Correcting and reweighting false label masks in brain tumor segmentation
© 2020 American Association of Physicists in Medicine..
PURPOSE: Recently, brain tumor segmentation has made important progress. However, the quality of manual labels plays an important role in the performance, while in practice, it could vary greatly and in turn could substantially mislead the learning process and decrease the accuracy. We need to design a mechanism to combine label correction and sample reweighting to improve the effectiveness of brain tumor segmentation.
METHODS: We propose a novel sample reweighting and label refinement method, and a novel three-dimensional (3D) generative adversarial network (GAN) is introduced to combine these two models into an united framework.
RESULTS: Extensive experiments on the BraTS19 dataset have demonstrated that our approach obtains competitive results when compared with other state-of-the-art approaches when handling the false labels in brain tumor segmentation.
CONCLUSIONS: The 3D GAN-based approach is an effective approach to handle false label masks by simultaneously applying label correction and sample reweighting. Our method is robust to variations in tumor shape and background clutter.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2021 |
|---|---|
| Erschienen: |
2021 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:48 |
|---|---|
| Enthalten in: |
Medical physics - 48(2021), 1 vom: 30. Jan., Seite 169-177 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Cheng, Guohua [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Brain tumor segmentation |
|---|
| Anmerkungen: |
Date Completed 30.04.2021 Date Revised 30.04.2021 published: Print-Electronic Citation Status MEDLINE |
|---|
| doi: |
10.1002/mp.14480 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM315457015 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM315457015 | ||
| 003 | DE-627 | ||
| 005 | 20231225154944.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231225s2021 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1002/mp.14480 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1051.xml |
| 035 | |a (DE-627)NLM315457015 | ||
| 035 | |a (NLM)32974920 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Cheng, Guohua |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Correcting and reweighting false label masks in brain tumor segmentation |
| 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 30.04.2021 | ||
| 500 | |a Date Revised 30.04.2021 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a © 2020 American Association of Physicists in Medicine. | ||
| 520 | |a PURPOSE: Recently, brain tumor segmentation has made important progress. However, the quality of manual labels plays an important role in the performance, while in practice, it could vary greatly and in turn could substantially mislead the learning process and decrease the accuracy. We need to design a mechanism to combine label correction and sample reweighting to improve the effectiveness of brain tumor segmentation | ||
| 520 | |a METHODS: We propose a novel sample reweighting and label refinement method, and a novel three-dimensional (3D) generative adversarial network (GAN) is introduced to combine these two models into an united framework | ||
| 520 | |a RESULTS: Extensive experiments on the BraTS19 dataset have demonstrated that our approach obtains competitive results when compared with other state-of-the-art approaches when handling the false labels in brain tumor segmentation | ||
| 520 | |a CONCLUSIONS: The 3D GAN-based approach is an effective approach to handle false label masks by simultaneously applying label correction and sample reweighting. Our method is robust to variations in tumor shape and background clutter | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a brain tumor segmentation | |
| 650 | 4 | |a deep learning | |
| 650 | 4 | |a generative adversarial network | |
| 650 | 4 | |a volume segmentation | |
| 700 | 1 | |a Ji, Hongli |e verfasserin |4 aut | |
| 700 | 1 | |a He, Linyang |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Medical physics |d 1974 |g 48(2021), 1 vom: 30. Jan., Seite 169-177 |w (DE-627)NLM000294748 |x 2473-4209 |7 nnns |
| 773 | 1 | 8 | |g volume:48 |g year:2021 |g number:1 |g day:30 |g month:01 |g pages:169-177 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1002/mp.14480 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 48 |j 2021 |e 1 |b 30 |c 01 |h 169-177 | ||