Federated Semi-Supervised Medical Image Segmentation via Prototype-Based Pseudo-Labeling and Contrastive Learning
Existing federated learning works mainly focus on the fully supervised training setting. In realistic scenarios, however, most clinical sites can only provide data without annotations due to the lack of resources or expertise. In this work, we are concerned with the practical yet challenging federated semi-supervised segmentation (FSSS), where labeled data are only with several clients and other clients can just provide unlabeled data. We take an early attempt to tackle this problem and propose a novel FSSS method with prototype-based pseudo-labeling and contrastive learning. First, we transmit a labeled-aggregated model, which is obtained based on prototype similarity, to each unlabeled client, to work together with the global model for debiased pseudo labels generation via a consistency- and entropy-aware selection strategy. Second, we transfer image-level prototypes from labeled datasets to unlabeled clients and conduct prototypical contrastive learning on unlabeled models to enhance their discriminative power. Finally, we perform the dynamic model aggregation with a designed consistency-aware aggregation strategy to dynamically adjust the aggregation weights of each local model. We evaluate our method on COVID-19 X-ray infected region segmentation, COVID-19 CT infected region segmentation and colorectal polyp segmentation, and experimental results consistently demonstrate the effectiveness of our proposed method. Codes areavailable at https://github.com/zhangbaiming/FedSemiSeg.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2024 |
|---|---|
| Erschienen: |
2024 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:43 |
|---|---|
| Enthalten in: |
IEEE transactions on medical imaging - 43(2024), 2 vom: 01. Feb., Seite 649-661 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Wu, Huisi [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
|---|
| Anmerkungen: |
Date Completed 05.02.2024 Date Revised 05.02.2024 published: Print-Electronic Citation Status MEDLINE |
|---|
| doi: |
10.1109/TMI.2023.3314430 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM362004609 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM362004609 | ||
| 003 | DE-627 | ||
| 005 | 20240205231855.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231226s2024 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1109/TMI.2023.3314430 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1281.xml |
| 035 | |a (DE-627)NLM362004609 | ||
| 035 | |a (NLM)37703140 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Wu, Huisi |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Federated Semi-Supervised Medical Image Segmentation via Prototype-Based Pseudo-Labeling and Contrastive Learning |
| 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 05.02.2024 | ||
| 500 | |a Date Revised 05.02.2024 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a Existing federated learning works mainly focus on the fully supervised training setting. In realistic scenarios, however, most clinical sites can only provide data without annotations due to the lack of resources or expertise. In this work, we are concerned with the practical yet challenging federated semi-supervised segmentation (FSSS), where labeled data are only with several clients and other clients can just provide unlabeled data. We take an early attempt to tackle this problem and propose a novel FSSS method with prototype-based pseudo-labeling and contrastive learning. First, we transmit a labeled-aggregated model, which is obtained based on prototype similarity, to each unlabeled client, to work together with the global model for debiased pseudo labels generation via a consistency- and entropy-aware selection strategy. Second, we transfer image-level prototypes from labeled datasets to unlabeled clients and conduct prototypical contrastive learning on unlabeled models to enhance their discriminative power. Finally, we perform the dynamic model aggregation with a designed consistency-aware aggregation strategy to dynamically adjust the aggregation weights of each local model. We evaluate our method on COVID-19 X-ray infected region segmentation, COVID-19 CT infected region segmentation and colorectal polyp segmentation, and experimental results consistently demonstrate the effectiveness of our proposed method. Codes areavailable at https://github.com/zhangbaiming/FedSemiSeg | ||
| 650 | 4 | |a Journal Article | |
| 700 | 1 | |a Zhang, Baiming |e verfasserin |4 aut | |
| 700 | 1 | |a Chen, Cheng |e verfasserin |4 aut | |
| 700 | 1 | |a Qin, Jing |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t IEEE transactions on medical imaging |d 1982 |g 43(2024), 2 vom: 01. Feb., Seite 649-661 |w (DE-627)NLM082855269 |x 1558-254X |7 nnns |
| 773 | 1 | 8 | |g volume:43 |g year:2024 |g number:2 |g day:01 |g month:02 |g pages:649-661 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1109/TMI.2023.3314430 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 43 |j 2024 |e 2 |b 01 |c 02 |h 649-661 | ||