Machine learning-based CT texture analysis in the differentiation of testicular masses
PurposeTo evaluate the ability of texture features for distinguishing between benign and malignant testicular masses, and furthermore, for identifying primary testicular lymphoma in malignant tumors and identifying seminoma in testicular germ cell tumors, respectively.MethodsWe retrospectively colle...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2024-01-01
|
| Series: | Frontiers in Oncology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2023.1284040/full |
| _version_ | 1827380752321347584 |
|---|---|
| author | Can Hu Can Hu Xiaomeng Qiao Zhenyu Xu Zhiyu Zhang Xuefeng Zhang |
| author_facet | Can Hu Can Hu Xiaomeng Qiao Zhenyu Xu Zhiyu Zhang Xuefeng Zhang |
| author_sort | Can Hu |
| collection | DOAJ |
| description | PurposeTo evaluate the ability of texture features for distinguishing between benign and malignant testicular masses, and furthermore, for identifying primary testicular lymphoma in malignant tumors and identifying seminoma in testicular germ cell tumors, respectively.MethodsWe retrospectively collected 77 patients with an abdominal and pelvic enhanced computed tomography (CT) examination and a histopathologically confirmed testicular mass from a single center. The ROI of each mass was split into two parts by the largest cross-sectional slice and deemed to be two samples. After all processing steps, three-dimensional texture features were extracted from unenhanced and contrast-enhanced CT images. Excellent reproducibility of texture features was defined as intra-class correlation coefficient ≥0.8 (ICC ≥0.8). All the groups were balanced via the synthetic minority over-sampling technique (SMOTE) method. Dimension reduction was based on pearson correlation coefficient (PCC). Before model building, minimum-redundancy maximum-relevance (mRMR) selection and recursive feature elimination (RFE) were used for further feature selection. At last, three ML classifiers with the highest cross validation with 5-fold were selected: autoencoder (AE), support vector machine(SVM), linear discriminant analysis (LAD). Logistics regression (LR) and LR-LASSO were also constructed to compare with the ML classifiers.Results985 texture features with ICC ≥0.8 were extracted for further feature selection process. With the highest AUC of 0.946 (P <0.01), logistics regression was proved to be the best model for the identification of benign or malignant testicular masses. Besides, LR also had the best performance in identifying primary testicular lymphoma in malignant testicular tumors and in identifying seminoma in testicular germ cell tumors, with the AUC of 0.982 (P <0.01) and 0.928 (P <0.01), respectively.ConclusionUntil now, this is the first study that applied CT texture analysis (CTTA) to assess the heterogeneity of testicular tumors. LR model based on CTTA might be a promising non-invasive tool for the diagnosis and differentiation of testicular masses. The accurate diagnosis of testicular masses would assist urologists in correct preoperative and perioperative decision making. |
| first_indexed | 2024-03-08T13:38:50Z |
| format | Article |
| id | doaj.art-f6edbeaefb35428fba1886699936c108 |
| institution | Directory Open Access Journal |
| issn | 2234-943X |
| language | English |
| last_indexed | 2024-03-08T13:38:50Z |
| publishDate | 2024-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Oncology |
| spelling | doaj.art-f6edbeaefb35428fba1886699936c1082024-01-16T13:37:04ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2024-01-011310.3389/fonc.2023.12840401284040Machine learning-based CT texture analysis in the differentiation of testicular massesCan Hu0Can Hu1Xiaomeng Qiao2Zhenyu Xu3Zhiyu Zhang4Xuefeng Zhang5Department of Urology, The First Affiliated Hospital of Soochow University, Suzhou, Jiangsu, ChinaDepartment of Urology, Suzhou Xiangcheng People’s Hospital, Suzhou, ChinaDepartment of Radiology, The First Affiliated Hospital of Soochow University, Suzhou, Jiangsu, ChinaDepartment of Urology, The Affiliated Hospital of Nanjing University of Traditional Chinese Medicine: Traditional Chinese Medicine Hospital of Kunshan, Kunshan, ChinaDepartment of Urology, The First Affiliated Hospital of Soochow University, Suzhou, Jiangsu, ChinaDepartment of Urology, The First Affiliated Hospital of Soochow University, Suzhou, Jiangsu, ChinaPurposeTo evaluate the ability of texture features for distinguishing between benign and malignant testicular masses, and furthermore, for identifying primary testicular lymphoma in malignant tumors and identifying seminoma in testicular germ cell tumors, respectively.MethodsWe retrospectively collected 77 patients with an abdominal and pelvic enhanced computed tomography (CT) examination and a histopathologically confirmed testicular mass from a single center. The ROI of each mass was split into two parts by the largest cross-sectional slice and deemed to be two samples. After all processing steps, three-dimensional texture features were extracted from unenhanced and contrast-enhanced CT images. Excellent reproducibility of texture features was defined as intra-class correlation coefficient ≥0.8 (ICC ≥0.8). All the groups were balanced via the synthetic minority over-sampling technique (SMOTE) method. Dimension reduction was based on pearson correlation coefficient (PCC). Before model building, minimum-redundancy maximum-relevance (mRMR) selection and recursive feature elimination (RFE) were used for further feature selection. At last, three ML classifiers with the highest cross validation with 5-fold were selected: autoencoder (AE), support vector machine(SVM), linear discriminant analysis (LAD). Logistics regression (LR) and LR-LASSO were also constructed to compare with the ML classifiers.Results985 texture features with ICC ≥0.8 were extracted for further feature selection process. With the highest AUC of 0.946 (P <0.01), logistics regression was proved to be the best model for the identification of benign or malignant testicular masses. Besides, LR also had the best performance in identifying primary testicular lymphoma in malignant testicular tumors and in identifying seminoma in testicular germ cell tumors, with the AUC of 0.982 (P <0.01) and 0.928 (P <0.01), respectively.ConclusionUntil now, this is the first study that applied CT texture analysis (CTTA) to assess the heterogeneity of testicular tumors. LR model based on CTTA might be a promising non-invasive tool for the diagnosis and differentiation of testicular masses. The accurate diagnosis of testicular masses would assist urologists in correct preoperative and perioperative decision making.https://www.frontiersin.org/articles/10.3389/fonc.2023.1284040/fullcontrast enhanced computerized tomographyCT texture analysistesticular massesmachine learningurology and radiology |
| spellingShingle | Can Hu Can Hu Xiaomeng Qiao Zhenyu Xu Zhiyu Zhang Xuefeng Zhang Machine learning-based CT texture analysis in the differentiation of testicular masses Frontiers in Oncology contrast enhanced computerized tomography CT texture analysis testicular masses machine learning urology and radiology |
| title | Machine learning-based CT texture analysis in the differentiation of testicular masses |
| title_full | Machine learning-based CT texture analysis in the differentiation of testicular masses |
| title_fullStr | Machine learning-based CT texture analysis in the differentiation of testicular masses |
| title_full_unstemmed | Machine learning-based CT texture analysis in the differentiation of testicular masses |
| title_short | Machine learning-based CT texture analysis in the differentiation of testicular masses |
| title_sort | machine learning based ct texture analysis in the differentiation of testicular masses |
| topic | contrast enhanced computerized tomography CT texture analysis testicular masses machine learning urology and radiology |
| url | https://www.frontiersin.org/articles/10.3389/fonc.2023.1284040/full |
| work_keys_str_mv | AT canhu machinelearningbasedcttextureanalysisinthedifferentiationoftesticularmasses AT canhu machinelearningbasedcttextureanalysisinthedifferentiationoftesticularmasses AT xiaomengqiao machinelearningbasedcttextureanalysisinthedifferentiationoftesticularmasses AT zhenyuxu machinelearningbasedcttextureanalysisinthedifferentiationoftesticularmasses AT zhiyuzhang machinelearningbasedcttextureanalysisinthedifferentiationoftesticularmasses AT xuefengzhang machinelearningbasedcttextureanalysisinthedifferentiationoftesticularmasses |