A Novel Framework With Weighted Decision Map Based on Convolutional Neural Network for Cardiac MR Segmentation
For diagnosing cardiovascular disease, an accurate segmentation method is needed. There are several unresolved issues in the complex field of cardiac magnetic resonance imaging, some of which have been partially addressed by using deep neural networks. To solve two problems of over-segmentation and under-segmentation of anatomical shapes in the short-axis view from different cardiac magnetic resonance sequences, we propose a novel two-stage framework with a weighted decision map based on convolutional neural networks to segment the myocardium (Myo), left ventricle (LV), and right ventricle (RV) simultaneously. The framework comprises a decision map extractor and a cardiac segmenter. A cascaded U-Net++ is used as a decision map extractor to acquire the decision map that decides the category of each pixel. Cardiac segmenter is a multiscale dual-path feature aggregation network (MDFA-Net) which consists of a densely connected network and an asymmetric encoding and decoding network. The input to the cardiac segmenter is derived from processed original images weighted by the output of the decision map extractor. We conducted experiments on two datasets of multi-sequence cardiac magnetic resonance segmentation challenge 2019 (MS-CMRSeg 2019) and myocardial pathology segmentation challenge 2020 (MyoPS 2020). Test results obtained on MyoPS 2020 show that the average Dice coefficients of the proposed method on the segmentation tasks of Myo, LV and RV are 84.70%, 86.00%, and 86.31%, respectively.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2022 |
|---|---|
| Erschienen: |
2022 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:26 |
|---|---|
| Enthalten in: |
IEEE journal of biomedical and health informatics - 26(2022), 5 vom: 01. Mai, Seite 2228-2239 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Li, Fei Yan [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
|---|
| Anmerkungen: |
Date Completed 09.05.2022 Date Revised 28.05.2022 published: Print-Electronic Citation Status MEDLINE |
|---|
| doi: |
10.1109/JBHI.2021.3131758 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM33388714X |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM33388714X | ||
| 003 | DE-627 | ||
| 005 | 20231225222552.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231225s2022 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1109/JBHI.2021.3131758 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1112.xml |
| 035 | |a (DE-627)NLM33388714X | ||
| 035 | |a (NLM)34851840 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Li, Fei Yan |e verfasserin |4 aut | |
| 245 | 1 | 2 | |a A Novel Framework With Weighted Decision Map Based on Convolutional Neural Network for Cardiac MR Segmentation |
| 264 | 1 | |c 2022 | |
| 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 09.05.2022 | ||
| 500 | |a Date Revised 28.05.2022 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a For diagnosing cardiovascular disease, an accurate segmentation method is needed. There are several unresolved issues in the complex field of cardiac magnetic resonance imaging, some of which have been partially addressed by using deep neural networks. To solve two problems of over-segmentation and under-segmentation of anatomical shapes in the short-axis view from different cardiac magnetic resonance sequences, we propose a novel two-stage framework with a weighted decision map based on convolutional neural networks to segment the myocardium (Myo), left ventricle (LV), and right ventricle (RV) simultaneously. The framework comprises a decision map extractor and a cardiac segmenter. A cascaded U-Net++ is used as a decision map extractor to acquire the decision map that decides the category of each pixel. Cardiac segmenter is a multiscale dual-path feature aggregation network (MDFA-Net) which consists of a densely connected network and an asymmetric encoding and decoding network. The input to the cardiac segmenter is derived from processed original images weighted by the output of the decision map extractor. We conducted experiments on two datasets of multi-sequence cardiac magnetic resonance segmentation challenge 2019 (MS-CMRSeg 2019) and myocardial pathology segmentation challenge 2020 (MyoPS 2020). Test results obtained on MyoPS 2020 show that the average Dice coefficients of the proposed method on the segmentation tasks of Myo, LV and RV are 84.70%, 86.00%, and 86.31%, respectively | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a Research Support, Non-U.S. Gov't | |
| 700 | 1 | |a Li, Weisheng |e verfasserin |4 aut | |
| 700 | 1 | |a Gao, Xinbo |e verfasserin |4 aut | |
| 700 | 1 | |a Xiao, Bin |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t IEEE journal of biomedical and health informatics |d 2013 |g 26(2022), 5 vom: 01. Mai, Seite 2228-2239 |w (DE-627)NLM217081614 |x 2168-2208 |7 nnns |
| 773 | 1 | 8 | |g volume:26 |g year:2022 |g number:5 |g day:01 |g month:05 |g pages:2228-2239 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1109/JBHI.2021.3131758 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 26 |j 2022 |e 5 |b 01 |c 05 |h 2228-2239 | ||