Decoders configurations based on Unet family and feature pyramid network for COVID-19 segmentation on CT images
Coronavirus Disease 2019 (COVID-19) pandemic has been ferociously destroying global health and economics. According to World Health Organisation (WHO), until May 2021, more than one hundred million infected cases and 3.2 million deaths have been reported in over 200 countries. Unfortunately, the num...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2021-09-01
|
| Series: | PeerJ Computer Science |
| Subjects: | |
| Online Access: | https://peerj.com/articles/cs-719.pdf |
| _version_ | 1818718411459395584 |
|---|---|
| author | Hai Thanh Nguyen Toan Bao Tran Huong Hoang Luong Tuan Khoi Nguyen Huynh |
| author_facet | Hai Thanh Nguyen Toan Bao Tran Huong Hoang Luong Tuan Khoi Nguyen Huynh |
| author_sort | Hai Thanh Nguyen |
| collection | DOAJ |
| description | Coronavirus Disease 2019 (COVID-19) pandemic has been ferociously destroying global health and economics. According to World Health Organisation (WHO), until May 2021, more than one hundred million infected cases and 3.2 million deaths have been reported in over 200 countries. Unfortunately, the numbers are still on the rise. Therefore, scientists are making a significant effort in researching accurate, efficient diagnoses. Several studies advocating artificial intelligence proposed COVID diagnosis methods on lung images with high accuracy. Furthermore, some affected areas in the lung images can be detected accurately by segmentation methods. This work has considered state-of-the-art Convolutional Neural Network architectures, combined with the Unet family and Feature Pyramid Network (FPN) for COVID segmentation tasks on Computed Tomography (CT) scanner samples the Italian Society of Medical and Interventional Radiology dataset. The experiments show that the decoder-based Unet family has reached the best (a mean Intersection Over Union (mIoU) of 0.9234, 0.9032 in dice score, and a recall of 0.9349) with a combination between SE ResNeXt and Unet++. The decoder with the Unet family obtained better COVID segmentation performance in comparison with Feature Pyramid Network. Furthermore, the proposed method outperforms recent segmentation state-of-the-art approaches such as the SegNet-based network, ADID-UNET, and A-SegNet + FTL. Therefore, it is expected to provide good segmentation visualizations of medical images. |
| first_indexed | 2024-12-17T19:50:37Z |
| format | Article |
| id | doaj.art-f4e352989ad74ed29d5272e5f3864eae |
| institution | Directory Open Access Journal |
| issn | 2376-5992 |
| language | English |
| last_indexed | 2024-12-17T19:50:37Z |
| publishDate | 2021-09-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ Computer Science |
| spelling | doaj.art-f4e352989ad74ed29d5272e5f3864eae2022-12-21T21:34:44ZengPeerJ Inc.PeerJ Computer Science2376-59922021-09-017e71910.7717/peerj-cs.719Decoders configurations based on Unet family and feature pyramid network for COVID-19 segmentation on CT imagesHai Thanh Nguyen0Toan Bao Tran1Huong Hoang Luong2Tuan Khoi Nguyen Huynh3College of Information and Communication Technology, Can Tho University, Can Tho, VietnamCenter of Software Engineering, Duy Tan University, Da Nang, VietnamFPT University, Can Tho, VietnamFPT University, Can Tho, VietnamCoronavirus Disease 2019 (COVID-19) pandemic has been ferociously destroying global health and economics. According to World Health Organisation (WHO), until May 2021, more than one hundred million infected cases and 3.2 million deaths have been reported in over 200 countries. Unfortunately, the numbers are still on the rise. Therefore, scientists are making a significant effort in researching accurate, efficient diagnoses. Several studies advocating artificial intelligence proposed COVID diagnosis methods on lung images with high accuracy. Furthermore, some affected areas in the lung images can be detected accurately by segmentation methods. This work has considered state-of-the-art Convolutional Neural Network architectures, combined with the Unet family and Feature Pyramid Network (FPN) for COVID segmentation tasks on Computed Tomography (CT) scanner samples the Italian Society of Medical and Interventional Radiology dataset. The experiments show that the decoder-based Unet family has reached the best (a mean Intersection Over Union (mIoU) of 0.9234, 0.9032 in dice score, and a recall of 0.9349) with a combination between SE ResNeXt and Unet++. The decoder with the Unet family obtained better COVID segmentation performance in comparison with Feature Pyramid Network. Furthermore, the proposed method outperforms recent segmentation state-of-the-art approaches such as the SegNet-based network, ADID-UNET, and A-SegNet + FTL. Therefore, it is expected to provide good segmentation visualizations of medical images.https://peerj.com/articles/cs-719.pdfCovid segmentationCovid diagnosisComputed tomography scannerSegmentation visualization |
| spellingShingle | Hai Thanh Nguyen Toan Bao Tran Huong Hoang Luong Tuan Khoi Nguyen Huynh Decoders configurations based on Unet family and feature pyramid network for COVID-19 segmentation on CT images PeerJ Computer Science Covid segmentation Covid diagnosis Computed tomography scanner Segmentation visualization |
| title | Decoders configurations based on Unet family and feature pyramid network for COVID-19 segmentation on CT images |
| title_full | Decoders configurations based on Unet family and feature pyramid network for COVID-19 segmentation on CT images |
| title_fullStr | Decoders configurations based on Unet family and feature pyramid network for COVID-19 segmentation on CT images |
| title_full_unstemmed | Decoders configurations based on Unet family and feature pyramid network for COVID-19 segmentation on CT images |
| title_short | Decoders configurations based on Unet family and feature pyramid network for COVID-19 segmentation on CT images |
| title_sort | decoders configurations based on unet family and feature pyramid network for covid 19 segmentation on ct images |
| topic | Covid segmentation Covid diagnosis Computed tomography scanner Segmentation visualization |
| url | https://peerj.com/articles/cs-719.pdf |
| work_keys_str_mv | AT haithanhnguyen decodersconfigurationsbasedonunetfamilyandfeaturepyramidnetworkforcovid19segmentationonctimages AT toanbaotran decodersconfigurationsbasedonunetfamilyandfeaturepyramidnetworkforcovid19segmentationonctimages AT huonghoangluong decodersconfigurationsbasedonunetfamilyandfeaturepyramidnetworkforcovid19segmentationonctimages AT tuankhoinguyenhuynh decodersconfigurationsbasedonunetfamilyandfeaturepyramidnetworkforcovid19segmentationonctimages |