DPC-MSGATNet: dual-path chain multi-scale gated axial-transformer network for four-chamber view segmentation in fetal echocardiography
Abstract Echocardiography is essential in evaluating fetal cardiac anatomical structures and functions when clinicians conduct early treatment and screening for congenital heart defects, a common and intricate fetal malformation. Nevertheless, the prenatal detection rate of fetal CHD remains low sin...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2023-01-01
|
| Series: | Complex & Intelligent Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s40747-023-00968-x |
| _version_ | 1797769266586451968 |
|---|---|
| author | Sibo Qiao Shanchen Pang Gang Luo Yi Sun Wenjing Yin Silin Pan Zhihan Lv |
| author_facet | Sibo Qiao Shanchen Pang Gang Luo Yi Sun Wenjing Yin Silin Pan Zhihan Lv |
| author_sort | Sibo Qiao |
| collection | DOAJ |
| description | Abstract Echocardiography is essential in evaluating fetal cardiac anatomical structures and functions when clinicians conduct early treatment and screening for congenital heart defects, a common and intricate fetal malformation. Nevertheless, the prenatal detection rate of fetal CHD remains low since the peculiarities of fetal cardiac structures and the variousness of fetal CHD. Precisely segmenting four cardiac chambers can assist clinicians in analyzing cardiac morphology and further facilitate CHD diagnosis. Hence, we design a dual-path chain multi-scale gated axial-transformer network (DPC-MSGATNet) that simultaneously models global dependencies and local visual cues for fetal ultrasound (US) four-chamber (FC) views and further accurately segments four chambers. Our DPC-MSGATNet includes a global and a local branch that simultaneously operates on an entire FC view and image patches to learn multi-scale representations. We design a plug-and-play module, Interactive dual-path chain gated axial-transformer (IDPCGAT), to enhance the interactions between global and local branches. In IDPCGAT, the multi-scale representations from the two branches can complement each other, capturing the same region’s salient features and suppressing feature responses to maintain only the activations associated with specific targets. Extensive experiments demonstrate that the DPC-MSGATNet exceeds seven state-of-the-art convolution- and transformer-based methods by a large margin in terms of F1 and IoU scores on our fetal FC view dataset, achieving a F1 score of 96.87 $$\%$$ % and an IoU score of 93.99 $$\%$$ % . The codes and datasets can be available at https://github.comQiaoSiBo/DPC-MSGATNet . |
| first_indexed | 2024-03-12T21:06:27Z |
| format | Article |
| id | doaj.art-e62d6c895bac4b249bc5baee3e3ac9d3 |
| institution | Directory Open Access Journal |
| issn | 2199-4536 2198-6053 |
| language | English |
| last_indexed | 2024-03-12T21:06:27Z |
| publishDate | 2023-01-01 |
| publisher | Springer |
| record_format | Article |
| series | Complex & Intelligent Systems |
| spelling | doaj.art-e62d6c895bac4b249bc5baee3e3ac9d32023-07-30T11:27:48ZengSpringerComplex & Intelligent Systems2199-45362198-60532023-01-01944503451910.1007/s40747-023-00968-xDPC-MSGATNet: dual-path chain multi-scale gated axial-transformer network for four-chamber view segmentation in fetal echocardiographySibo Qiao0Shanchen Pang1Gang Luo2Yi Sun3Wenjing Yin4Silin Pan5Zhihan Lv6The School of Computer Science and Technology, China University of PetroleumThe School of Computer Science and Technology, China University of PetroleumThe Heart Center, Qingdao Women and Children’s HospitalThe Heart Center, Qingdao Women and Children’s HospitalThe School of Computer Science and Technology, China University of PetroleumThe Heart Center, Qingdao Women and Children’s HospitalThe Department of Game Design Faculty of Arts, Uppsala UniversityAbstract Echocardiography is essential in evaluating fetal cardiac anatomical structures and functions when clinicians conduct early treatment and screening for congenital heart defects, a common and intricate fetal malformation. Nevertheless, the prenatal detection rate of fetal CHD remains low since the peculiarities of fetal cardiac structures and the variousness of fetal CHD. Precisely segmenting four cardiac chambers can assist clinicians in analyzing cardiac morphology and further facilitate CHD diagnosis. Hence, we design a dual-path chain multi-scale gated axial-transformer network (DPC-MSGATNet) that simultaneously models global dependencies and local visual cues for fetal ultrasound (US) four-chamber (FC) views and further accurately segments four chambers. Our DPC-MSGATNet includes a global and a local branch that simultaneously operates on an entire FC view and image patches to learn multi-scale representations. We design a plug-and-play module, Interactive dual-path chain gated axial-transformer (IDPCGAT), to enhance the interactions between global and local branches. In IDPCGAT, the multi-scale representations from the two branches can complement each other, capturing the same region’s salient features and suppressing feature responses to maintain only the activations associated with specific targets. Extensive experiments demonstrate that the DPC-MSGATNet exceeds seven state-of-the-art convolution- and transformer-based methods by a large margin in terms of F1 and IoU scores on our fetal FC view dataset, achieving a F1 score of 96.87 $$\%$$ % and an IoU score of 93.99 $$\%$$ % . The codes and datasets can be available at https://github.comQiaoSiBo/DPC-MSGATNet .https://doi.org/10.1007/s40747-023-00968-xConvolutional neural networkEchocardiographyFetal four chambersSemantic segmentationTransformer |
| spellingShingle | Sibo Qiao Shanchen Pang Gang Luo Yi Sun Wenjing Yin Silin Pan Zhihan Lv DPC-MSGATNet: dual-path chain multi-scale gated axial-transformer network for four-chamber view segmentation in fetal echocardiography Complex & Intelligent Systems Convolutional neural network Echocardiography Fetal four chambers Semantic segmentation Transformer |
| title | DPC-MSGATNet: dual-path chain multi-scale gated axial-transformer network for four-chamber view segmentation in fetal echocardiography |
| title_full | DPC-MSGATNet: dual-path chain multi-scale gated axial-transformer network for four-chamber view segmentation in fetal echocardiography |
| title_fullStr | DPC-MSGATNet: dual-path chain multi-scale gated axial-transformer network for four-chamber view segmentation in fetal echocardiography |
| title_full_unstemmed | DPC-MSGATNet: dual-path chain multi-scale gated axial-transformer network for four-chamber view segmentation in fetal echocardiography |
| title_short | DPC-MSGATNet: dual-path chain multi-scale gated axial-transformer network for four-chamber view segmentation in fetal echocardiography |
| title_sort | dpc msgatnet dual path chain multi scale gated axial transformer network for four chamber view segmentation in fetal echocardiography |
| topic | Convolutional neural network Echocardiography Fetal four chambers Semantic segmentation Transformer |
| url | https://doi.org/10.1007/s40747-023-00968-x |
| work_keys_str_mv | AT siboqiao dpcmsgatnetdualpathchainmultiscalegatedaxialtransformernetworkforfourchamberviewsegmentationinfetalechocardiography AT shanchenpang dpcmsgatnetdualpathchainmultiscalegatedaxialtransformernetworkforfourchamberviewsegmentationinfetalechocardiography AT gangluo dpcmsgatnetdualpathchainmultiscalegatedaxialtransformernetworkforfourchamberviewsegmentationinfetalechocardiography AT yisun dpcmsgatnetdualpathchainmultiscalegatedaxialtransformernetworkforfourchamberviewsegmentationinfetalechocardiography AT wenjingyin dpcmsgatnetdualpathchainmultiscalegatedaxialtransformernetworkforfourchamberviewsegmentationinfetalechocardiography AT silinpan dpcmsgatnetdualpathchainmultiscalegatedaxialtransformernetworkforfourchamberviewsegmentationinfetalechocardiography AT zhihanlv dpcmsgatnetdualpathchainmultiscalegatedaxialtransformernetworkforfourchamberviewsegmentationinfetalechocardiography |