000			03536nlm1a2200385 4500
001			665005
005			20231030041949.0
035			_a(RuTPU)RU\TPU\network\36204
035			_aRU\TPU\network\33381
090			_a665005
100			_a20210621a2021 k y0engy50 ba
101	0		_aeng
102			_aDE
135			_adrcn ---uucaa
181		0	_ai
182		0	_ab
200	1		_aAnalysis of Deep Neural Networks for Detection of Coronary Artery Stenosis _fV. V. Danilov, O. M. Gerget, K. Yu. Klyshnikov [et al.]
203			_aText _celectronic
300			_aTitle screen
320			_a[References: 19 tit.]
330			_aThis paper describes an approach based on machine learning technology that is of particular interest for the localization and characterization of both single focal stenoses and multivessel multifocal lesions. Due to the complexity of analyzing large amounts of data for the cardiac surgeon, we pay special attention to the analysis, training, and comparison of popular neural networks that classify and localize foci of stenosis on coronary angiography data. From the complete coronarography dataset collected at the Research Institute for Complex Issues of Cardiovascular Diseases, we retrospectively select data of 100 patients. For the automated analysis of the medical data, the paper considers in detail three models (SSD MobileNet V1, Faster-RCNN ResNet-50 V1, and Faster-RCNN NASNet), which differ in their architecture, complexity, and the number of weights. The models are compared in terms of their basic efficiency characteristics: accuracy, training time, and prediction time. The test results show that the training and prediction times are directly proportional to the complexity of the models. In this regard, Faster-RCNN NASNet exhibits the lowest prediction time (the average processing time for one image is 880 ms), while Faster-RCNN ResNet-50 V1 has the highest prediction accuracy. The latter model reaches the mean average precision (mAP) level of 0.92 on the validation dataset. On the other hand, SSD MobileNet V1 is the fastest model, capable of making predictions with a prediction rate of 23 fps.
333			_aРежим доступа: по договору с организацией-держателем ресурса
461			_tProgramming and Computer Software
463			_tVol. 47, iss. 3 _v[P. 153-160] _d2021
610	1		_aэлектронный ресурс
610	1		_aтруды учёных ТПУ
701		1	_aDanilov _bV. V. _cspecialist in the field of informatics and computer technology _cengineer of Tomsk Polytechnic University _f1989- _gVyacheslav Vladimirovich _2stltpush _3(RuTPU)RU\TPU\pers\37831
701		1	_aGerget _bO. M. _cSpecialist in the field of informatics and computer technology _cAssociate Professor of Tomsk Polytechnic University, Candidate of technical sciences _f1974- _gOlga Mikhailovna _2stltpush _3(RuTPU)RU\TPU\pers\31430
701		1	_aKlyshnikov _bK. Yu. _gKirill Yurjevich
701		1	_aFrangi _bA. _gAlejandro
701		1	_aOvcharenko _bE. A. _gEvgeny Andreevich
712	0	2	_aНациональный исследовательский Томский политехнический университет _bИнженерная школа информационных технологий и робототехники _bОтделение информационных технологий _h7951 _2stltpush _3(RuTPU)RU\TPU\col\23515
801		2	_aRU _b63413507 _c20210621 _gRCR
856	4		_uhttps://doi.org/10.1134/S0361768821030038
942			_cCF