for 1D-CNN and 2D-CNN respectively. Moreover, It can be confirmed that the performance of 1D CNN is higher than 2D CNN.

CNN Set Accuracy Sensitivity Specificity AUROC
1D-CNN SNUBH-R 0.770 0.034 0.944 0.037 0.062 0.058 0.513 0.082
SNUBH-BP 0.775 0.030 0.898 0.028 0.319 0.103 0.663 0.050
2D-CNN SNUBH-R 0.715 0.044 0.854 0.059 0.150 0.075 0.518 0.058
SNUBH-BP 0.764 0.038 0.892 0.050 0.284 0.117 0.612 0.062
Table 3: Performance of stage-2

In stage-2, the performance is also improved with SNUBH-BP set. Thus, we confirm that our preprocessing technique can help to improve the CAO classification ability. However, the above two tables show that the 1D-CNN shows better performance than 2D-CNN, so if who wants to use CNN for classifying CAO the 1D-CNN is recommended.

5 Conclusion

We do not conduct the experiment for finding the optimal structure of the CNN and the hyperparameters for CNN. However, our experiments show that our preprocessing technique, based on both noise reduction and pulse extraction, can improve the classification performance with simple CNN. The performance is improved as much as 0.372 and 0.150 in stage-1 and stage-2 respectively with 1D-CNN. The CAO classification performance will be highly improved if the optimal CNN structure is found with fine hyperparameter. However, when using our preprocessing method, everyone can achieve high performance without finding the fine classifier.


This research was supported by grant No. 2017R1A2B4004503 and Hankuk University of Foreign Studies Research Fund. Also, this research was in line with the Declaration of Helsinki and approved by the Seoul National University Bundang Hospital institutional review board in 2019 (B-1811-502-003).


  1. T. Fawcett (2006) An introduction to roc analysis. Pattern Recognition Letters 27 (8), pp. 861 – 874. Cited by: §4.
  2. R. M. Fuchs, S. C. Achuff, L. Grunwald, F. C. Yin and L. S. Griffith (1982) Electrocardiographic localization of coronary artery narrowings: studies during myocardial ischemia and infarction in patients with one-vessel disease.. Circulation 66 (6), pp. 1168–1176. Cited by: §1.
  3. P. Georgoulias (2016) Myocardial perfusion (spect) imaging: radiotracers and techniques. Frontiers in Heart Failure Volume 2: Molecular Imaging and Related Topics 1st ed, Bentham Science Publishers. External Links: ISBN 9781681083773 Cited by: §1.
  4. R. E. Gregg, M. Fiol-Sala, K. C. Nikus, R. Startt, S. H. Zhou, A. Carrillo, V. Barbara, C. S. Chien and J. M. Lindauer (2012) Automated discrimination of proximal right coronary artery occlusion from middle-to-distal right coronary artery occlusion and left circumflex occlusion in st-elevation myocardial infarction. Journal of electrocardiology 45 (4), pp. 343–349. Cited by: §2, §3.
  5. R. E. Gregg and S. Babaeizadeh (2014) Detection of culprit coronary lesion location in pre-hospital 12-lead ecg. Journal of Electrocardiology 47 (6), pp. 890–894. Cited by: §2, §3, §3.
  6. K. He, X. Zhang, S. Ren and J. Sun (2015) Deep residual learning for image recognition. External Links: 1512.03385 Cited by: §3.
  7. S. S. Kim, H. S. Choi, M. H. Jeong, J. G. Cho, Y. K. Ahn, J. H. Kim, S. C. Chae, Y. J. Kim, S. H. Hur, I. W. Seong, T. J. Hong, D. Choi, M. C. Cho, C. J. Kim, K. B. Seung, W. S. Chung, Y. S. Jang, S. W. Rha, J. H. Bae and S. J. Park (2011) Clinical outcomes of acute myocardial infarction with occluded left circumflex artery. Journal of Cardiology 57 (3), pp. 290–296. Cited by: §1.
  8. Y. Park, I. D. Yun and S. Kang (2019) Preprocessing method for performance enhancement in cnn-based stemi detection from 12-lead ecg. IEEE Access 7 (), pp. 99964–99977. Cited by: §2, §3, §4.
  9. K. Thygesen, J. S. Alpert, A. S. Jaffe, M. L. Simoons, B. R. Chaitman and H. D. White (2012) Third universal definition of myocardial infarction. Circulation 126 (16), pp. 2020–2035. Cited by: §1.
Comments 0
Request Comment
You are adding the first comment!
How to quickly get a good reply:
  • Give credit where it’s due by listing out the positive aspects of a paper before getting into which changes should be made.
  • Be specific in your critique, and provide supporting evidence with appropriate references to substantiate general statements.
  • Your comment should inspire ideas to flow and help the author improves the paper.

The better we are at sharing our knowledge with each other, the faster we move forward.
The feedback must be of minimum 40 characters and the title a minimum of 5 characters
Add comment
Loading ...
This is a comment super asjknd jkasnjk adsnkj
The feedback must be of minumum 40 characters
The feedback must be of minumum 40 characters

You are asking your first question!
How to quickly get a good answer:
  • Keep your question short and to the point
  • Check for grammar or spelling errors.
  • Phrase it like a question
Test description