Search

To predict clinical response in locally advanced cervical cancer (LACC) patients by a combination of measures, including clinical and brachytherapy parameters and several machine learning (ML) approaches.Brachytherapy features such as insertion approaches, source metrics, dosimetric, and clinical measures were used for modeling. Four different ML approaches, including LASSO, Ridge, support vector machine (SVM), and Random Forest (RF), were applied to extracted measures for model development alone or in combination. Model performance was evaluated using the area under the curve (AUC) of receiver operating characteristics curve, sensitivity, specificity, and accuracy. Our results were compared with a reference model developed by simple logistic regression applied to three distinct clinical features identified by previous papers.One hundred eleven LACC patients were included. Nine data sets were obtained based on the features, and 36 predictive models were built. In terms of AUC, the model developed using RF applied to dosimetric, physical, and total BT sessions features were found as the most predictive [AUC; 0.82 (0.95 confidence interval (CI); 0.79 -0.93), sensitivity; 0.79, specificity; 0.76, and accuracy; 0.77]. The AUC (0.95 CI), sensitivity, specificity, and accuracy for the reference model were found as 0.56 (0.52 ...0.68), 0.51, 0.51, and 0.48, respectively. Most RF models had significantly better performance than the reference model (Bonferroni corrected p-value0.0014).Brachytherapy response can be predicted using dosimetric and physical parameters extracted from treatment parameters. Machine learning algorithms, including Random Forest, could play a critical role in such predictive modeling.

This study aims to measure the reproducibility of radiomics features in ankle bone radiography over changes in post-processing parameters including contrast, edge enhancement and latitude. Lateral ankle bone radiographies for sixty patients were obtained from three digital radiology centers. All images were acquired by same image acquisition settings. A two-dimensional region of interest was drawn in any image and 93 features from 6 feature sets including first and second order were extracted. The coefficient of variation (COV) and intraclass correlation coefficient (ICC) were calculated to assess feature reproducibility for each center and among all centers in three scenarios: Adams (Nat Rev Endocrinol 9(1):28, 2013) ten different contrast Brown et al. (J Med Imaging 5(1):011017, 2018) ten different edge enhancement and Hirvasniemi et al. (Osteoarthr Cartilage 27(6):906-914, 2019) ten different image latitude parameters. Based on ICC analysis, it is observed that 46-100-44% of Histogram, 54-72-42% of GLCM, 43-76-36% of GLDM, 60-90-17% of GLRLM, 33-19-21% of GLSZM and 13-20-0% of NGTDM radiomics features had 90%ICC 100% over changes in contrast-edge enhancement-latitude changes respectively. Based on COV, GLRLM was only feature set that 100% of their features had COV ≤ 5% over changes in contrast and edge enhancement. The results presented here, indicating that radiomics features extracted are vulnerable over changes in contrast, edge enhancement and latitude. The most reproducible features that introduced in this study could be used for further clinical decision making.

Background Radiomics features reproducibility assessment is a critical issue in imaging biomarker development era. In the present study, we aimed to assess test–retest reproducibility analysis of bone mineral densitometry (BMD) image radiomics features. Methods In this prospective research work, eighteen patients were included and were subjected to DXA BMD scans acquired within 10 min of each other under an approved protocol. Seven regions of interest (ROIs) including four lumbar spine regions (L1-L4) and three hip regions (trochanteric, inter trochanteric and neck) in both test and re-test images were segmented and 107 radiomics features from seven different feature sets were extracted. Intra-class correlation coefficient (ICC) were initially used to estimate radiomics features reproducibility. Results We showed that there is no radiomics feature with 90% < ICC

Auditing the treatment planning system (TPS) software for a radiotherapy unit is of paramount importance in any radiation therapy department. A Plexiglas phantom was proposed to measure the ionization ofAuditing was performed using a Plexiglas phantom in an end-to-end test, and relative dose points were detected by a farmer-type ionization chamber and compared with the relative dose of similar points in TPS. The audit results were determined as pass optimal level (3.3%), pass action level (between 3.3% and 5%), and out of tolerance (5%).The comparison of the collected data revealed that 80% of the measured values were ≤5% in the pass level, and 20% of the points were out of tolerance (between 5% and 6.99%).This study documented the appropriateness of the dosimetry audit test and this phantom design for the HDR brachytherapy TPS.

Background Wedge filters are commonly used in radiation oncology for eliminating hot spots and creating a uniform dose distribution in optimizing isodose curves in the target volume for clinical aspects. These are some limited standard physical wedges (15°, 30°, 45°, 60°),or creating an arbitrary wedge angle, like motorized wedge or dynamic wedge,... The new formulation is presented by the combination of wedge fields for determining an arbitrary effective wedge angles. The isodose curves also are derived for these wedges. Materials and methods we performed the dosimetry of Varian Clinac 2100C/D with Scanditronix Wellhofer water blue phantom, CU500E, OmniPro - Accept software and 0.13cc ionization chamber for 6Mv photon beam in depth of 10cm (reference depth) for universal physical wedges (15°, 30°, 45°, and 60°) and reference field 10x10cm2. By combining the isodose curve standard wedge fields with compatible weighting dose for each field, the effective isodose curve is calculated for any wedge angle. Results The relation between a given effective wedge angle and the weighting of each combining wedge fields was derived. A good agreement was found between the measured and calculated wedge angles and the maximum deviation did not exceed 3°. The difference between the measured and calculated data decreased when the combined wedge angles were closer. The results are in agreement with the motorized single wedge appliance in the literature. Conclusions This technique showed that the effective wedge angle that is obtained from this method is adequate for clinical applications and the motorized wedge formalism is a special case of this consideration.

Background: In radiation therapy, estimation of surface doses is clinically important. This study aimed to obtain an analytical relationship to determine the skin surface dose, kerma and the depth of maximum dose, with energies of 6 and 18 megavoltage (MV). Materials and Methods: To obtain the dose on the surface of skin, using the relationship between dose and kerma and solving differential equations governing the two quantities, a general relationship of dose changes relative to the depth was obtained. By dosimetry all the standard square fields of 5cm×5cm to 40cm×40cm, an equation similar to response to differential equations of the dose and kerma were fitted on the measurements for any field size and energy. Applying two conditions: a) equality of the area under dose distribution and kerma changes in versus depth in 6 and 18 MV, b) equality of the kerma and dose at x=d max and using these results, coefficients of the obtained analytical relationship were determined. By putting the depth of zero in the relation, amount of PDD and kerma on the surface of the skin, could be obtained. Results: Using the MATLAB software, an exponential binomial function with R-Square >0.9953 was determined for any field size and depth in two energy modes 6 and 18MV, the surface PDD and kerma was obtained and both of them increase due to the increase of the field, but they reduce due to increased energy and from the obtained relation, depth of maximum dose can be determined. Conclusions: Using this analytical formula, one can find the skin surface dose, kerma and thickness of the buildup region.