Machine Learning Radiomics Signature for Differentiating Lymphoma versus Benign Splenomegaly on CT
Background: We aimed to develop and validate a preoperative CT-based radiomics signature for differentiating lymphoma versus benign splenomegaly. Methods: We retrospectively analyzed CT studies from 139 patients (age range 26–93 years, 43% female) between 2011 and 2019 with histopathological diagnos...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/13/24/3632 |
| _version_ | 1797381413099536384 |
|---|---|
| author | Jih-An Cheng Yu-Chun Lin Yenpo Lin Ren-Chin Wu Hsin-Ying Lu Lan-Yan Yang Hsin-Ju Chiang Yu-Hsiang Juan Ying-Chieh Lai Gigin Lin |
| author_facet | Jih-An Cheng Yu-Chun Lin Yenpo Lin Ren-Chin Wu Hsin-Ying Lu Lan-Yan Yang Hsin-Ju Chiang Yu-Hsiang Juan Ying-Chieh Lai Gigin Lin |
| author_sort | Jih-An Cheng |
| collection | DOAJ |
| description | Background: We aimed to develop and validate a preoperative CT-based radiomics signature for differentiating lymphoma versus benign splenomegaly. Methods: We retrospectively analyzed CT studies from 139 patients (age range 26–93 years, 43% female) between 2011 and 2019 with histopathological diagnosis of the spleen (19 lymphoma, 120 benign) and divided them into developing (<i>n</i> = 79) and testing (<i>n</i> = 60) datasets. The volumetric radiomic features were extracted from manual segmentation of the whole spleen on venous-phase CT imaging using PyRadiomics package. LASSO regression was applied for feature selection and development of the radiomic signature, which was interrogated with the complete blood cell count and differential count. All <i>p</i> values < 0.05 were considered to be significant. Results: Seven features were selected for constructing the radiomic signature after feature selection, including first-order statistics (10th percentile and Robust Mean Absolute Deviation), shape-based (Surface Area), and texture features (Correlation, MCC, Small Area Low Gray-level Emphasis and Low Gray-level Zone Emphasis). The radiomic signature achieved an excellent diagnostic accuracy of 97%, sensitivity of 89%, and specificity of 98%, distinguishing lymphoma versus benign splenomegaly in the testing dataset. The radiomic signature significantly correlated with the platelet and segmented neutrophil percentage. Conclusions: CT-based radiomics signature can be useful in distinguishing lymphoma versus benign splenomegaly and can reflect the changes in underlying blood profiles. |
| first_indexed | 2024-03-08T20:52:10Z |
| format | Article |
| id | doaj.art-d1d90bfd6cbb469db2e2fe102c375fac |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-08T20:52:10Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-d1d90bfd6cbb469db2e2fe102c375fac2023-12-22T14:03:08ZengMDPI AGDiagnostics2075-44182023-12-011324363210.3390/diagnostics13243632Machine Learning Radiomics Signature for Differentiating Lymphoma versus Benign Splenomegaly on CTJih-An Cheng0Yu-Chun Lin1Yenpo Lin2Ren-Chin Wu3Hsin-Ying Lu4Lan-Yan Yang5Hsin-Ju Chiang6Yu-Hsiang Juan7Ying-Chieh Lai8Gigin Lin9Department of Medical Imaging and Intervention, Chang Gung Memorial Hospital at Linkou, 5 Fuhsing St., Guishan, Taoyuan 333, TaiwanDepartment of Medical Imaging and Intervention, Chang Gung Memorial Hospital at Linkou, 5 Fuhsing St., Guishan, Taoyuan 333, TaiwanDepartment of Medical Imaging and Intervention, Chang Gung Memorial Hospital at Linkou, 5 Fuhsing St., Guishan, Taoyuan 333, TaiwanDepartment of Pathology, Chang Gung Memorial Hospital at Linkou, 5 Fuhsing St., Guishan, Taoyuan 333, TaiwanDepartment of Medical Imaging and Intervention, Chang Gung Memorial Hospital at Linkou, 5 Fuhsing St., Guishan, Taoyuan 333, TaiwanClinical Trial Center, Chang Gung Memorial Hospital at Linkou and Chang Gung University, 5 Fuhsing St., Guishan, Taoyuan 333, TaiwanDepartment of Medical Imaging and Intervention, Chang Gung Memorial Hospital at Linkou, 5 Fuhsing St., Guishan, Taoyuan 333, TaiwanDepartment of Medical Imaging and Intervention, Chang Gung Memorial Hospital at Linkou, 5 Fuhsing St., Guishan, Taoyuan 333, TaiwanDepartment of Medical Imaging and Intervention, Chang Gung Memorial Hospital at Linkou, 5 Fuhsing St., Guishan, Taoyuan 333, TaiwanDepartment of Medical Imaging and Intervention, Chang Gung Memorial Hospital at Linkou, 5 Fuhsing St., Guishan, Taoyuan 333, TaiwanBackground: We aimed to develop and validate a preoperative CT-based radiomics signature for differentiating lymphoma versus benign splenomegaly. Methods: We retrospectively analyzed CT studies from 139 patients (age range 26–93 years, 43% female) between 2011 and 2019 with histopathological diagnosis of the spleen (19 lymphoma, 120 benign) and divided them into developing (<i>n</i> = 79) and testing (<i>n</i> = 60) datasets. The volumetric radiomic features were extracted from manual segmentation of the whole spleen on venous-phase CT imaging using PyRadiomics package. LASSO regression was applied for feature selection and development of the radiomic signature, which was interrogated with the complete blood cell count and differential count. All <i>p</i> values < 0.05 were considered to be significant. Results: Seven features were selected for constructing the radiomic signature after feature selection, including first-order statistics (10th percentile and Robust Mean Absolute Deviation), shape-based (Surface Area), and texture features (Correlation, MCC, Small Area Low Gray-level Emphasis and Low Gray-level Zone Emphasis). The radiomic signature achieved an excellent diagnostic accuracy of 97%, sensitivity of 89%, and specificity of 98%, distinguishing lymphoma versus benign splenomegaly in the testing dataset. The radiomic signature significantly correlated with the platelet and segmented neutrophil percentage. Conclusions: CT-based radiomics signature can be useful in distinguishing lymphoma versus benign splenomegaly and can reflect the changes in underlying blood profiles.https://www.mdpi.com/2075-4418/13/24/3632computer-aided diagnosisquantitative imaging biomarkersradiomicslymphomasplenomegaly |
| spellingShingle | Jih-An Cheng Yu-Chun Lin Yenpo Lin Ren-Chin Wu Hsin-Ying Lu Lan-Yan Yang Hsin-Ju Chiang Yu-Hsiang Juan Ying-Chieh Lai Gigin Lin Machine Learning Radiomics Signature for Differentiating Lymphoma versus Benign Splenomegaly on CT Diagnostics computer-aided diagnosis quantitative imaging biomarkers radiomics lymphoma splenomegaly |
| title | Machine Learning Radiomics Signature for Differentiating Lymphoma versus Benign Splenomegaly on CT |
| title_full | Machine Learning Radiomics Signature for Differentiating Lymphoma versus Benign Splenomegaly on CT |
| title_fullStr | Machine Learning Radiomics Signature for Differentiating Lymphoma versus Benign Splenomegaly on CT |
| title_full_unstemmed | Machine Learning Radiomics Signature for Differentiating Lymphoma versus Benign Splenomegaly on CT |
| title_short | Machine Learning Radiomics Signature for Differentiating Lymphoma versus Benign Splenomegaly on CT |
| title_sort | machine learning radiomics signature for differentiating lymphoma versus benign splenomegaly on ct |
| topic | computer-aided diagnosis quantitative imaging biomarkers radiomics lymphoma splenomegaly |
| url | https://www.mdpi.com/2075-4418/13/24/3632 |
| work_keys_str_mv | AT jihancheng machinelearningradiomicssignaturefordifferentiatinglymphomaversusbenignsplenomegalyonct AT yuchunlin machinelearningradiomicssignaturefordifferentiatinglymphomaversusbenignsplenomegalyonct AT yenpolin machinelearningradiomicssignaturefordifferentiatinglymphomaversusbenignsplenomegalyonct AT renchinwu machinelearningradiomicssignaturefordifferentiatinglymphomaversusbenignsplenomegalyonct AT hsinyinglu machinelearningradiomicssignaturefordifferentiatinglymphomaversusbenignsplenomegalyonct AT lanyanyang machinelearningradiomicssignaturefordifferentiatinglymphomaversusbenignsplenomegalyonct AT hsinjuchiang machinelearningradiomicssignaturefordifferentiatinglymphomaversusbenignsplenomegalyonct AT yuhsiangjuan machinelearningradiomicssignaturefordifferentiatinglymphomaversusbenignsplenomegalyonct AT yingchiehlai machinelearningradiomicssignaturefordifferentiatinglymphomaversusbenignsplenomegalyonct AT giginlin machinelearningradiomicssignaturefordifferentiatinglymphomaversusbenignsplenomegalyonct |