EPolar-UNet : An edge-attending polar UNet for automatic medical image segmentation with small datasets
© 2024 American Association of Physicists in Medicine..
BACKGROUND: Medical image segmentation is one of the most key steps in computer-aided clinical diagnosis, geometric characterization, measurement, image registration, and so forth. Convolutional neural networks especially UNet and its variants have been successfully used in many medical image segmentation tasks. However, the results are limited by the deficiency in extracting high resolution edge information because of the design of the skip connections in UNet and the need for large available datasets.
PURPOSE: In this paper, we proposed an edge-attending polar UNet (EPolar-UNet), which was trained on the polar coordinate system instead of classic Cartesian coordinate system with an edge-attending construction in skip connection path.
METHODS: EPolar-UNet extracted the location information from an eight-stacked hourglass network as the pole for polar transformation and extracted the boundary cues from an edge-attending UNet, which consisted of a deconvolution layer and a subtraction operation.
RESULTS: We evaluated the performance of EPolar-UNet across three imaging modalities for different segmentation tasks: CVC-ClinicDB dataset for polyp, ISIC-2018 dataset for skin lesion, and our private ultrasound dataset for liver tumor segmentation. Our proposed model outperformed state-of-the-art models on all three datasets and needed only 30%-60% of training data compared with the benchmark UNet model to achieve similar performances for medical image segmentation tasks.
CONCLUSIONS: We proposed an end-to-end EPolar-UNet for automatic medical image segmentation and showed good performance on small datasets, which was critical in the field of medical image segmentation.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2024 |
|---|---|
| Erschienen: |
2024 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:51 |
|---|---|
| Enthalten in: |
Medical physics - 51(2024), 3 vom: 31. März, Seite 1702-1713 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Ling, Yating [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Edge-attending |
|---|
| Anmerkungen: |
Date Completed 13.03.2024 Date Revised 13.03.2024 published: Print-Electronic Citation Status MEDLINE |
|---|
| doi: |
10.1002/mp.16957 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM367886723 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM367886723 | ||
| 003 | DE-627 | ||
| 005 | 20240313234203.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 240201s2024 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1002/mp.16957 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1326.xml |
| 035 | |a (DE-627)NLM367886723 | ||
| 035 | |a (NLM)38299370 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Ling, Yating |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a EPolar-UNet |b An edge-attending polar UNet for automatic medical image segmentation with small datasets |
| 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 13.03.2024 | ||
| 500 | |a Date Revised 13.03.2024 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a © 2024 American Association of Physicists in Medicine. | ||
| 520 | |a BACKGROUND: Medical image segmentation is one of the most key steps in computer-aided clinical diagnosis, geometric characterization, measurement, image registration, and so forth. Convolutional neural networks especially UNet and its variants have been successfully used in many medical image segmentation tasks. However, the results are limited by the deficiency in extracting high resolution edge information because of the design of the skip connections in UNet and the need for large available datasets | ||
| 520 | |a PURPOSE: In this paper, we proposed an edge-attending polar UNet (EPolar-UNet), which was trained on the polar coordinate system instead of classic Cartesian coordinate system with an edge-attending construction in skip connection path | ||
| 520 | |a METHODS: EPolar-UNet extracted the location information from an eight-stacked hourglass network as the pole for polar transformation and extracted the boundary cues from an edge-attending UNet, which consisted of a deconvolution layer and a subtraction operation | ||
| 520 | |a RESULTS: We evaluated the performance of EPolar-UNet across three imaging modalities for different segmentation tasks: CVC-ClinicDB dataset for polyp, ISIC-2018 dataset for skin lesion, and our private ultrasound dataset for liver tumor segmentation. Our proposed model outperformed state-of-the-art models on all three datasets and needed only 30%-60% of training data compared with the benchmark UNet model to achieve similar performances for medical image segmentation tasks | ||
| 520 | |a CONCLUSIONS: We proposed an end-to-end EPolar-UNet for automatic medical image segmentation and showed good performance on small datasets, which was critical in the field of medical image segmentation | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a edge-attending | |
| 650 | 4 | |a polar transformation | |
| 650 | 4 | |a segmentation | |
| 700 | 1 | |a Wang, Yuling |e verfasserin |4 aut | |
| 700 | 1 | |a Liu, Qian |e verfasserin |4 aut | |
| 700 | 1 | |a Yu, Jie |e verfasserin |4 aut | |
| 700 | 1 | |a Xu, Lei |e verfasserin |4 aut | |
| 700 | 1 | |a Zhang, Xiaoqian |e verfasserin |4 aut | |
| 700 | 1 | |a Liang, Ping |e verfasserin |4 aut | |
| 700 | 1 | |a Kong, Dexing |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Medical physics |d 1974 |g 51(2024), 3 vom: 31. März, Seite 1702-1713 |w (DE-627)NLM000294748 |x 2473-4209 |7 nnns |
| 773 | 1 | 8 | |g volume:51 |g year:2024 |g number:3 |g day:31 |g month:03 |g pages:1702-1713 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1002/mp.16957 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 51 |j 2024 |e 3 |b 31 |c 03 |h 1702-1713 | ||