Research Article
Effect of Kernel Functions on the Performance of Support Vector Regression Algorithm in Predicting Patient-Specific Organ Doses from CT Scans
Wencheng Shao
,
Xin Lin,
Ying Huang,
Liangyong Qu,
Weihai Zhuo*,
Haikuan Liu*
Issue:
Volume 11, Issue 1, March 2025
Pages:
1-11
Received:
11 February 2025
Accepted:
20 February 2025
Published:
21 March 2025
Abstract: Background: CT examinations are commonly utilized for the diagnosis of internal diseases. The X-rays emitted during CT scans can elevate the risks of developing solid cancers by causing DNA damage. The risk of CT scan-induced solid cancers is intricately linked to the organ doses specific to each patient. The Support Vector Regression (SVR) algorithm exhibits the capability to swiftly and accurately predict organ doses. Kernel functions, including linear, polynomial, and radial basis (RBF) functions, play a crucial role in the overall performance of SVR when predicting patient-specific organ doses from CT scans. Therefore, it is imperative to investigate the influence of kernel selection on the comprehensive predictive effectiveness of SVR. Purpose: This study investigates the impact of kernel functions on the predictive performance of SVR models trained by radiomics features, and to pinpoint the optimal kernel function for predicting patient-specific organ doses from CT scans. Methods: CT images from head and abdominal CT scans were processed using DeepViewer®, an auto-segmentation tool for defining regions of interest (ROIs) within their organs. Radiomics features were extracted from the CT data and ROIs. Benchmark organ doses were calculated through Monte Carlo simulations. SVR models, utilizing the radiomics features, were trained with linear-, polynomial-, and RBF kernels to predict patient-specific organ doses from CT scans. The robustness of the SVR prediction was examined by applying 25 random sample splits with each kernel. The mean absolute percentage error (MAPE) and coefficient of determination (R2) were compared among the kernels to identify the optimal kernel. Results: The linear kernel obtains better overall predictive performance than the polynomial and RBF kernels. The SVR trained with the linear kernel function achieves lower MAPE values, below 5% for head organs and under 6.8% for abdominal organs. Furthermore, it shows higher R2 values exceeding 0.85 for head organs and going beyond 0.8 for abdominal organs. Conclusions: Kernel selection severely impact the overall performance of SVR models. The optimal kernel varies with CT scanned parts and organ types indicating the necessity to conduct organ-specific kernel selection.
Abstract: Background: CT examinations are commonly utilized for the diagnosis of internal diseases. The X-rays emitted during CT scans can elevate the risks of developing solid cancers by causing DNA damage. The risk of CT scan-induced solid cancers is intricately linked to the organ doses specific to each patient. The Support Vector Regression (SVR) algorit...
Show More
Research Article
Indoor Radon Survey in Some Buildings of Mkwawa University College of Education
Anaceth Mwijage Adrian,
Frank Amos Kisinza,
Maria Kalisti Amma,
Amos Vincent Ntarisa*
Issue:
Volume 11, Issue 1, March 2025
Pages:
12-22
Received:
18 April 2025
Accepted:
10 May 2025
Published:
18 June 2025
DOI:
10.11648/j.rst.20251101.12
Downloads:
Views:
Abstract: Background: Radon is a radioactive gas that is found all over the world and is well-known for its capacity to induce lung cancer. Purpose: This study aimed at the determination of indoor radon and its association with the excess lifetime cancer risk (ELCR) and annual effective dose in Mkwawa University College of Education (MUCE). Methods: The measurements of indoor radon concentrations were carried out using radon eye. Results: It was found that the indoor radon concentrations ranged from 0-55.7±4.0 Bq/m3 with an arithmetic mean of 12.2±3.5 Bq/m3 which are all below the limit of 100 Bq/m3 set by WHO. The annual effective dose was estimated in the range of 0.01-0.69 mSv/y with an average of 0.165±0.075 mSv/y which are below the limit of 1 mSv set by ICRP. The ELCR was estimated to be in the range of 0.035-2.415×10-3 with the mean value of 0.588±0.262×10-3 which are below 1.45×10-3 the value of world average. The lung cancer cases per million people per year (LCC) was estimated in the range values of 0.18-12.42 per million persons with mean value of 3.015±1.355 per million persons. The LCC obtained in this study is below the ICRP recommended limit of 170-230 per million persons. Conclusion: The results of indoor radon concentration obtained in this study are well below the limits set by WHO, EPA and ICRP. Hence, the students and staff at MUCE are all safe as the annual effective dose, ELCR, LCC due to radon exposure are within the allowable limits.
Abstract: Background: Radon is a radioactive gas that is found all over the world and is well-known for its capacity to induce lung cancer. Purpose: This study aimed at the determination of indoor radon and its association with the excess lifetime cancer risk (ELCR) and annual effective dose in Mkwawa University College of Education (MUCE). Methods: The meas...
Show More
