Purpose We sought to develop machine learning models to detect multileaf collimator (MLC) modeling errors with the use of radiomic features of fluence maps measured in patient‐specific quality assurance (QA) for intensity‐modulated radiation therapy (IMRT) with an electric portal imaging device (EPID). Methods Fluence maps measured with EPID for 38 beams from 19 clinical IMRT plans were assessed. Plans with various degrees of error in MLC modeling parameters [i.e., MLC transmission factor (TF) and dosimetric leaf gap (DLG)] and plans with an MLC positional error for comparison were created. For a total of 152 error plans for each type of error, we calculated fluence difference maps for each beam by subtracting the calculated maps from the measured maps. A total of 837 radiomic features were extracted from each fluence difference map, and we determined the number of features used for the training dataset in the machine learning models by using random forest regression. Machine learning models using the five typical algorithms [decision tree, k‐nearest neighbor (kNN), support vector machine (SVM), logistic regression, and random forest] for binary classification between the error‐free plan and the plan with the corresponding error for each type of error were developed. We used part of the total dataset to perform fourfold cross‐validation to tune the models, and we used the remaining test dataset to evaluate the performance of the developed models. A gamma analysis was also performed between the measured and calculated fluence maps with the criteria of 3%/2 and 2%/2 mm for all of the types of error. Results The radiomic features and its optimal number were similar for the models for the TF and the DLG error detection, which was different from the MLC positional error. The highest sensitivity was obtained as 0.913 for the TF error with SVM and logistic regression, 0.978 for the DLG error with kNN and SVM, and 1.000 for the MLC positional error with kNN, SVM, and random forest. The highest specificity was obtained as 1.000 for the TF error with a decision tree, SVM, and logistic regression, 1.000 for the DLG error with a decision tree, logistic regression, and random forest, and 0.909 for the MLC positional error with a decision tree and logistic regression. The gamma analysis showed the poorest performance in which sensitivities were 0.737 for the TF error and the DLG error and 0.882 for the MLC positional error for 3%/2 mm. The addition of another type of error to fluence maps significantly reduced the sensitivity for the TF and the DLG error, whereas no effect was observed for the MLC positional error detection. Conclusions Compared to the conventional gamma analysis, the radiomics‐based machine learning models showed higher sensitivity and specificity in detecting a single type of the MLC modeling error and the MLC positional error. Although the developed models need further improvement for detecting multiple types of error, radiomics‐based IMRT QA was shown to be a promising approach for detecting the MLC modeli...

No abstract

No abstract

Purpose: We calculated the dosimetric indices and estimated the tumor control probability (TCP) considering six degree-of-freedom (6DoF) patient setup errors in stereotactic radiosurgery (SRS) using a single-isocenter technique.Methods: We used simulated spherical gross tumor volumes (GTVs) with diameters of 1.0 cm (GTV 1), 2.0 cm (GTV 2), and 3.0 cm (GTV 3), and the distance (d) between the target center and isocenter was set to 0, 5, and 10 cm. We created the dose distribution by convolving the blur component to uniform dose distribution. The prescription dose was 20 Gy and the dose distribution was adjusted so that D95 (%) of each GTV was covered by 100% of the prescribed dose. The GTV was simultaneously rotated within 0°-1.0°(δR) around the x-, y-, and z-axes and then translated within 0-1.0 mm (δT) in the x-, y-, and z-axis directions. D95, conformity index (CI), and conformation number (CN) were evaluated by varying the distance from the isocenter. The TCP was estimated by translating the calculated dose distribution into a biological response. In addition, we derived the x-y-z coordinates with the smallest TCP reduction rate that minimize the sum of squares of the residuals as the optimal isocenter coordinates using the relationship between 6DoF setup error, distance from isocenter, and GTV size.Results: D95, CI, and CN were decreased with increasing isocenter distance, decreasing GTV size, and increasing setup error. TCP of GTVs without 6DoF setup error was estimated to be 77.0%. TCP were 25.8% (GTV 1), 35.0% (GTV 2), and 53.0% (GTV 3) with (d, δT , δR) = (10 cm, 1.0 mm, 1.0°). The TCP was 52.3% (GTV 1), 54.9% (GTV 2), and 66.1% (GTV 3) with (d, δT , δR) = (10 cm, 1.0 mm, 1.0°) at the optimal isocenter position. Conclusion:The TCP in SRS for multiple brain metastases with a single-isocenter technique may decrease with increasing isocenter distance and decreasing GTV size when the 6DoF setup errors are exceeded (1.0 mm, 1.0°). Additionally, it might be possible to better maintain TCP for GTVs with 6DoF setup errors by using the optimal isocenter position.

This study investigated the efficacy and safety of radiotherapy as part of multidisciplinary therapy for advanced hepatocellular carcinoma (HCC). Clinical data of 49 HCC patients treated with radiotherapy were assessed retrospectively. The efficacy of radiotherapy was assessed by progression-free survival, disease control rate, and overall survival. Safety was assessed by symptoms and hematological assay, and changes in hepatic reserve function were determined by Child–Pugh score and albumin–bilirubin (ALBI) score. Forty patients underwent curative radiotherapy, and nine patients with portal vein tumor thrombus (PVTT) underwent palliative radiotherapy as part of multidisciplinary therapy. Local disease control for curative therapy was 80.0% and stereotactic body radiotherapy was 86.7% which was greater than that of conventional radiotherapy (60.0%). Patients with PVTT had a median observation period of 651 days and 75% three-year survival when treated with multitherapy, including radiotherapy for palliative intent, transcatheter arterial chemoembolization, and administration of molecular targeted agents. No adverse events higher than grade 3 and no changes in the Child–Pugh score and ALBI score were seen. Radiotherapy is safe and effective for HCC treatment and can be a part of multidisciplinary therapy.