Purpose. To develop and evaluate the performance of a deep learning model to generate synthetic pulmonary perfusion images from clinical 4DCT images for patients undergoing radiotherapy for lung cancer. Methods. A clinical data set of 58 pre- and post-radiotherapy 99mTc-labeled MAA-SPECT perfusion studies (32 patients) each with contemporaneous 4DCT studies was collected. Using the inhale and exhale phases of the 4DCT, a 3D-residual network was trained to create synthetic perfusion images utilizing the MAA-SPECT as ground truth. The training process was repeated for a 50-imaging study, five-fold validation with twenty model instances trained per fold. The highest performing model instance from each fold was selected for inference upon the eight-study test set. A manual lung segmentation was used to compute correlation metrics constrained to the voxels within the lungs. From the pre-treatment test cases (N = 5), 50th percentile contours of well-perfused lung were generated from both the clinical and synthetic perfusion images and the agreement was quantified. Results. Across the hold-out test set, our deep learning model predicted perfusion with a Spearman correlation coefficient of 0.70 (IQR: 0.61–0.76) and a Pearson correlation coefficient of 0.66 (IQR: 0.49–0.73). The agreement of the functional avoidance contour pairs was Dice of 0.803 (IQR: 0.750–0.810) and average surface distance of 5.92 mm (IQR: 5.68–7.55). Conclusion. We demonstrate that from 4DCT alone, a deep learning model can generate synthetic perfusion images with potential application in functional avoidance treatment planning.
The plots of standard deviation of CT number of pixel inside CTV and PTV for these 10-phase image sets showed irregularity for different patients. Conclusion: In current imaging technology, there was no significant feature found in this high-order image pixel analysis for providing a threshold to limit the subjective factor of clinician in delineation of tumor target and margin tactics is employed in clinical practice for cure rate control. Further potential improvement should include large cohort of patient data collection, precise selection of target location, combination of different imaging modalities investigation of special algorithm for boundary noise process and high order imaging information in dignostic application.
In this work, the multilayer perceptron model was used to forecast the time series of global solar radiation for a near future about a week. Different architectures of this model were built through varying its different hyperparameters such as optimizers, activation functions, number of neurons and neuron dropout in which their performance was evaluated using error metrics. It was found that the architectures (60, SGD, Sigmoid), (10, Adam, Relu) and (60, SGD, Sigmoid) presented an R2 around 0.877, 0.873 and 0.872, respectively. The architecture with neuron dropout (150, SGD, Sigmoid, 0.2) presented a higher performance among all the architectures evaluated and its R2 value was 0.884. Architectures with higher performance are used to predict future values of solar radiation.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.