Consistency label-activated region generating network for weakly supervised medical image segmentation
Copyright © 2024 Elsevier Ltd. All rights reserved..
The current methods of auto-segmenting medical images are limited due to insufficient and ambiguous pathonmorphological labeling. In clinical practice, rough classification labels (such as disease or normal) are more commonly used than precise segmentation masks. However, there is still much to be explored regarding utilizing these weak clinical labels to accurately determine the lesion mask and guide medical image segmentation. In this paper, we proposed a weakly supervised medical image segmentation model to directly generate the lesion mask through a class activation map (CAM) guided cycle-consistency label-activated region transferring network. Cycle-consistency enforces that the mappings between the two domains should be reversible, which ensures that the original image can be reconstructed from the translated image. We developed a complementary branches fusion module to address the issue of blurry boundaries in CAM-guided segmentation. The complementary branch preserves the original semantic information of the non-lesion region and perfectly fuses the transferred feature of the lesion region with a complementary mask-constrained fake image generation process to clear the boundary of the lesion and non-lesion regions. This module allows the class transformation to focus solely on the label-activated region, resulting in more explicit segmentation. This model can accurately identify different region of medical images at the pixel-level while preserving the overall semantic structure semantion. It organizes disease labels and corresponding regions during image synthesis. Our method utilizes a joint discrimination strategy that significantly enhances the precision of the produced lesion mask. Extensive experiments of the proposed method on BraTs, ISIC and COVID-19 datasets demonstrate superior performance over existing state-of-the-art methods. The code and datasets are available at: https://github.com/mlcb-jlu/MedImgSeg.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2024 |
---|---|
Erschienen: |
2024 |
Enthalten in: |
Zur Gesamtaufnahme - volume:173 |
---|---|
Enthalten in: |
Computers in biology and medicine - 173(2024) vom: 20. Apr., Seite 108380 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Du, Wei [VerfasserIn] |
---|
Links: |
---|
Themen: |
Cycle consistency |
---|
Anmerkungen: |
Date Completed 17.04.2024 Date Revised 17.04.2024 published: Print-Electronic Citation Status MEDLINE |
---|
doi: |
10.1016/j.compbiomed.2024.108380 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM370452232 |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | NLM370452232 | ||
003 | DE-627 | ||
005 | 20240417232822.0 | ||
007 | cr uuu---uuuuu | ||
008 | 240401s2024 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1016/j.compbiomed.2024.108380 |2 doi | |
028 | 5 | 2 | |a pubmed24n1378.xml |
035 | |a (DE-627)NLM370452232 | ||
035 | |a (NLM)38555701 | ||
035 | |a (PII)S0010-4825(24)00464-5 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Du, Wei |e verfasserin |4 aut | |
245 | 1 | 0 | |a Consistency label-activated region generating network for weakly supervised 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 17.04.2024 | ||
500 | |a Date Revised 17.04.2024 | ||
500 | |a published: Print-Electronic | ||
500 | |a Citation Status MEDLINE | ||
520 | |a Copyright © 2024 Elsevier Ltd. All rights reserved. | ||
520 | |a The current methods of auto-segmenting medical images are limited due to insufficient and ambiguous pathonmorphological labeling. In clinical practice, rough classification labels (such as disease or normal) are more commonly used than precise segmentation masks. However, there is still much to be explored regarding utilizing these weak clinical labels to accurately determine the lesion mask and guide medical image segmentation. In this paper, we proposed a weakly supervised medical image segmentation model to directly generate the lesion mask through a class activation map (CAM) guided cycle-consistency label-activated region transferring network. Cycle-consistency enforces that the mappings between the two domains should be reversible, which ensures that the original image can be reconstructed from the translated image. We developed a complementary branches fusion module to address the issue of blurry boundaries in CAM-guided segmentation. The complementary branch preserves the original semantic information of the non-lesion region and perfectly fuses the transferred feature of the lesion region with a complementary mask-constrained fake image generation process to clear the boundary of the lesion and non-lesion regions. This module allows the class transformation to focus solely on the label-activated region, resulting in more explicit segmentation. This model can accurately identify different region of medical images at the pixel-level while preserving the overall semantic structure semantion. It organizes disease labels and corresponding regions during image synthesis. Our method utilizes a joint discrimination strategy that significantly enhances the precision of the produced lesion mask. Extensive experiments of the proposed method on BraTs, ISIC and COVID-19 datasets demonstrate superior performance over existing state-of-the-art methods. The code and datasets are available at: https://github.com/mlcb-jlu/MedImgSeg | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a Cycle consistency | |
650 | 4 | |a Deep generative mode | |
650 | 4 | |a Label-activated region transferring | |
650 | 4 | |a Medical image segmentation | |
650 | 4 | |a Weakly supervised | |
700 | 1 | |a Huo, Yongkang |e verfasserin |4 aut | |
700 | 1 | |a Zhou, Rixin |e verfasserin |4 aut | |
700 | 1 | |a Sun, Yu |e verfasserin |4 aut | |
700 | 1 | |a Tang, Shiyi |e verfasserin |4 aut | |
700 | 1 | |a Zhao, Xuan |e verfasserin |4 aut | |
700 | 1 | |a Li, Ying |e verfasserin |4 aut | |
700 | 1 | |a Li, Gaoyang |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Computers in biology and medicine |d 1970 |g 173(2024) vom: 20. Apr., Seite 108380 |w (DE-627)NLM000382272 |x 1879-0534 |7 nnns |
773 | 1 | 8 | |g volume:173 |g year:2024 |g day:20 |g month:04 |g pages:108380 |
856 | 4 | 0 | |u http://dx.doi.org/10.1016/j.compbiomed.2024.108380 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 173 |j 2024 |b 20 |c 04 |h 108380 |