A lightweight hierarchical convolution network for brain tumor segmentation
Abstract Background Brain tumor segmentation plays a significant role in clinical treatment and surgical planning. Recently, several deep convolutional networks have been proposed for brain tumor segmentation and have achieved impressive performance. However, most state-of-the-art models use 3D conv...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2022-12-01
|
| Series: | BMC Bioinformatics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12859-022-05039-5 |
| _version_ | 1811196669696409600 |
|---|---|
| author | Yuhu Wang Yuzhen Cao Jinqiu Li Hongtao Wu Shuo Wang Xinming Dong Hui Yu |
| author_facet | Yuhu Wang Yuzhen Cao Jinqiu Li Hongtao Wu Shuo Wang Xinming Dong Hui Yu |
| author_sort | Yuhu Wang |
| collection | DOAJ |
| description | Abstract Background Brain tumor segmentation plays a significant role in clinical treatment and surgical planning. Recently, several deep convolutional networks have been proposed for brain tumor segmentation and have achieved impressive performance. However, most state-of-the-art models use 3D convolution networks, which require high computational costs. This makes it difficult to apply these models to medical equipment in the future. Additionally, due to the large diversity of the brain tumor and uncertain boundaries between sub-regions, some models cannot well-segment multiple tumors in the brain at the same time. Results In this paper, we proposed a lightweight hierarchical convolution network, called LHC-Net. Our network uses a multi-scale strategy which the common 3D convolution is replaced by the hierarchical convolution with residual-like connections. It improves the ability of multi-scale feature extraction and greatly reduces parameters and computation resources. On the BraTS2020 dataset, LHC-Net achieves the Dice scores of 76.38%, 90.01% and 83.32% for ET, WT and TC, respectively, which is better than that of 3D U-Net with 73.50%, 89.42% and 81.92%. Especially on the multi-tumor set, our model shows significant performance improvement. In addition, LHC-Net has 1.65M parameters and 35.58G FLOPs, which is two times fewer parameters and three times less computation compared with 3D U-Net. Conclusion Our proposed method achieves automatic segmentation of tumor sub-regions from four-modal brain MRI images. LHC-Net achieves competitive segmentation performance with fewer parameters and less computation than the state-of-the-art models. It means that our model can be applied under limited medical computing resources. By using the multi-scale strategy on channels, LHC-Net can well-segment multiple tumors in the patient’s brain. It has great potential for application to other multi-scale segmentation tasks. |
| first_indexed | 2024-04-12T01:01:44Z |
| format | Article |
| id | doaj.art-e6efe4b41b414a2383cf9e031aa7df2a |
| institution | Directory Open Access Journal |
| issn | 1471-2105 |
| language | English |
| last_indexed | 2024-04-12T01:01:44Z |
| publishDate | 2022-12-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Bioinformatics |
| spelling | doaj.art-e6efe4b41b414a2383cf9e031aa7df2a2022-12-22T03:54:25ZengBMCBMC Bioinformatics1471-21052022-12-0122S511810.1186/s12859-022-05039-5A lightweight hierarchical convolution network for brain tumor segmentationYuhu Wang0Yuzhen Cao1Jinqiu Li2Hongtao Wu3Shuo Wang4Xinming Dong5Hui Yu6Tianjin International Engineering Institute, Tianjin UniversityDepartment of Biomedical Engineering, Tianjin Key Laboratory of Biomedical Detecting Techniques and Instruments, Tianjin UniversityTianjin International Engineering Institute, Tianjin UniversityDepartment of Biomedical Engineering, Tianjin Key Laboratory of Biomedical Detecting Techniques and Instruments, Tianjin UniversityDepartment of Biomedical Engineering, Tianjin Key Laboratory of Biomedical Detecting Techniques and Instruments, Tianjin UniversityTianjin Rehabilitation Convalescent CenterDepartment of Biomedical Engineering, Tianjin Key Laboratory of Biomedical Detecting Techniques and Instruments, Tianjin UniversityAbstract Background Brain tumor segmentation plays a significant role in clinical treatment and surgical planning. Recently, several deep convolutional networks have been proposed for brain tumor segmentation and have achieved impressive performance. However, most state-of-the-art models use 3D convolution networks, which require high computational costs. This makes it difficult to apply these models to medical equipment in the future. Additionally, due to the large diversity of the brain tumor and uncertain boundaries between sub-regions, some models cannot well-segment multiple tumors in the brain at the same time. Results In this paper, we proposed a lightweight hierarchical convolution network, called LHC-Net. Our network uses a multi-scale strategy which the common 3D convolution is replaced by the hierarchical convolution with residual-like connections. It improves the ability of multi-scale feature extraction and greatly reduces parameters and computation resources. On the BraTS2020 dataset, LHC-Net achieves the Dice scores of 76.38%, 90.01% and 83.32% for ET, WT and TC, respectively, which is better than that of 3D U-Net with 73.50%, 89.42% and 81.92%. Especially on the multi-tumor set, our model shows significant performance improvement. In addition, LHC-Net has 1.65M parameters and 35.58G FLOPs, which is two times fewer parameters and three times less computation compared with 3D U-Net. Conclusion Our proposed method achieves automatic segmentation of tumor sub-regions from four-modal brain MRI images. LHC-Net achieves competitive segmentation performance with fewer parameters and less computation than the state-of-the-art models. It means that our model can be applied under limited medical computing resources. By using the multi-scale strategy on channels, LHC-Net can well-segment multiple tumors in the patient’s brain. It has great potential for application to other multi-scale segmentation tasks.https://doi.org/10.1186/s12859-022-05039-5Brain tumor segmentationLightweight networkDeep learningConvolutional neural network |
| spellingShingle | Yuhu Wang Yuzhen Cao Jinqiu Li Hongtao Wu Shuo Wang Xinming Dong Hui Yu A lightweight hierarchical convolution network for brain tumor segmentation BMC Bioinformatics Brain tumor segmentation Lightweight network Deep learning Convolutional neural network |
| title | A lightweight hierarchical convolution network for brain tumor segmentation |
| title_full | A lightweight hierarchical convolution network for brain tumor segmentation |
| title_fullStr | A lightweight hierarchical convolution network for brain tumor segmentation |
| title_full_unstemmed | A lightweight hierarchical convolution network for brain tumor segmentation |
| title_short | A lightweight hierarchical convolution network for brain tumor segmentation |
| title_sort | lightweight hierarchical convolution network for brain tumor segmentation |
| topic | Brain tumor segmentation Lightweight network Deep learning Convolutional neural network |
| url | https://doi.org/10.1186/s12859-022-05039-5 |
| work_keys_str_mv | AT yuhuwang alightweighthierarchicalconvolutionnetworkforbraintumorsegmentation AT yuzhencao alightweighthierarchicalconvolutionnetworkforbraintumorsegmentation AT jinqiuli alightweighthierarchicalconvolutionnetworkforbraintumorsegmentation AT hongtaowu alightweighthierarchicalconvolutionnetworkforbraintumorsegmentation AT shuowang alightweighthierarchicalconvolutionnetworkforbraintumorsegmentation AT xinmingdong alightweighthierarchicalconvolutionnetworkforbraintumorsegmentation AT huiyu alightweighthierarchicalconvolutionnetworkforbraintumorsegmentation AT yuhuwang lightweighthierarchicalconvolutionnetworkforbraintumorsegmentation AT yuzhencao lightweighthierarchicalconvolutionnetworkforbraintumorsegmentation AT jinqiuli lightweighthierarchicalconvolutionnetworkforbraintumorsegmentation AT hongtaowu lightweighthierarchicalconvolutionnetworkforbraintumorsegmentation AT shuowang lightweighthierarchicalconvolutionnetworkforbraintumorsegmentation AT xinmingdong lightweighthierarchicalconvolutionnetworkforbraintumorsegmentation AT huiyu lightweighthierarchicalconvolutionnetworkforbraintumorsegmentation |