Multi-Source Domain Adaptation for Medical Image Segmentation
Unsupervised domain adaptation(UDA) aims to mitigate the performance drop of models tested on the target domain, due to the domain shift from the target to sources. Most UDA segmentation methods focus on the scenario of solely single source domain. However, in practical situations data with gold standard could be available from multiple sources (domains), and the multi-source training data could provide more information for knowledge transfer. How to utilize them to achieve better domain adaptation yet remains to be further explored. This work investigates multi-source UDA and proposes a new framework for medical image segmentation. Firstly, we employ a multi-level adversarial learning scheme to adapt features at different levels between each of the source domains and the target, to improve the segmentation performance. Then, we propose a multi-model consistency loss to transfer the learned multi-source knowledge to the target domain simultaneously. Finally, we validated the proposed framework on two applications, i.e., multi-modality cardiac segmentation and cross-modality liver segmentation. The results showed our method delivered promising performance and compared favorably to state-of-the-art approaches.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2024 |
---|---|
Erschienen: |
2024 |
Enthalten in: |
Zur Gesamtaufnahme - volume:43 |
---|---|
Enthalten in: |
IEEE transactions on medical imaging - 43(2024), 4 vom: 22. Apr., Seite 1640-1651 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Pei, Chenhao [VerfasserIn] |
---|
Links: |
---|
Themen: |
---|
Anmerkungen: |
Date Completed 04.04.2024 Date Revised 04.04.2024 published: Print-Electronic Citation Status MEDLINE |
---|
doi: |
10.1109/TMI.2023.3346285 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM366246275 |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | NLM366246275 | ||
003 | DE-627 | ||
005 | 20240404234516.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231227s2024 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1109/TMI.2023.3346285 |2 doi | |
028 | 5 | 2 | |a pubmed24n1364.xml |
035 | |a (DE-627)NLM366246275 | ||
035 | |a (NLM)38133966 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Pei, Chenhao |e verfasserin |4 aut | |
245 | 1 | 0 | |a Multi-Source Domain Adaptation for Medical Image Segmentation |
264 | 1 | |c 2024 | |
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 04.04.2024 | ||
500 | |a Date Revised 04.04.2024 | ||
500 | |a published: Print-Electronic | ||
500 | |a Citation Status MEDLINE | ||
520 | |a Unsupervised domain adaptation(UDA) aims to mitigate the performance drop of models tested on the target domain, due to the domain shift from the target to sources. Most UDA segmentation methods focus on the scenario of solely single source domain. However, in practical situations data with gold standard could be available from multiple sources (domains), and the multi-source training data could provide more information for knowledge transfer. How to utilize them to achieve better domain adaptation yet remains to be further explored. This work investigates multi-source UDA and proposes a new framework for medical image segmentation. Firstly, we employ a multi-level adversarial learning scheme to adapt features at different levels between each of the source domains and the target, to improve the segmentation performance. Then, we propose a multi-model consistency loss to transfer the learned multi-source knowledge to the target domain simultaneously. Finally, we validated the proposed framework on two applications, i.e., multi-modality cardiac segmentation and cross-modality liver segmentation. The results showed our method delivered promising performance and compared favorably to state-of-the-art approaches | ||
650 | 4 | |a Journal Article | |
700 | 1 | |a Wu, Fuping |e verfasserin |4 aut | |
700 | 1 | |a Yang, Mingjing |e verfasserin |4 aut | |
700 | 1 | |a Pan, Lin |e verfasserin |4 aut | |
700 | 1 | |a Ding, Wangbin |e verfasserin |4 aut | |
700 | 1 | |a Dong, Jinwei |e verfasserin |4 aut | |
700 | 1 | |a Huang, Liqin |e verfasserin |4 aut | |
700 | 1 | |a Zhuang, Xiahai |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t IEEE transactions on medical imaging |d 1982 |g 43(2024), 4 vom: 22. Apr., Seite 1640-1651 |w (DE-627)NLM082855269 |x 1558-254X |7 nnns |
773 | 1 | 8 | |g volume:43 |g year:2024 |g number:4 |g day:22 |g month:04 |g pages:1640-1651 |
856 | 4 | 0 | |u http://dx.doi.org/10.1109/TMI.2023.3346285 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 43 |j 2024 |e 4 |b 22 |c 04 |h 1640-1651 |