The objective of this study was to explore radiomics features from longitudinal diffusion-weighted MRIs (DWIs) for pathologic treatment effect prediction in patients with localized soft tissue sarcoma (STS) undergoing hypofractionated preoperative radiotherapy (RT). Thirty patients with localized STS treated with preoperative hypofractionated RT were recruited to this longitudinal imaging study. DWIs were acquired at three time points using a 0.35 T MRI-guided radiotherapy system. Treatment effect score (TES) was obtained from the post-surgery pathology as a surrogate of treatment outcome. Patients were divided into two groups based on TES. Response prediction was first performed using a support vector machine (SVM) with only mean apparent diffusion coefficient (ADC) or delta ADC to serve as the benchmark. Radiomics features were then extracted from tumor ADC maps at each of the three time points. Logistic regression and SVM were constructed to predict the TES group using features selected by univariate analysis and sequential forward selection. Classification performance using SVM with features from different time points and with or without delta radiomics were evaluated. Prediction performance using only mean ADC or delta ADC was poor (area under the curve (AUC) < 0.7). For the radiomics study using features from all time points and corresponding delta radiomics, SVM significantly outperformed logistic regression (AUC of 0.91 ± 0.05 v.s. 0.85 ± 0.06). Prediction AUC values using single or multiple time points without delta radiomics were all below 0.74. Including delta radiomics of mid- or post-treatment relative to the baseline drastically boosted the prediction. In this work, an SVM model was built to predict the TES using radiomics features from longitudinal DWI. Based on this study, we found that use of mean ADC, delta ADC, or radiomics features alone was not sufficient for response prediction, and including delta radiomics features of mid- or post-treatment relative to the baseline can optimize the prediction of TES, a pathologic and clinical endpoint.

Detection of brain metastases is a paramount task in cancer management due both to the number of high-risk patients and the difficulty of achieving consistent detection. In this study, we aim to improve the accuracy of automated brain metastasis (BM) detection methods using a novel asymmetric UNet (asym-UNet) architecture. An end-to-end asymmetric 3D-UNet architecture, with two down-sampling arms and one up-sampling arm, was constructed to capture the imaging features. The two down-sampling arms were trained using two different kernels (3 × 3 × 3 and 1 × 1 × 3, respectively) with the kernel (1 × 1 × 3) dominating the learning. As a comparison, vanilla single 3D UNets were trained with different kernels and evaluated using the same datasets. Voxel-based Dice similarity coefficient (DSC _v ), sensitivity ( S _v ), precision ( P _v ), BM-based sensitivity ( S _BM ), and false detection rate ( F _BM ) were used to evaluate model performance. Contrast-enhanced T1 MR images from 195 patients with a total of 1034 BMs were solicited from our institutional stereotactic radiosurgery database. The patient cohort was split into training (160 patients, 809 lesions), validation (20 patients, 136 lesions), and testing (15 patients, 89 lesions) datasets. The lesions in the testing dataset were further divided into two subgroups based on the diameters (small S = 1–10 mm, large L = 11–26 mm). In the testing dataset, there were 72 and 17 BMs in the S and L sub-groups, respectively. Among all trained networks, asym-UNet achieved the highest DSC _v of 0.84 and lowest F _BM of 0.24. Although vanilla 3D-UNet with a single 1 × 1 × 3 kernel achieved the highest sensitivities for the S group, it resulted in the lowest precision and highest false detection rate. Asym-UNet was shown to balance sensitivity and false detection rate as well as keep the segmentation accuracy high. The novel asym-UNet segmentation network showed overall competitive segmentation performance and more pronounced improvement in hard-to-detect small BMs comparing to the vanilla single 3D UNet.

Electron density maps must be accurately estimated to achieve valid dose calculation in MR-only radiotherapy. The goal of this study is to assess whether two deep learning models, the conditional generative adversarial network (cGAN) and the cycle-consistent generative adversarial network (cycleGAN), can generate accurate abdominal synthetic CT (sCT) images from 0.35T MR images for MR-only liver radiotherapy. A retrospective study was performed using CT images and 0.35T MR images of 12 patients with liver (n = 8) and non-liver abdominal (n = 4) cancer. CT images were deformably registered to the corresponding MR images to generate deformed CT (dCT) images for treatment planning. Both cGAN and cycleGAN were trained using MR and dCT transverse slices. Four-fold cross-validation testing was conducted to generate sCT images for all patients. The HU prediction accuracy was evaluated by voxel-wise similarity metric between each dCT and sCT image for all 12 patients. dCT-based and sCT-based dose distributions were compared using gamma and dose-volume histogram (DVH) metric analysis for 8 liver patients. sCT _cycleGAN achieved the average mean absolute error (MAE) of 94.1 HU, while sCT _cGAN achieved 89.8 HU. In both models, the average gamma passing rates within all volumes of interest were higher than 95% using a 2%, 2 mm criterion, and 99% using a 3%, 3 mm criterion. The average differences in the mean dose and DVH metrics were within ±0.6% for the planning target volume and within ±0.15% for evaluated organs in both models. Results : demonstrated that abdominal sCT images generated by both cGAN and cycleGAN achieved accurate dose calculation for 8 liver radiotherapy plans. sCT _cGAN images had smaller average MAE and achieved better dose calculation accuracy than sCTcyleGAN images. More abdominal patients will be enrolled in the future to further evaluate the two models.

Existing volumetric modulated arc therapy (VMAT) optimization using coplanar arcs is highly efficient but usually dosimetrically inferior to intensity modulated radiation therapy (IMRT) with optimized non-coplanar beams. To achieve both dosimetric quality and delivery efficiency, we proposed in this study, a novel integrated optimization method for non-coplanar VMAT (4 π VMAT). 4 π VMAT with direct aperture optimization (DAO) was achieved by utilizing a least square dose fidelity objective, along with an anisotropic total variation term for regularizing the fluence smoothness, a single segment term for imposing simple apertures, and a group sparsity term for selecting beam angles. Continuous gantry/couch angle trajectories were selected using the Dijkstra’s algorithm, where the edge and node costs were determined based on the maximal gantry rotation speed and the estimated fluence map at the current iteration, respectively. The couch–gantry–patient collision space was calculated based on actual machine geometry and a human subject 3D surface. Beams leading to collision are excluded from the DAO and beam trajectory selection (BTS). An alternating optimization strategy was implemented to solve the integrated DAO and BTS problem. The feasibility of 4 π VMAT using one full-arc or two full-arcs was tested on nine patients with brain, lung, or prostate cancer. The plan was compared against a coplanar VMAT (2 π VMAT) plan using one additional arc and collimator rotation. Compared to 2 π VMAT, 4 π VMAT reduced the average maximum and mean organs-at-risk dose by 9.63% and 3.08% of the prescription dose with the same target coverage. R50 was reduced by 23.0%. Maximum doses to the dose limiting organs, such as the brainstem, the major vessels, and the proximal bronchus, were reduced by 8.1 Gy (64.8%), 16.3 Gy (41.5%), and 19.83 Gy (55.5%), respectively. The novel 4 π VMAT approach affords efficient delivery of non-coplanar arc trajectories that lead to dosimetric improvements compared with coplanar VMAT using more arcs.