Real-time coronary artery stenosis detection based on modern neural networks; Scientific Reports; Vol. 11, iss. 1

Dades bibliogràfiques
Parent link:Scientific Reports
Vol. 11, iss. 1.— 2021.— [7582, 13 p.]
Autor corporatiu: Национальный исследовательский Томский политехнический университет Инженерная школа информационных технологий и робототехники Научно-образовательная лаборатория обработки и анализа больших данных, Национальный исследовательский Томский политехнический университет Инженерная школа информационных технологий и робототехники Отделение информационных технологий
Altres autors: Danilov V. V. Vyacheslav Vladimirovich, Klyshnikov K. Yu. Kirill Yurjevich, Gerget O. M. Olga Mikhailovna, Kutikhin A. G. Anton Gennadievich, Ganuykov V. I. Vladimir, Frangi A. F. Alejandro, Ovcharenko E. A. Evgeny Andreevich
Sumari:Title screen
Invasive coronary angiography remains the gold standard for diagnosing coronary artery disease, which may be complicated by both, patient-specific anatomy and image quality. Deep learning techniques aimed at detecting coronary artery stenoses may facilitate the diagnosis. However, previous studies have failed to achieve superior accuracy and performance for real-time labeling. Our study is aimed at confirming the feasibility of real-time coronary artery stenosis detection using deep learning methods. To reach this goal we trained and tested eight promising detectors based on different neural network architectures (MobileNet, ResNet-50, ResNet-101, Inception ResNet, NASNet) using clinical angiography data of 100 patients. Three neural networks have demonstrated superior results. The network based on Faster-RCNN Inception ResNet V2 is the most accurate and it achieved the mean Average Precision of 0.95, F1-score 0.96 and the slowest prediction rate of 3 fps on the validation subset. The relatively lightweight SSD MobileNet V2 network proved itself as the fastest one with a low mAP of 0.83, F1-score of 0.80 and a mean prediction rate of 38 fps. The model based on RFCN ResNet-101 V2 has demonstrated an optimal accuracy-to-speed ratio. Its mAP makes up 0.94, F1-score 0.96 while the prediction speed is 10 fps. The resultant performance-accuracy balance of the modern neural networks has confirmed the feasibility of real-time coronary artery stenosis detection supporting the decision-making process of the Heart Team interpreting coronary angiography findings.
Idioma:anglès
Publicat: 2021
Matèries:
Accés en línia:https://doi.org/10.1038/s41598-021-87174-2
Format: Electrònic Capítol de llibre
KOHA link:https://koha.lib.tpu.ru/cgi-bin/koha/opac-detail.pl?biblionumber=667328

MARC

LEADER 00000naa0a2200000 4500
001 667328
005 20251127124010.0
035 |a (RuTPU)RU\TPU\network\38533 
035 |a RU\TPU\network\36097 
090 |a 667328 
100 |a 20220316d2021 k||y0rusy50 ba 
101 0 |a eng 
135 |a drcn ---uucaa 
181 0 |a i  
182 0 |a b 
200 1 |a Real-time coronary artery stenosis detection based on modern neural networks  |f V. V. Danilov, K. Yu. Klyshnikov, O. M. Gerget [et al.] 
203 |a Text  |c electronic 
300 |a Title screen 
320 |a [References: 51 tit.] 
330 |a Invasive coronary angiography remains the gold standard for diagnosing coronary artery disease, which may be complicated by both, patient-specific anatomy and image quality. Deep learning techniques aimed at detecting coronary artery stenoses may facilitate the diagnosis. However, previous studies have failed to achieve superior accuracy and performance for real-time labeling. Our study is aimed at confirming the feasibility of real-time coronary artery stenosis detection using deep learning methods. To reach this goal we trained and tested eight promising detectors based on different neural network architectures (MobileNet, ResNet-50, ResNet-101, Inception ResNet, NASNet) using clinical angiography data of 100 patients. Three neural networks have demonstrated superior results. The network based on Faster-RCNN Inception ResNet V2 is the most accurate and it achieved the mean Average Precision of 0.95, F1-score 0.96 and the slowest prediction rate of 3 fps on the validation subset. The relatively lightweight SSD MobileNet V2 network proved itself as the fastest one with a low mAP of 0.83, F1-score of 0.80 and a mean prediction rate of 38 fps. The model based on RFCN ResNet-101 V2 has demonstrated an optimal accuracy-to-speed ratio. Its mAP makes up 0.94, F1-score 0.96 while the prediction speed is 10 fps. The resultant performance-accuracy balance of the modern neural networks has confirmed the feasibility of real-time coronary artery stenosis detection supporting the decision-making process of the Heart Team interpreting coronary angiography findings. 
338 |b Российский научный фонд  |d 18-75-10061 
461 |t Scientific Reports 
463 |t Vol. 11, iss. 1  |v [7582, 13 p.]  |d 2021 
610 1 |a электронный ресурс 
610 1 |a труды учёных ТПУ 
610 1 |a режим реального времени 
610 1 |a обнаружение 
610 1 |a диагностика 
610 1 |a ишемическая болезнь 
610 1 |a глубокое обучение 
610 1 |a стеноз 
610 1 |a нейронные сети 
610 1 |a коронарные артерии 
701 1 |a Danilov  |b V. V.  |c specialist in the field of informatics and computer technology  |c engineer of Tomsk Polytechnic University  |f 1989-  |g Vyacheslav Vladimirovich  |3 (RuTPU)RU\TPU\pers\37831 
701 1 |a Klyshnikov  |b K. Yu.  |g Kirill Yurjevich 
701 1 |a Gerget  |b O. M.  |c Specialist in the field of informatics and computer technology  |c Professor of Tomsk Polytechnic University, Doctor of Sciences  |f 1974-  |g Olga Mikhailovna  |3 (RuTPU)RU\TPU\pers\31430  |9 15593 
701 1 |a Kutikhin  |b A. G.  |g Anton Gennadievich 
701 1 |a Ganuykov  |b V. I.  |g Vladimir 
701 1 |a Frangi  |b A. F.  |g Alejandro 
701 1 |a Ovcharenko  |b E. A.  |g Evgeny Andreevich 
712 0 2 |a Национальный исследовательский Томский политехнический университет  |b Инженерная школа информационных технологий и робототехники  |b Научно-образовательная лаборатория обработки и анализа больших данных  |3 (RuTPU)RU\TPU\col\23599 
712 0 2 |a Национальный исследовательский Томский политехнический университет  |b Инженерная школа информационных технологий и робототехники  |b Отделение информационных технологий  |3 (RuTPU)RU\TPU\col\23515 
801 2 |a RU  |b 63413507  |c 20220316  |g RCR 
856 4 |u https://doi.org/10.1038/s41598-021-87174-2 
942 |c CF