Corona virus disease 2019 lesion segmentation network based on an adaptive joint loss function
Corona virus disease 2019 (COVID-19) is an acute respiratory infectious disease with strong contagiousness, strong variability, and long incubation period. The probability of misdiagnosis and missed diagnosis can be significantly decreased with the use of automatic segmentation of COVID-19 lesions based on computed tomography images, which helps doctors in rapid diagnosis and precise treatment. This paper introduced the level set generalized Dice loss function (LGDL) in conjunction with the level set segmentation method based on COVID-19 lesion segmentation network and proposed a dual-path COVID-19 lesion segmentation network (Dual-SAUNet++) to address the pain points such as the complex symptoms of COVID-19 and the blurred boundaries that are challenging to segment. LGDL is an adaptive weight joint loss obtained by combining the generalized Dice loss of the mask path and the mean square error of the level set path. On the test set, the model achieved Dice similarity coefficient of (87.81 ± 10.86)%, intersection over union of (79.20 ± 14.58)%, sensitivity of (94.18 ± 13.56)%, specificity of (99.83 ± 0.43)% and Hausdorff distance of 18.29 ± 31.48 mm. Studies indicated that Dual-SAUNet++ has a great anti-noise capability and it can segment multi-scale lesions while simultaneously focusing on their area and border information. The method proposed in this paper assists doctors in judging the severity of COVID-19 infection by accurately segmenting the lesion, and provides a reliable basis for subsequent clinical treatment.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2023 |
|---|---|
| Erschienen: |
2023 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:40 |
|---|---|
| Enthalten in: |
Sheng wu yi xue gong cheng xue za zhi = Journal of biomedical engineering = Shengwu yixue gongchengxue zazhi - 40(2023), 4 vom: 25. Aug., Seite 743-752 |
| Sprache: |
Chinesisch |
|---|
| Beteiligte Personen: |
Xiao, Hanguang [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Computed tomography |
|---|
| Anmerkungen: |
Date Completed 06.09.2023 Date Revised 06.11.2023 published: Print Citation Status MEDLINE |
|---|
| doi: |
10.7507/1001-5515.202206051 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM361644701 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM361644701 | ||
| 003 | DE-627 | ||
| 005 | 20231226085558.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231226s2023 xx |||||o 00| ||chi c | ||
| 024 | 7 | |a 10.7507/1001-5515.202206051 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1205.xml |
| 035 | |a (DE-627)NLM361644701 | ||
| 035 | |a (NLM)37666765 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a chi | ||
| 100 | 1 | |a Xiao, Hanguang |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Corona virus disease 2019 lesion segmentation network based on an adaptive joint loss function |
| 264 | 1 | |c 2023 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Completed 06.09.2023 | ||
| 500 | |a Date Revised 06.11.2023 | ||
| 500 | |a published: Print | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a Corona virus disease 2019 (COVID-19) is an acute respiratory infectious disease with strong contagiousness, strong variability, and long incubation period. The probability of misdiagnosis and missed diagnosis can be significantly decreased with the use of automatic segmentation of COVID-19 lesions based on computed tomography images, which helps doctors in rapid diagnosis and precise treatment. This paper introduced the level set generalized Dice loss function (LGDL) in conjunction with the level set segmentation method based on COVID-19 lesion segmentation network and proposed a dual-path COVID-19 lesion segmentation network (Dual-SAUNet++) to address the pain points such as the complex symptoms of COVID-19 and the blurred boundaries that are challenging to segment. LGDL is an adaptive weight joint loss obtained by combining the generalized Dice loss of the mask path and the mean square error of the level set path. On the test set, the model achieved Dice similarity coefficient of (87.81 ± 10.86)%, intersection over union of (79.20 ± 14.58)%, sensitivity of (94.18 ± 13.56)%, specificity of (99.83 ± 0.43)% and Hausdorff distance of 18.29 ± 31.48 mm. Studies indicated that Dual-SAUNet++ has a great anti-noise capability and it can segment multi-scale lesions while simultaneously focusing on their area and border information. The method proposed in this paper assists doctors in judging the severity of COVID-19 infection by accurately segmenting the lesion, and provides a reliable basis for subsequent clinical treatment | ||
| 650 | 4 | |a English Abstract | |
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a Computed tomography | |
| 650 | 4 | |a Corona virus disease 2019 | |
| 650 | 4 | |a Lesion segmentation | |
| 650 | 4 | |a Level set distance map | |
| 650 | 4 | |a Level set generalized Dice loss function | |
| 700 | 1 | |a Li, Huanqi |e verfasserin |4 aut | |
| 700 | 1 | |a Ran, Zhiqiang |e verfasserin |4 aut | |
| 700 | 1 | |a Zhang, Qihang |e verfasserin |4 aut | |
| 700 | 1 | |a Zhang, Bolong |e verfasserin |4 aut | |
| 700 | 1 | |a Wei, Yujia |e verfasserin |4 aut | |
| 700 | 1 | |a Zhu, Xiuhong |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Sheng wu yi xue gong cheng xue za zhi = Journal of biomedical engineering = Shengwu yixue gongchengxue zazhi |d 1997 |g 40(2023), 4 vom: 25. Aug., Seite 743-752 |w (DE-627)NLM093699425 |x 1001-5515 |7 nnns |
| 773 | 1 | 8 | |g volume:40 |g year:2023 |g number:4 |g day:25 |g month:08 |g pages:743-752 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.7507/1001-5515.202206051 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 40 |j 2023 |e 4 |b 25 |c 08 |h 743-752 | ||