Multi-scale channel attention U-Net: a novel framework for automated gallbladder segmentation in medical imaging
ObjectivesTo develop a novel automatic delineation model, the Multi-Scale Channel Attention U-Net (MCAU-Net) model, for gallbladder segmentation on CT images of patients with liver cancer.MethodsWe retrospectively collected the CT images from 120 patients with liver cancer, based on which ground tru...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Oncology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2025.1528654/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832583702039756800 |
|---|---|
| author | Yiming Zhou Xiaobo Wen Xiaobo Wen Kang Fu Meina Li Lin Sun Xiao Hu |
| author_facet | Yiming Zhou Xiaobo Wen Xiaobo Wen Kang Fu Meina Li Lin Sun Xiao Hu |
| author_sort | Yiming Zhou |
| collection | DOAJ |
| description | ObjectivesTo develop a novel automatic delineation model, the Multi-Scale Channel Attention U-Net (MCAU-Net) model, for gallbladder segmentation on CT images of patients with liver cancer.MethodsWe retrospectively collected the CT images from 120 patients with liver cancer, based on which ground truth was manually delineated by physicians. The images and ground truth constitute a dataset, which was proportionally divided into a training set (54%), a validation set (6%), and a test set (40%). Data augmentation was performed on the training set. Our proposed MCAU-Net model was employed for gallbladder segmentation and its performance was evaluated using Dice Similarity Coefficient (DSC), Jaccard Similarity Coefficient (JSC), Positive Predictive Value (PPV), Sensitivity (SE), Hausdorff Distance (HD), Relative Volume Difference (RVD), and Volumetric Overlap Error (VOE) metrics.ResultsOn the test set, MCAU-Net achieved DSC, JSC, PPV, SE, HD, RVD, and VOE values of 0.85 ± 0.22, 0.79 ± 0.23, 0.92 ± 0.14, 0.84 ± 0.23, 2.75 ± 0.98, 0.18 ± 0.48, and 0.22 ± 0.42, respectively. Compared to the control models, U-Net, SEU-Net and TransUNet, the MCAU-Net improved DSC 0.06, 0.04 and 0.06, JSC by 0.09, 0.06 and 0.09, PPV by 0.08, 0.08 and 0.05, SE by 0.05,0.05 and 0.07, and reduced HD by 0.45, 0.28 and 0.41, RVD by 0.07, 0.03 and 0.07, VOE by 0.04, 0.02 and 0.08 respectively. Qualitative results revealed that MCAU-Net produced smoother and more accurate boundaries, closer to the expert delineation, with less over-segmentation and under-segmentation and improved robustness.ConclusionsThe MCAU-Net model significantly improves gallbladder segmentation on CT images. It satisfies clinical requirements and enhances the efficiency of physicians, particularly in segmenting complex anatomical structures. |
| format | Article |
| id | doaj-art-21e27b3e3d404e04ac78f37c7c9072f0 |
| institution | Kabale University |
| issn | 2234-943X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Oncology |
| spelling | doaj-art-21e27b3e3d404e04ac78f37c7c9072f02025-01-28T06:41:19ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2025-01-011510.3389/fonc.2025.15286541528654Multi-scale channel attention U-Net: a novel framework for automated gallbladder segmentation in medical imagingYiming Zhou0Xiaobo Wen1Xiaobo Wen2Kang Fu3Meina Li4Lin Sun5Xiao Hu6Department of Hepatobiliary Pancreatic Surgery, The Affiliated Hospital of Medical College of Qingdao University, Qingdao, Shandong, ChinaSchool of Pharmacy, Qingdao University, Qingdao, ChinaQingdao Cancer Institute, Qingdao University, Qingdao, ChinaDepartment of Hepatobiliary Pancreatic Surgery, The Affiliated Hospital of Medical College of Qingdao University, Qingdao, Shandong, ChinaDepartment of Urology, Qingdao Municipal Hospital, Qingdao, Shandong, ChinaDepartment of ICU, The Affiliated Hospital of Qingdao University, Qingdao, Shandong, ChinaDepartment of Hepatobiliary Pancreatic Surgery, The Affiliated Hospital of Medical College of Qingdao University, Qingdao, Shandong, ChinaObjectivesTo develop a novel automatic delineation model, the Multi-Scale Channel Attention U-Net (MCAU-Net) model, for gallbladder segmentation on CT images of patients with liver cancer.MethodsWe retrospectively collected the CT images from 120 patients with liver cancer, based on which ground truth was manually delineated by physicians. The images and ground truth constitute a dataset, which was proportionally divided into a training set (54%), a validation set (6%), and a test set (40%). Data augmentation was performed on the training set. Our proposed MCAU-Net model was employed for gallbladder segmentation and its performance was evaluated using Dice Similarity Coefficient (DSC), Jaccard Similarity Coefficient (JSC), Positive Predictive Value (PPV), Sensitivity (SE), Hausdorff Distance (HD), Relative Volume Difference (RVD), and Volumetric Overlap Error (VOE) metrics.ResultsOn the test set, MCAU-Net achieved DSC, JSC, PPV, SE, HD, RVD, and VOE values of 0.85 ± 0.22, 0.79 ± 0.23, 0.92 ± 0.14, 0.84 ± 0.23, 2.75 ± 0.98, 0.18 ± 0.48, and 0.22 ± 0.42, respectively. Compared to the control models, U-Net, SEU-Net and TransUNet, the MCAU-Net improved DSC 0.06, 0.04 and 0.06, JSC by 0.09, 0.06 and 0.09, PPV by 0.08, 0.08 and 0.05, SE by 0.05,0.05 and 0.07, and reduced HD by 0.45, 0.28 and 0.41, RVD by 0.07, 0.03 and 0.07, VOE by 0.04, 0.02 and 0.08 respectively. Qualitative results revealed that MCAU-Net produced smoother and more accurate boundaries, closer to the expert delineation, with less over-segmentation and under-segmentation and improved robustness.ConclusionsThe MCAU-Net model significantly improves gallbladder segmentation on CT images. It satisfies clinical requirements and enhances the efficiency of physicians, particularly in segmenting complex anatomical structures.https://www.frontiersin.org/articles/10.3389/fonc.2025.1528654/fulldeep learningU-Netgallbladderautomatically delineatedmulti-scale channel attention |
| spellingShingle | Yiming Zhou Xiaobo Wen Xiaobo Wen Kang Fu Meina Li Lin Sun Xiao Hu Multi-scale channel attention U-Net: a novel framework for automated gallbladder segmentation in medical imaging Frontiers in Oncology deep learning U-Net gallbladder automatically delineated multi-scale channel attention |
| title | Multi-scale channel attention U-Net: a novel framework for automated gallbladder segmentation in medical imaging |
| title_full | Multi-scale channel attention U-Net: a novel framework for automated gallbladder segmentation in medical imaging |
| title_fullStr | Multi-scale channel attention U-Net: a novel framework for automated gallbladder segmentation in medical imaging |
| title_full_unstemmed | Multi-scale channel attention U-Net: a novel framework for automated gallbladder segmentation in medical imaging |
| title_short | Multi-scale channel attention U-Net: a novel framework for automated gallbladder segmentation in medical imaging |
| title_sort | multi scale channel attention u net a novel framework for automated gallbladder segmentation in medical imaging |
| topic | deep learning U-Net gallbladder automatically delineated multi-scale channel attention |
| url | https://www.frontiersin.org/articles/10.3389/fonc.2025.1528654/full |
| work_keys_str_mv | AT yimingzhou multiscalechannelattentionunetanovelframeworkforautomatedgallbladdersegmentationinmedicalimaging AT xiaobowen multiscalechannelattentionunetanovelframeworkforautomatedgallbladdersegmentationinmedicalimaging AT xiaobowen multiscalechannelattentionunetanovelframeworkforautomatedgallbladdersegmentationinmedicalimaging AT kangfu multiscalechannelattentionunetanovelframeworkforautomatedgallbladdersegmentationinmedicalimaging AT meinali multiscalechannelattentionunetanovelframeworkforautomatedgallbladdersegmentationinmedicalimaging AT linsun multiscalechannelattentionunetanovelframeworkforautomatedgallbladdersegmentationinmedicalimaging AT xiaohu multiscalechannelattentionunetanovelframeworkforautomatedgallbladdersegmentationinmedicalimaging |