Analysis of Deep Neural Networks for Detection of Coronary Artery Stenosis; Programming and Computer Software; Vol. 47, iss. 3
| Parent link: | Programming and Computer Software Vol. 47, iss. 3.— 2021.— [P. 153-160] |
|---|---|
| Údar corparáideach: | |
| Rannpháirtithe: | , , , , |
| Achoimre: | Title screen This 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. Режим доступа: по договору с организацией-держателем ресурса |
| Teanga: | Béarla |
| Foilsithe / Cruthaithe: |
2021
|
| Ábhair: | |
| Rochtain ar líne: | https://doi.org/10.1134/S0361768821030038 |
| Formáid: | Leictreonach Caibidil leabhair |
| KOHA link: | https://koha.lib.tpu.ru/cgi-bin/koha/opac-detail.pl?biblionumber=665005 |
MARC
| LEADER | 00000naa0a2200000 4500 | ||
|---|---|---|---|
| 001 | 665005 | ||
| 005 | 20260807071628.0 | ||
| 035 | |a (RuTPU)RU\TPU\network\36204 | ||
| 035 | |a RU\TPU\network\33381 | ||
| 090 | |a 665005 | ||
| 100 | |a 20210621d2021 k||y0rusy50 ba | ||
| 101 | 0 | |a eng | |
| 102 | |a DE | ||
| 135 | |a drcn ---uucaa | ||
| 181 | 0 | |a i | |
| 182 | 0 | |a b | |
| 200 | 1 | |a Analysis of Deep Neural Networks for Detection of Coronary Artery Stenosis |f V. V. Danilov, O. M. Gerget, K. Yu. Klyshnikov [et al.] | |
| 203 | |a Text |c electronic | ||
| 300 | |a Title screen | ||
| 320 | |a [References: 19 tit.] | ||
| 330 | |a This 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 | |a Режим доступа: по договору с организацией-держателем ресурса | ||
| 461 | |t Programming and Computer Software | ||
| 463 | |t Vol. 47, iss. 3 |v [P. 153-160] |d 2021 | ||
| 610 | 1 | |a электронный ресурс | |
| 610 | 1 | |a труды учёных ТПУ | |
| 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 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 Klyshnikov |b K. Yu. |g Kirill Yurjevich | |
| 701 | 1 | |a Frangi |b A. |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 |c 2017- |x TPU |7 ca |8 rus |9 28330 |
| 801 | 2 | |a RU |b 63413507 |c 20210621 |g RCR | |
| 856 | 4 | |u https://doi.org/10.1134/S0361768821030038 | |
| 942 | |c CF | ||