COVID TV-Unet: Segmenting COVID-19 chest CT images using connectivity imposed Unet
The novel corona-virus disease (COVID-19) pandemic has caused a major outbreak in more than 200 countries around the world, leading to a severe impact on the health and life of many people globally. By October 2020, more than 44 million people were infected, and more than 1,000,000 deaths were repor...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2021-01-01
|
| Series: | Computer Methods and Programs in Biomedicine Update |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666990021000069 |
| _version_ | 1819095699173670912 |
|---|---|
| author | Narges Saeedizadeh Shervin Minaee Rahele Kafieh Shakib Yazdani Milan Sonka |
| author_facet | Narges Saeedizadeh Shervin Minaee Rahele Kafieh Shakib Yazdani Milan Sonka |
| author_sort | Narges Saeedizadeh |
| collection | DOAJ |
| description | The novel corona-virus disease (COVID-19) pandemic has caused a major outbreak in more than 200 countries around the world, leading to a severe impact on the health and life of many people globally. By October 2020, more than 44 million people were infected, and more than 1,000,000 deaths were reported. Computed Tomography (CT) images can be used as an alternative to the time-consuming RT-PCR test, to detect COVID-19. In this work we propose a segmentation framework to detect chest regions in CT images, which are infected by COVID-19. An architecture similar to a Unet model was employed to detect ground glass regions on a voxel level. As the infected regions tend to form connected components (rather than randomly distributed voxels), a suitable regularization term based on 2D-anisotropic total-variation was developed and added to the loss function. The proposed model is therefore called ”TV-Unet”. Experimental results obtained on a relatively large-scale CT segmentation dataset of around 900 images, incorporating this new regularization term leads to a 2% gain on overall segmentation performance compared to the Unet trained from scratch. Our experimental analysis, ranging from visual evaluation of the predicted segmentation results to quantitative assessment of segmentation performance (precision, recall, Dice score, and mIoU) demonstrated great ability to identify COVID-19 associated regions of the lungs, achieving a mIoU rate of over 99%, and a Dice score of around 86%. |
| first_indexed | 2024-12-21T23:47:27Z |
| format | Article |
| id | doaj.art-fb3edcf3e5b44235b7cd079ef7926519 |
| institution | Directory Open Access Journal |
| issn | 2666-9900 |
| language | English |
| last_indexed | 2024-12-21T23:47:27Z |
| publishDate | 2021-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Computer Methods and Programs in Biomedicine Update |
| spelling | doaj.art-fb3edcf3e5b44235b7cd079ef79265192022-12-21T18:46:04ZengElsevierComputer Methods and Programs in Biomedicine Update2666-99002021-01-011100007COVID TV-Unet: Segmenting COVID-19 chest CT images using connectivity imposed UnetNarges Saeedizadeh0Shervin Minaee1Rahele Kafieh2Shakib Yazdani3Milan Sonka4Medical Image and Signal Processing Research Center, Isfahan University of Medical Sciences, Iran; Corresponding authors.Snap Inc., Seattle, WA, USA; Corresponding authors.Medical Image and Signal Processing Research Center, Isfahan University of Medical Sciences, Iran; Corresponding authors.ECE Department, Isfahan University of Technology, IranIowa Institute for Biomedical Imaging, The University of Iowa, Iowa City, USAThe novel corona-virus disease (COVID-19) pandemic has caused a major outbreak in more than 200 countries around the world, leading to a severe impact on the health and life of many people globally. By October 2020, more than 44 million people were infected, and more than 1,000,000 deaths were reported. Computed Tomography (CT) images can be used as an alternative to the time-consuming RT-PCR test, to detect COVID-19. In this work we propose a segmentation framework to detect chest regions in CT images, which are infected by COVID-19. An architecture similar to a Unet model was employed to detect ground glass regions on a voxel level. As the infected regions tend to form connected components (rather than randomly distributed voxels), a suitable regularization term based on 2D-anisotropic total-variation was developed and added to the loss function. The proposed model is therefore called ”TV-Unet”. Experimental results obtained on a relatively large-scale CT segmentation dataset of around 900 images, incorporating this new regularization term leads to a 2% gain on overall segmentation performance compared to the Unet trained from scratch. Our experimental analysis, ranging from visual evaluation of the predicted segmentation results to quantitative assessment of segmentation performance (precision, recall, Dice score, and mIoU) demonstrated great ability to identify COVID-19 associated regions of the lungs, achieving a mIoU rate of over 99%, and a Dice score of around 86%.http://www.sciencedirect.com/science/article/pii/S2666990021000069Deep learningComputed tomographyCOVID-19Image segmentationConvolutional encoder decoderTotal variation |
| spellingShingle | Narges Saeedizadeh Shervin Minaee Rahele Kafieh Shakib Yazdani Milan Sonka COVID TV-Unet: Segmenting COVID-19 chest CT images using connectivity imposed Unet Computer Methods and Programs in Biomedicine Update Deep learning Computed tomography COVID-19 Image segmentation Convolutional encoder decoder Total variation |
| title | COVID TV-Unet: Segmenting COVID-19 chest CT images using connectivity imposed Unet |
| title_full | COVID TV-Unet: Segmenting COVID-19 chest CT images using connectivity imposed Unet |
| title_fullStr | COVID TV-Unet: Segmenting COVID-19 chest CT images using connectivity imposed Unet |
| title_full_unstemmed | COVID TV-Unet: Segmenting COVID-19 chest CT images using connectivity imposed Unet |
| title_short | COVID TV-Unet: Segmenting COVID-19 chest CT images using connectivity imposed Unet |
| title_sort | covid tv unet segmenting covid 19 chest ct images using connectivity imposed unet |
| topic | Deep learning Computed tomography COVID-19 Image segmentation Convolutional encoder decoder Total variation |
| url | http://www.sciencedirect.com/science/article/pii/S2666990021000069 |
| work_keys_str_mv | AT nargessaeedizadeh covidtvunetsegmentingcovid19chestctimagesusingconnectivityimposedunet AT shervinminaee covidtvunetsegmentingcovid19chestctimagesusingconnectivityimposedunet AT rahelekafieh covidtvunetsegmentingcovid19chestctimagesusingconnectivityimposedunet AT shakibyazdani covidtvunetsegmentingcovid19chestctimagesusingconnectivityimposedunet AT milansonka covidtvunetsegmentingcovid19chestctimagesusingconnectivityimposedunet |