Semi-Supervised 3D Medical Image Segmentation Based on Dual-Task Consistent Joint Learning and Task-Level Regularization
Semi-supervised learning has attracted wide attention from many researchers since its ability to utilize a few data with labels and relatively more data without labels to learn information. Some existing semi-supervised methods for medical image segmentation enforce the regularization of training by implicitly perturbing data or networks to perform the consistency. Most consistency regularization methods focus on data level or network structure level, and rarely of them focus on the task level. It may not directly lead to an improvement in task accuracy. To overcome the problem, this work proposes a semi-supervised dual-task consistent joint learning framework with task-level regularization for 3D medical image segmentation. Two branches are utilized to simultaneously predict the segmented and signed distance maps, and they can learn useful information from each other by constructing a consistency loss function between the two tasks. The segmentation branch learns rich information from both labeled and unlabeled data to strengthen the constraints on the geometric structure of the target. Experimental results on two benchmark datasets show that the proposed method can achieve better performance compared with other state-of-the-art works. It illustrates our method improves segmentation performance by utilizing unlabeled data and consistent regularization.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2023 |
|---|---|
| Erschienen: |
2023 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:20 |
|---|---|
| Enthalten in: |
IEEE/ACM transactions on computational biology and bioinformatics - 20(2023), 4 vom: 15. Juli, Seite 2457-2467 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Chen, Qi-Qi [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
|---|
| Anmerkungen: |
Date Revised 10.08.2023 published: Print-Electronic Citation Status PubMed-not-MEDLINE |
|---|
| doi: |
10.1109/TCBB.2022.3144428 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM335961932 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM335961932 | ||
| 003 | DE-627 | ||
| 005 | 20231225231042.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231225s2023 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1109/TCBB.2022.3144428 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1119.xml |
| 035 | |a (DE-627)NLM335961932 | ||
| 035 | |a (NLM)35061590 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Chen, Qi-Qi |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Semi-Supervised 3D Medical Image Segmentation Based on Dual-Task Consistent Joint Learning and Task-Level Regularization |
| 264 | 1 | |c 2023 | |
| 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 Revised 10.08.2023 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status PubMed-not-MEDLINE | ||
| 520 | |a Semi-supervised learning has attracted wide attention from many researchers since its ability to utilize a few data with labels and relatively more data without labels to learn information. Some existing semi-supervised methods for medical image segmentation enforce the regularization of training by implicitly perturbing data or networks to perform the consistency. Most consistency regularization methods focus on data level or network structure level, and rarely of them focus on the task level. It may not directly lead to an improvement in task accuracy. To overcome the problem, this work proposes a semi-supervised dual-task consistent joint learning framework with task-level regularization for 3D medical image segmentation. Two branches are utilized to simultaneously predict the segmented and signed distance maps, and they can learn useful information from each other by constructing a consistency loss function between the two tasks. The segmentation branch learns rich information from both labeled and unlabeled data to strengthen the constraints on the geometric structure of the target. Experimental results on two benchmark datasets show that the proposed method can achieve better performance compared with other state-of-the-art works. It illustrates our method improves segmentation performance by utilizing unlabeled data and consistent regularization | ||
| 650 | 4 | |a Journal Article | |
| 700 | 1 | |a Sun, Zhao-Hui |e verfasserin |4 aut | |
| 700 | 1 | |a Wei, Chuan-Feng |e verfasserin |4 aut | |
| 700 | 1 | |a Wu, Edmond Q |e verfasserin |4 aut | |
| 700 | 1 | |a Ming, Dong |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t IEEE/ACM transactions on computational biology and bioinformatics |d 2004 |g 20(2023), 4 vom: 15. Juli, Seite 2457-2467 |w (DE-627)NLM16601530X |x 1557-9964 |7 nnns |
| 773 | 1 | 8 | |g volume:20 |g year:2023 |g number:4 |g day:15 |g month:07 |g pages:2457-2467 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1109/TCBB.2022.3144428 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 20 |j 2023 |e 4 |b 15 |c 07 |h 2457-2467 | ||