Mamba- and ResNet-Based Dual-Branch Network for Ultrasound Thyroid Nodule Segmentation
Accurate segmentation of thyroid nodules in ultrasound images is crucial for the diagnosis of thyroid cancer and preoperative planning. However, the segmentation of thyroid nodules is challenging due to their irregular shape, blurred boundary, and uneven echo texture. To address these challenges, a...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-10-01
|
| Series: | Bioengineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2306-5354/11/10/1047 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850204902552240128 |
|---|---|
| author | Min Hu Yaorong Zhang Huijun Xue Hao Lv Shipeng Han |
| author_facet | Min Hu Yaorong Zhang Huijun Xue Hao Lv Shipeng Han |
| author_sort | Min Hu |
| collection | DOAJ |
| description | Accurate segmentation of thyroid nodules in ultrasound images is crucial for the diagnosis of thyroid cancer and preoperative planning. However, the segmentation of thyroid nodules is challenging due to their irregular shape, blurred boundary, and uneven echo texture. To address these challenges, a novel Mamba- and ResNet-based dual-branch network (MRDB) is proposed. Specifically, the visual state space block (VSSB) from Mamba and ResNet-34 are utilized to construct a dual encoder for extracting global semantics and local details, and establishing multi-dimensional feature connections. Meanwhile, an upsampling–convolution strategy is employed in the left decoder focusing on image size and detail reconstruction. A convolution–upsampling strategy is used in the right decoder to emphasize gradual feature refinement and recovery. To facilitate the interaction between local details and global context within the encoder and decoder, cross-skip connection is introduced. Additionally, a novel hybrid loss function is proposed to improve the boundary segmentation performance of thyroid nodules. Experimental results show that MRDB outperforms the state-of-the-art approaches with DSC of 90.02% and 80.6% on two public thyroid nodule datasets, TN3K and TNUI-2021, respectively. Furthermore, experiments on a third external dataset, DDTI, demonstrate that our method improves the DSC by 10.8% compared to baseline and exhibits good generalization to clinical small-scale thyroid nodule datasets. The proposed MRDB can effectively improve thyroid nodule segmentation accuracy and has great potential for clinical applications. |
| format | Article |
| id | doaj-art-e306f9388e7f4e2c86af133742534c81 |
| institution | OA Journals |
| issn | 2306-5354 |
| language | English |
| publishDate | 2024-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Bioengineering |
| spelling | doaj-art-e306f9388e7f4e2c86af133742534c812025-08-20T02:11:12ZengMDPI AGBioengineering2306-53542024-10-011110104710.3390/bioengineering11101047Mamba- and ResNet-Based Dual-Branch Network for Ultrasound Thyroid Nodule SegmentationMin Hu0Yaorong Zhang1Huijun Xue2Hao Lv3Shipeng Han4Department of Medical Electronics, School of Biomedical Engineering, Air Force Medical University, Xi’an 710032, ChinaDepartment of Medical Electronics, School of Biomedical Engineering, Air Force Medical University, Xi’an 710032, ChinaDepartment of Medical Electronics, School of Biomedical Engineering, Air Force Medical University, Xi’an 710032, ChinaDepartment of Medical Electronics, School of Biomedical Engineering, Air Force Medical University, Xi’an 710032, ChinaDepartment of Medical Electronics, School of Biomedical Engineering, Air Force Medical University, Xi’an 710032, ChinaAccurate segmentation of thyroid nodules in ultrasound images is crucial for the diagnosis of thyroid cancer and preoperative planning. However, the segmentation of thyroid nodules is challenging due to their irregular shape, blurred boundary, and uneven echo texture. To address these challenges, a novel Mamba- and ResNet-based dual-branch network (MRDB) is proposed. Specifically, the visual state space block (VSSB) from Mamba and ResNet-34 are utilized to construct a dual encoder for extracting global semantics and local details, and establishing multi-dimensional feature connections. Meanwhile, an upsampling–convolution strategy is employed in the left decoder focusing on image size and detail reconstruction. A convolution–upsampling strategy is used in the right decoder to emphasize gradual feature refinement and recovery. To facilitate the interaction between local details and global context within the encoder and decoder, cross-skip connection is introduced. Additionally, a novel hybrid loss function is proposed to improve the boundary segmentation performance of thyroid nodules. Experimental results show that MRDB outperforms the state-of-the-art approaches with DSC of 90.02% and 80.6% on two public thyroid nodule datasets, TN3K and TNUI-2021, respectively. Furthermore, experiments on a third external dataset, DDTI, demonstrate that our method improves the DSC by 10.8% compared to baseline and exhibits good generalization to clinical small-scale thyroid nodule datasets. The proposed MRDB can effectively improve thyroid nodule segmentation accuracy and has great potential for clinical applications.https://www.mdpi.com/2306-5354/11/10/1047thyroid nodulevisual MambaResNetultrasound image segmentation |
| spellingShingle | Min Hu Yaorong Zhang Huijun Xue Hao Lv Shipeng Han Mamba- and ResNet-Based Dual-Branch Network for Ultrasound Thyroid Nodule Segmentation Bioengineering thyroid nodule visual Mamba ResNet ultrasound image segmentation |
| title | Mamba- and ResNet-Based Dual-Branch Network for Ultrasound Thyroid Nodule Segmentation |
| title_full | Mamba- and ResNet-Based Dual-Branch Network for Ultrasound Thyroid Nodule Segmentation |
| title_fullStr | Mamba- and ResNet-Based Dual-Branch Network for Ultrasound Thyroid Nodule Segmentation |
| title_full_unstemmed | Mamba- and ResNet-Based Dual-Branch Network for Ultrasound Thyroid Nodule Segmentation |
| title_short | Mamba- and ResNet-Based Dual-Branch Network for Ultrasound Thyroid Nodule Segmentation |
| title_sort | mamba and resnet based dual branch network for ultrasound thyroid nodule segmentation |
| topic | thyroid nodule visual Mamba ResNet ultrasound image segmentation |
| url | https://www.mdpi.com/2306-5354/11/10/1047 |
| work_keys_str_mv | AT minhu mambaandresnetbaseddualbranchnetworkforultrasoundthyroidnodulesegmentation AT yaorongzhang mambaandresnetbaseddualbranchnetworkforultrasoundthyroidnodulesegmentation AT huijunxue mambaandresnetbaseddualbranchnetworkforultrasoundthyroidnodulesegmentation AT haolv mambaandresnetbaseddualbranchnetworkforultrasoundthyroidnodulesegmentation AT shipenghan mambaandresnetbaseddualbranchnetworkforultrasoundthyroidnodulesegmentation |