Contrast-Enhanced CT Texture Analysis for Distinguishing Fat-Poor Renal Angiomyolipoma From Chromophobe Renal Cell Carcinoma
Objective: To evaluate the value of 2-dimensional (2D) and 3-dimensional (3D) computed tomography texture analysis (CTTA) models in distinguishing fat-poor angiomyolipoma (fpAML) from chromophobe renal cell carcinoma (chRCC). Methods: We retrospectively enrolled 32 fpAMLs and 24 chRCCs. Texture feat...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SAGE Publications
2019-10-01
|
| Series: | Molecular Imaging |
| Online Access: | https://doi.org/10.1177/1536012119883161 |
| _version_ | 1797280437527117824 |
|---|---|
| author | Guangjie Yang MD Aidi Gong BS Pei Nie MD Lei Yan BS Wenjie Miao BS Yujun Zhao BS Jie Wu MD Jingjing Cui BS Yan Jia BS Zhenguang Wang MD |
| author_facet | Guangjie Yang MD Aidi Gong BS Pei Nie MD Lei Yan BS Wenjie Miao BS Yujun Zhao BS Jie Wu MD Jingjing Cui BS Yan Jia BS Zhenguang Wang MD |
| author_sort | Guangjie Yang MD |
| collection | DOAJ |
| description | Objective: To evaluate the value of 2-dimensional (2D) and 3-dimensional (3D) computed tomography texture analysis (CTTA) models in distinguishing fat-poor angiomyolipoma (fpAML) from chromophobe renal cell carcinoma (chRCC). Methods: We retrospectively enrolled 32 fpAMLs and 24 chRCCs. Texture features were extracted from 2D and 3D regions of interest in triphasic CT images. The 2D and 3D CTTA models were constructed with the least absolute shrinkage and selection operator algorithm and texture scores were calculated. The diagnostic performance of the 2D and 3D CTTA models was evaluated with respect to calibration, discrimination, and clinical usefulness. Results: Of the 177 and 183 texture features extracted from 2D and 3D regions of interest, respectively, 5 2D features and 8 3D features were selected to build 2D and 3D CTTA models. The 2D CTTA model (area under the curve [AUC], 0.811; 95% confidence interval [CI], 0.695-0.927) and the 3D CTTA model (AUC, 0.915; 95% CI, 0.838-0.993) showed good discrimination and calibration ( P > .05). There was no significant difference in AUC between the 2 models ( P = .093). Decision curve analysis showed the 3D model outperformed the 2D model in terms of clinical usefulness. Conclusions: The CTTA models based on contrast-enhanced CT images had a high value in differentiating fpAML from chRCC. |
| first_indexed | 2024-03-07T16:41:11Z |
| format | Article |
| id | doaj.art-4747d2b9eb7d420da29c7a9cd1ccbe8f |
| institution | Directory Open Access Journal |
| issn | 1536-0121 |
| language | English |
| last_indexed | 2024-03-07T16:41:11Z |
| publishDate | 2019-10-01 |
| publisher | SAGE Publications |
| record_format | Article |
| series | Molecular Imaging |
| spelling | doaj.art-4747d2b9eb7d420da29c7a9cd1ccbe8f2024-03-03T08:19:05ZengSAGE PublicationsMolecular Imaging1536-01212019-10-011810.1177/1536012119883161Contrast-Enhanced CT Texture Analysis for Distinguishing Fat-Poor Renal Angiomyolipoma From Chromophobe Renal Cell CarcinomaGuangjie Yang MD0Aidi Gong BS1Pei Nie MD2Lei Yan BS3Wenjie Miao BS4Yujun Zhao BS5Jie Wu MD6Jingjing Cui BS7Yan Jia BS8Zhenguang Wang MD9 PET-CT Center, The Affiliated Hospital of Qingdao University, Qingdao, Shandong, China PET-CT Center, The Affiliated Hospital of Qingdao University, Qingdao, Shandong, China Radiology Department, The Affiliated Hospital of Qingdao University, Qingdao, Shandong, China PET-CT Center, The Affiliated Hospital of Qingdao University, Qingdao, Shandong, China PET-CT Center, The Affiliated Hospital of Qingdao University, Qingdao, Shandong, China PET-CT Center, The Affiliated Hospital of Qingdao University, Qingdao, Shandong, China Pathology Department, The Affiliated Hospital of Qingdao University, Qingdao, Shandong, China Huiying Medical Technology Co, Ltd, Beijing, China Huiying Medical Technology Co, Ltd, Beijing, China PET-CT Center, The Affiliated Hospital of Qingdao University, Qingdao, Shandong, ChinaObjective: To evaluate the value of 2-dimensional (2D) and 3-dimensional (3D) computed tomography texture analysis (CTTA) models in distinguishing fat-poor angiomyolipoma (fpAML) from chromophobe renal cell carcinoma (chRCC). Methods: We retrospectively enrolled 32 fpAMLs and 24 chRCCs. Texture features were extracted from 2D and 3D regions of interest in triphasic CT images. The 2D and 3D CTTA models were constructed with the least absolute shrinkage and selection operator algorithm and texture scores were calculated. The diagnostic performance of the 2D and 3D CTTA models was evaluated with respect to calibration, discrimination, and clinical usefulness. Results: Of the 177 and 183 texture features extracted from 2D and 3D regions of interest, respectively, 5 2D features and 8 3D features were selected to build 2D and 3D CTTA models. The 2D CTTA model (area under the curve [AUC], 0.811; 95% confidence interval [CI], 0.695-0.927) and the 3D CTTA model (AUC, 0.915; 95% CI, 0.838-0.993) showed good discrimination and calibration ( P > .05). There was no significant difference in AUC between the 2 models ( P = .093). Decision curve analysis showed the 3D model outperformed the 2D model in terms of clinical usefulness. Conclusions: The CTTA models based on contrast-enhanced CT images had a high value in differentiating fpAML from chRCC.https://doi.org/10.1177/1536012119883161 |
| spellingShingle | Guangjie Yang MD Aidi Gong BS Pei Nie MD Lei Yan BS Wenjie Miao BS Yujun Zhao BS Jie Wu MD Jingjing Cui BS Yan Jia BS Zhenguang Wang MD Contrast-Enhanced CT Texture Analysis for Distinguishing Fat-Poor Renal Angiomyolipoma From Chromophobe Renal Cell Carcinoma Molecular Imaging |
| title | Contrast-Enhanced CT Texture Analysis for Distinguishing Fat-Poor Renal Angiomyolipoma From Chromophobe Renal Cell Carcinoma |
| title_full | Contrast-Enhanced CT Texture Analysis for Distinguishing Fat-Poor Renal Angiomyolipoma From Chromophobe Renal Cell Carcinoma |
| title_fullStr | Contrast-Enhanced CT Texture Analysis for Distinguishing Fat-Poor Renal Angiomyolipoma From Chromophobe Renal Cell Carcinoma |
| title_full_unstemmed | Contrast-Enhanced CT Texture Analysis for Distinguishing Fat-Poor Renal Angiomyolipoma From Chromophobe Renal Cell Carcinoma |
| title_short | Contrast-Enhanced CT Texture Analysis for Distinguishing Fat-Poor Renal Angiomyolipoma From Chromophobe Renal Cell Carcinoma |
| title_sort | contrast enhanced ct texture analysis for distinguishing fat poor renal angiomyolipoma from chromophobe renal cell carcinoma |
| url | https://doi.org/10.1177/1536012119883161 |
| work_keys_str_mv | AT guangjieyangmd contrastenhancedcttextureanalysisfordistinguishingfatpoorrenalangiomyolipomafromchromophoberenalcellcarcinoma AT aidigongbs contrastenhancedcttextureanalysisfordistinguishingfatpoorrenalangiomyolipomafromchromophoberenalcellcarcinoma AT peiniemd contrastenhancedcttextureanalysisfordistinguishingfatpoorrenalangiomyolipomafromchromophoberenalcellcarcinoma AT leiyanbs contrastenhancedcttextureanalysisfordistinguishingfatpoorrenalangiomyolipomafromchromophoberenalcellcarcinoma AT wenjiemiaobs contrastenhancedcttextureanalysisfordistinguishingfatpoorrenalangiomyolipomafromchromophoberenalcellcarcinoma AT yujunzhaobs contrastenhancedcttextureanalysisfordistinguishingfatpoorrenalangiomyolipomafromchromophoberenalcellcarcinoma AT jiewumd contrastenhancedcttextureanalysisfordistinguishingfatpoorrenalangiomyolipomafromchromophoberenalcellcarcinoma AT jingjingcuibs contrastenhancedcttextureanalysisfordistinguishingfatpoorrenalangiomyolipomafromchromophoberenalcellcarcinoma AT yanjiabs contrastenhancedcttextureanalysisfordistinguishingfatpoorrenalangiomyolipomafromchromophoberenalcellcarcinoma AT zhenguangwangmd contrastenhancedcttextureanalysisfordistinguishingfatpoorrenalangiomyolipomafromchromophoberenalcellcarcinoma |