Prediction of dose deposition matrix using voxel features driven machine learning approach.

OBJECTIVES: A dose deposition matrix (DDM) prediction method using several voxel features and a machine learning (ML) approach is proposed for plan optimization in radiation therapy. METHODS: Head and lung cases with the inhomogeneous medium are used as training and testing data. The prediction model is a cascade forward backprop neural network where the input is the features of the voxel, including 1) voxel to body surface distance along the beamlet axis, 2) voxel to beamlet axis distance, 3) voxel density, 4) heterogeneity corrected voxel to body surface distance, 5) heterogeneity corrected voxel to beamlet axis, and (6) the dose of voxel obtained from the pencil beam (PB) algorithm. The output is the predicted voxel dose corresponding to a beamlet. The predicted DDM was used for plan optimization (ML method) and compared with the dose of MC-based plan optimization (MC method) and the dose of pencil beam-based plan optimization (PB method). The mean absolute error (MAE) value was calculated for full volume relative to the dose of the MC method to evaluate the overall dose performance of the final plan. RESULTS: For patient with head tumor, the ML method achieves MAE value 0.49 × 10-4 and PB has MAE 1.86 × 10-4. For patient with lung tumor, the ML method has MAE 1.42 × 10-4 and PB has MAE 3.72 × 10-4. The maximum percentage difference in PTV dose coverage (D98) between ML and MC methods is no more than 1.2% for patient with head tumor, while the difference is larger than 10% using the PB method. For patient with lung tumor, the maximum percentage difference in PTV dose coverage (D98) between ML and MC methods is no more than 2.1%, while the difference is larger than 16% using the PB method. CONCLUSIONS: In this work, a reliable DDM prediction method is established for plan optimization by applying several voxel features and the ML approach. The results show that the ML method based on voxel features can obtain plans comparable to the MC method and is better than the PB method in achieving accurate dose to the patient, which is helpful for rapid plan optimization and accurate dose calculation. ADVANCES IN KNOWLEDGE: Establishment of a new machine learning method based on the relationship between the voxel and beamlet features for dose deposition matrix prediction in radiation therapy.

Optimizing acute stroke outcome prediction models: Comparison of generalized regression neural networks and logistic regressions.

BACKGROUND: Generalized regression neural network (GRNN) and logistic regression (LR) are extensively used in the medical field; however, the better model for predicting stroke outcome has not been established. The primary goal of this study was to compare the accuracies of GRNN and LR models to identify the most optimal model for the prediction of acute stroke outcome, as well as explore useful biomarkers for predicting the prognosis of acute stroke patients. METHOD: In a single-center study, 216 (80% for the training set and 20% for the test set) acute stroke patients admitted to the Shenzhen Second People's Hospital between December 2019 to June 2021 were retrospectively recruited. The functional outcomes of the patients were measured using Barthel Index (BI) on discharge. A training set was used to optimize the GRNN and LR models. The test set was utilized to validate and compare the performances of GRNN and LR in predicting acute stroke outcome based on the area under the receiver operating characteristic curve (AUROC), accuracy, sensitivity, and the Kappa value. RESULT: The LR analysis showed that age, the National Institute Health Stroke Scale score, BI index, hemoglobin, and albumin were independently associated with stroke outcome. After validating in test set using these variables, we found that the GRNN model showed a better performance based on AUROC (0.931 vs 0.702), sensitivity (0.933 vs 0.700), specificity (0.889 vs 0.722), accuracy (0.896 vs 0.729), and the Kappa value (0.775 vs 0.416) than the LR model. CONCLUSION: Overall, the GRNN model demonstrated superior performance to the LR model in predicting the prognosis of acute stroke patients. In addition to its advantage in not affected by implicit interactions and complex relationship in the data. Thus, we suggested that GRNN could be served as the optimal statistical model for acute stroke outcome prediction. Simultaneously, prospective validation based on more variables of the GRNN model for the prediction is required in future studies.

Prediction of dose-volume histograms in nasopharyngeal cancer IMRT using geometric and dosimetric information.

A method using both patient geometric and dosimetric information was proposed to predict dose-volume histograms (DVHs) of organs at risk (OARs) for a nasopharyngeal cancer (NPC) intensity-modulated radiation therapy (IMRT) plan. A total of 106 nine-field IMRT NPC plans were used in this study. Twenty-six plans were randomly selected as testing cases, and the remaining plans were used as the training data. A method employing geometric and dosimetric information was developed for OAR DVH prediction. The dosimetric information was derived from an initial dose calculation using a simple unoptimized conformal plan. The DVHs were also predicted using only the geometric information. The DVH prediction model was a generalized regression neural network (GRNN). Mean absolute error (MAE) and R 2 values were introduced to evaluate DVH prediction accuracy. Significant differences in the DVH prediction accuracy were found between the method employing the geometric and dosimetric information and the method utilizing the geometric information for the brainstem (R 2, 0.98 versus 0.95, p  = 0.007; MAE, 3.52% versus 7.19%, p  = 0.002), spinal cord (R 2, 0.98 versus 0.96, p  < 0.001; MAE, 2.80% versus 4.36%, p  < 0.001), left optic nerve (R 2, 0.90 versus 0.77, p  = 0.014; MAE, 3.07% versus 11.29%, p  = 0.025) and other organs. On average, the R 2 value increased by ~6.7% and the MAE value decreased by ~46.7% after adding the dosimetric information to the DVH prediction. We developed a method for predicting DVHs of OARs in NPC IMRT plans by using geometric and dosimetric information. Adding dosimetric information can help predict the DVHs of OARs in NPC IMRT plans.