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

Detalles Bibliográficos
Parent link:	Scientific Reports Vol. 11, iss. 1.— 2021.— [7582, 13 p.]
Corporate Authors:	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
Outros autores:	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
Summary:	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:	inglés
Publicado:	2021
Subjects:	электронный ресурс труды учёных ТПУ режим реального времени обнаружение диагностика ишемическая болезнь глубокое обучение стеноз нейронные сети коронарные артерии
Acceso en liña:	https://doi.org/10.1038/s41598-021-87174-2
Formato:	Electrónico Capítulo de libro
KOHA link:	https://koha.lib.tpu.ru/cgi-bin/koha/opac-detail.pl?biblionumber=667328