TY - JOUR
T1 - Comparative study of deep learning models for automatic coronary stenosis detection in x-ray angiography
AU - Danilov, Viacheslav
AU - Gerget, Olga
AU - Klyshnikov, Kirill
AU - Ovcharenko, Evgeny
AU - Frangi, Alejandro
N1 - Funding Information:
Data mining, data pre-processing and development of the ML-based approach to detect stenosis were supported by a grant from the Russian Science Foundation, project No. 18-75-10061?Research and implementation of the concept of robotic minimally invasive prosthetics of the aortic valve?. The training of the developed models using Amazon Web Services was funded by the Ministry of Science and Higher Education, project No. FFSWW-2020-0014 ?Development of the technology for robotic multiparametric tomography based on big data processing and machine learning methods for studying promising composite materials?. The selection of the primary metrics suggesting the model performance and their analysis was supported by the grant of the Russian Foundation of Basic Research, project No. 19-07-00351/19 ?Methods and intelligent technologies for the scientific justification of strategic solutions on digital transformation?.
Publisher Copyright:
© 2020 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
Copyright:
Copyright 2020 Elsevier B.V., All rights reserved.
PY - 2020
Y1 - 2020
N2 - The article explores the application of machine learning approach to detect both single-vessel and multivessel coronary artery disease from X-ray angiography. Since the interpretation of coronary angiography images requires interventional cardiologists to have considerable training, our study is aimed at analysing, training, and assessing the potential of the existing object detectors for classifying and detecting coronary artery stenosis using angiographic imaging series. 100 patients who underwent coronary angiography at the Research Institute for Complex Issues of Cardiovascular Diseases were retrospectively enrolled in the study. To automate the medical data analysis, we examined and compared three models (SSD MobileNet V1, Faster-RCNN ResNet-50 V1, Faster-RCNN NASNet) with various architecture, network complexity, and a number of weights. To compare developed deep learning models, we used the mean Average Precision (mAP) metric, training time, and inference time. Testing results show that the training/inference time is directly proportional to the model complexity. Thus, Faster-RCNN NASNet demonstrates the slowest inference time. Its mean inference time per one image made up 880 ms. In terms of accuracy, Faster-RCNN ResNet-50 V1 demonstrates the highest prediction accuracy. This model has reached the mAP metric of 0.92 on the validation dataset. SSD MobileNet V1 has demonstrated the best inference time with the inference rate of 23 frames per second.
AB - The article explores the application of machine learning approach to detect both single-vessel and multivessel coronary artery disease from X-ray angiography. Since the interpretation of coronary angiography images requires interventional cardiologists to have considerable training, our study is aimed at analysing, training, and assessing the potential of the existing object detectors for classifying and detecting coronary artery stenosis using angiographic imaging series. 100 patients who underwent coronary angiography at the Research Institute for Complex Issues of Cardiovascular Diseases were retrospectively enrolled in the study. To automate the medical data analysis, we examined and compared three models (SSD MobileNet V1, Faster-RCNN ResNet-50 V1, Faster-RCNN NASNet) with various architecture, network complexity, and a number of weights. To compare developed deep learning models, we used the mean Average Precision (mAP) metric, training time, and inference time. Testing results show that the training/inference time is directly proportional to the model complexity. Thus, Faster-RCNN NASNet demonstrates the slowest inference time. Its mean inference time per one image made up 880 ms. In terms of accuracy, Faster-RCNN ResNet-50 V1 demonstrates the highest prediction accuracy. This model has reached the mAP metric of 0.92 on the validation dataset. SSD MobileNet V1 has demonstrated the best inference time with the inference rate of 23 frames per second.
KW - Deep Learning
KW - Stenosis Detection
KW - Transfer Learning
KW - X-ray Angiography
UR - http://www.scopus.com/inward/record.url?scp=85098158759&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85098158759&partnerID=8YFLogxK
M3 - Conference article
AN - SCOPUS:85098158759
VL - 2744
JO - CEUR Workshop Proceedings
JF - CEUR Workshop Proceedings
SN - 1613-0073
T2 - 30th International Conference on Computer Graphics and Machine Vision, GraphiCon 2020
Y2 - 22 September 2020 through 25 September 2020
ER -