Light-Convolution Dense Selection U-Net (LDS U-Net) for Ultrasound Lateral Bony Feature Segmentation

Scoliosis is a widespread medical condition where the spine becomes severely deformed and bends over time. It mostly affects young adults and may have a permanent impact on them. A periodic assessment, using a suitable modality, is necessary for its early detection. Conventionally, the usually emplo...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Sunetra Banerjee, Juan Lyu, Zixun Huang, Hung Fat Frank Leung, Timothy Tin-Yan Lee, De Yang, Steven Su, Yongping Zheng, Sai-Ho Ling
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	lateral bony feature depthwise separable convolution segmentation scoliosis ultrasound U-Net Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
Acceso en línea:	https://doaj.org/article/44084b7f4a1d4eb7b4bb8bafb0808978
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:44084b7f4a1d4eb7b4bb8bafb0808978
record_format	dspace
spelling	oai:doaj.org-article:44084b7f4a1d4eb7b4bb8bafb08089782021-11-11T15:14:19ZLight-Convolution Dense Selection U-Net (LDS U-Net) for Ultrasound Lateral Bony Feature Segmentation10.3390/app1121101802076-3417https://doaj.org/article/44084b7f4a1d4eb7b4bb8bafb08089782021-10-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/21/10180https://doaj.org/toc/2076-3417Scoliosis is a widespread medical condition where the spine becomes severely deformed and bends over time. It mostly affects young adults and may have a permanent impact on them. A periodic assessment, using a suitable modality, is necessary for its early detection. Conventionally, the usually employed modalities include X-ray and MRI, which employ ionising radiation and are expensive. Hence, a non-radiating 3D ultrasound imaging technique has been developed as a safe and economic alternative. However, ultrasound produces low-contrast images that are full of speckle noise, and skilled intervention is necessary for their processing. Given the prevalent occurrence of scoliosis and the limitations of scalability of human expert interventions, an automatic, fast, and low-computation assessment technique is being developed for mass scoliosis diagnosis. In this paper, a novel hybridized light-weight convolutional neural network architecture is presented for automatic lateral bony feature identification, which can help to develop a fully-fledged automatic scoliosis detection system. The proposed architecture, Light-convolution Dense Selection U-Net (LDS U-Net), can accurately segment ultrasound spine lateral bony features, from noisy images, thanks to its capabilities of smartly selecting only the useful information and extracting rich deep layer features from the input image. The proposed model is tested using a dataset of 109 spine ultrasound images. The segmentation result of the proposed network is compared with basic U-Net, Attention U-Net, and MultiResUNet using various popular segmentation indices. The results show that LDS U-Net provides a better segmentation performance compared to the other models. Additionally, LDS U-Net requires a smaller number of parameters and less memory, making it suitable for a large-batch screening process of scoliosis without a high computational requirement.Sunetra BanerjeeJuan LyuZixun HuangHung Fat Frank LeungTimothy Tin-Yan LeeDe YangSteven SuYongping ZhengSai-Ho LingMDPI AGarticlelateral bony featuredepthwise separable convolutionsegmentationscoliosisultrasoundU-NetTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 10180, p 10180 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	lateral bony feature depthwise separable convolution segmentation scoliosis ultrasound U-Net Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
spellingShingle	lateral bony feature depthwise separable convolution segmentation scoliosis ultrasound U-Net Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999 Sunetra Banerjee Juan Lyu Zixun Huang Hung Fat Frank Leung Timothy Tin-Yan Lee De Yang Steven Su Yongping Zheng Sai-Ho Ling Light-Convolution Dense Selection U-Net (LDS U-Net) for Ultrasound Lateral Bony Feature Segmentation
description	Scoliosis is a widespread medical condition where the spine becomes severely deformed and bends over time. It mostly affects young adults and may have a permanent impact on them. A periodic assessment, using a suitable modality, is necessary for its early detection. Conventionally, the usually employed modalities include X-ray and MRI, which employ ionising radiation and are expensive. Hence, a non-radiating 3D ultrasound imaging technique has been developed as a safe and economic alternative. However, ultrasound produces low-contrast images that are full of speckle noise, and skilled intervention is necessary for their processing. Given the prevalent occurrence of scoliosis and the limitations of scalability of human expert interventions, an automatic, fast, and low-computation assessment technique is being developed for mass scoliosis diagnosis. In this paper, a novel hybridized light-weight convolutional neural network architecture is presented for automatic lateral bony feature identification, which can help to develop a fully-fledged automatic scoliosis detection system. The proposed architecture, Light-convolution Dense Selection U-Net (LDS U-Net), can accurately segment ultrasound spine lateral bony features, from noisy images, thanks to its capabilities of smartly selecting only the useful information and extracting rich deep layer features from the input image. The proposed model is tested using a dataset of 109 spine ultrasound images. The segmentation result of the proposed network is compared with basic U-Net, Attention U-Net, and MultiResUNet using various popular segmentation indices. The results show that LDS U-Net provides a better segmentation performance compared to the other models. Additionally, LDS U-Net requires a smaller number of parameters and less memory, making it suitable for a large-batch screening process of scoliosis without a high computational requirement.
format	article
author	Sunetra Banerjee Juan Lyu Zixun Huang Hung Fat Frank Leung Timothy Tin-Yan Lee De Yang Steven Su Yongping Zheng Sai-Ho Ling
author_facet	Sunetra Banerjee Juan Lyu Zixun Huang Hung Fat Frank Leung Timothy Tin-Yan Lee De Yang Steven Su Yongping Zheng Sai-Ho Ling
author_sort	Sunetra Banerjee
title	Light-Convolution Dense Selection U-Net (LDS U-Net) for Ultrasound Lateral Bony Feature Segmentation
title_short	Light-Convolution Dense Selection U-Net (LDS U-Net) for Ultrasound Lateral Bony Feature Segmentation
title_full	Light-Convolution Dense Selection U-Net (LDS U-Net) for Ultrasound Lateral Bony Feature Segmentation
title_fullStr	Light-Convolution Dense Selection U-Net (LDS U-Net) for Ultrasound Lateral Bony Feature Segmentation
title_full_unstemmed	Light-Convolution Dense Selection U-Net (LDS U-Net) for Ultrasound Lateral Bony Feature Segmentation
title_sort	light-convolution dense selection u-net (lds u-net) for ultrasound lateral bony feature segmentation
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/44084b7f4a1d4eb7b4bb8bafb0808978
work_keys_str_mv	AT sunetrabanerjee lightconvolutiondenseselectionunetldsunetforultrasoundlateralbonyfeaturesegmentation AT juanlyu lightconvolutiondenseselectionunetldsunetforultrasoundlateralbonyfeaturesegmentation AT zixunhuang lightconvolutiondenseselectionunetldsunetforultrasoundlateralbonyfeaturesegmentation AT hungfatfrankleung lightconvolutiondenseselectionunetldsunetforultrasoundlateralbonyfeaturesegmentation AT timothytinyanlee lightconvolutiondenseselectionunetldsunetforultrasoundlateralbonyfeaturesegmentation AT deyang lightconvolutiondenseselectionunetldsunetforultrasoundlateralbonyfeaturesegmentation AT stevensu lightconvolutiondenseselectionunetldsunetforultrasoundlateralbonyfeaturesegmentation AT yongpingzheng lightconvolutiondenseselectionunetldsunetforultrasoundlateralbonyfeaturesegmentation AT saiholing lightconvolutiondenseselectionunetldsunetforultrasoundlateralbonyfeaturesegmentation
_version_	1718436362699407360

Light-Convolution Dense Selection U-Net (LDS U-Net) for Ultrasound Lateral Bony Feature Segmentation

Ejemplares similares