Identification and Diagnosis of Cerebral Stroke through Deep Convolutional Neural Network-Based Multimodal MRI Images
Copyright © 2021 Yanyan Pan et al..
This study aimed to explore the application value of multimodal magnetic resonance imaging (MRI) images based on the deep convolutional neural network (Conv.Net) in the diagnosis of strokes. Specifically, four automatic segmentation algorithms were proposed to segment multimodal MRI images of stroke patients. The segmentation effects were evaluated factoring into DICE, accuracy, sensitivity, and segmentation distance coefficient. It was found that although two-dimensional (2D) full convolutional neural network-based segmentation algorithm can locate and segment the lesion, its accuracy was low; the three-dimensional one exhibited higher accuracy, with various objective indicators improved, and the segmentation accuracy of the training set and the test set was 0.93 and 0.79, respectively, meeting the needs of automatic diagnosis. The asymmetric 3D residual U-Net network had good convergence and high segmentation accuracy, and the 3D deep residual network proposed on its basis had good segmentation coefficients, which can not only ensure segmentation accuracy but also avoid network degradation problems. In conclusion, the Conv.Net model can accurately segment the foci of patients with ischemic stroke and is suggested in clinic.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2021 |
|---|---|
| Erschienen: |
2021 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:2021 |
|---|---|
| Enthalten in: |
Contrast media & molecular imaging - 2021(2021) vom: 04., Seite 7598613 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Pan, Yanyan [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
|---|
| Anmerkungen: |
Date Completed 10.01.2022 Date Revised 10.01.2022 published: Electronic-eCollection Citation Status MEDLINE |
|---|
| doi: |
10.1155/2021/7598613 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM329252119 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM329252119 | ||
| 003 | DE-627 | ||
| 005 | 20231225204719.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231225s2021 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1155/2021/7598613 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1097.xml |
| 035 | |a (DE-627)NLM329252119 | ||
| 035 | |a (NLM)34381322 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Pan, Yanyan |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Identification and Diagnosis of Cerebral Stroke through Deep Convolutional Neural Network-Based Multimodal MRI Images |
| 264 | 1 | |c 2021 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Completed 10.01.2022 | ||
| 500 | |a Date Revised 10.01.2022 | ||
| 500 | |a published: Electronic-eCollection | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a Copyright © 2021 Yanyan Pan et al. | ||
| 520 | |a This study aimed to explore the application value of multimodal magnetic resonance imaging (MRI) images based on the deep convolutional neural network (Conv.Net) in the diagnosis of strokes. Specifically, four automatic segmentation algorithms were proposed to segment multimodal MRI images of stroke patients. The segmentation effects were evaluated factoring into DICE, accuracy, sensitivity, and segmentation distance coefficient. It was found that although two-dimensional (2D) full convolutional neural network-based segmentation algorithm can locate and segment the lesion, its accuracy was low; the three-dimensional one exhibited higher accuracy, with various objective indicators improved, and the segmentation accuracy of the training set and the test set was 0.93 and 0.79, respectively, meeting the needs of automatic diagnosis. The asymmetric 3D residual U-Net network had good convergence and high segmentation accuracy, and the 3D deep residual network proposed on its basis had good segmentation coefficients, which can not only ensure segmentation accuracy but also avoid network degradation problems. In conclusion, the Conv.Net model can accurately segment the foci of patients with ischemic stroke and is suggested in clinic | ||
| 650 | 4 | |a Journal Article | |
| 700 | 1 | |a Zhang, Huiping |e verfasserin |4 aut | |
| 700 | 1 | |a Yang, Jinsuo |e verfasserin |4 aut | |
| 700 | 1 | |a Guo, Jing |e verfasserin |4 aut | |
| 700 | 1 | |a Yang, Zhiguo |e verfasserin |4 aut | |
| 700 | 1 | |a Wang, Jianbing |e verfasserin |4 aut | |
| 700 | 1 | |a Song, Ge |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Contrast media & molecular imaging |d 2006 |g 2021(2021) vom: 04., Seite 7598613 |w (DE-627)NLM167405136 |x 1555-4317 |7 nnns |
| 773 | 1 | 8 | |g volume:2021 |g year:2021 |g day:04 |g pages:7598613 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1155/2021/7598613 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 2021 |j 2021 |b 04 |h 7598613 | ||