Purpose This study was designed to provide the foundation for combining immunotherapy to induce tumor antigen-specific T cells with proton radiation therapy to exploit the activity of those T cells. We have recently defined “immunogenic modulation,” a mechanism distinct from immunogenic cell death, whereby tumor cells surviving photon radiation therapy nonetheless become more susceptible to cytotoxic T lymphocyte (CTL)-mediated lysis. However, to our knowledge, there are no prior studies examining the role of proton radiation on tumor immune sensitivity. Materials and Methods Using cell lines of tumors frequently treated with proton radiation, such as prostate, breast, lung, and chordoma, we examined the effect of proton radiation on the viability and induction of immunogenic modulation in tumor cells by flow cytometric and immunofluorescent analysis of surface phenotype and the functional immune consequences. Results These studies show for the first time that a) proton and photon radiation induced comparable upregulation of surface molecules involved in immune recognition (HLA, ICAM-1, and the tumor-associated antigens CEA and MUC-1), b) proton radiation mediated calreticulin cell-surface expression, increasing sensitivity to cytotoxic T-lymphocyte killing of tumor cells, and c) cancer stem cells (CSCs), which are resistant to the direct cytolytic activity of proton radiation, nonetheless upregulated calreticulin after radiation in a manner similar to non-CSCs. Conclusions These findings offer a rationale for the use of proton radiation in combination with immunotherapy, including for patients who have failed radiation therapy alone or have limited treatment options.

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 (DSCv), 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 DSCv 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.

Conventional radiation therapy of brain tumors often produces cognitive deficits, particularly in children. We investigated the potential efficacy of merging Orthovoltage X-ray Minibeams (OXM). It segments the beam into an array of parallel, thin (~0.3 mm), planar beams, called minibeams, which are known from synchrotron x-ray experiments to spare tissues. Furthermore, the slight divergence of the OXM array make the individual minibeams gradually broaden, thus merging with their neighbors at a given tissue depth to produce a solid beam. In this way the proximal tissues, including the cerebral cortex, can be spared. Here we present experimental results with radiochromic films to characterize the method’s dosimetry. Furthermore, we present our Monte Carlo simulation results for physical absorbed dose, and a first-order biologic model to predict tissue tolerance. In particular, a 220-kVp orthovoltage beam provides a 5-fold sharper lateral penumbra than a 6-MV x-ray beam. The method can be implemented in arc-scan, which may include volumetric-modulated arc therapy (VMAT). Finally, OXM’s low beam energy makes it ideal for tumor-dose enhancement with contrast agents such as iodine or gold nanoparticles, and its low cost, portability, and small room-shielding requirements make it ideal for use in the low-and-middle-income countries.

The Grade of meningioma has significant implications for selecting treatment regimens ranging from observation to surgical resection with adjuvant radiation. For most patients, meningiomas are diagnosed radiologically, and Grade is not determined unless a surgical procedure is performed. The goal of this study is to train a novel auto-classification network to determine Grade I and II meningiomas using T1-contrast enhancing (T1-CE) and T2-Fluid attenuated inversion recovery (FLAIR) magnetic resonance (MR) images. Ninety-six consecutive treatment naïve patients with pre-operative T1-CE and T2-FLAIR MR images and subsequent pathologically diagnosed intracranial meningiomas were evaluated. Delineation of meningiomas was completed on both MR images. A novel asymmetric 3D convolutional neural network (CNN) architecture was constructed with two encoding paths based on T1-CE and T2-FLAIR. Each path used the same 3 × 3 × 3 kernel with different filters to weigh the spatial features of each sequence separately. Final model performance was assessed by tenfold cross-validation. Of the 96 patients, 55 (57%) were pathologically classified as Grade I and 41 (43%) as Grade II meningiomas. Optimization of our model led to a filter weighting of 18:2 between the T1-CE and T2-FLAIR MR image paths. 86 (90%) patients were classified correctly, and 10 (10%) were misclassified based on their pre-operative MRs with a model sensitivity of 0.85 and specificity of 0.93. Among the misclassified, 4 were Grade I, and 6 were Grade II. The model is robust to tumor locations and sizes. A novel asymmetric CNN with two differently weighted encoding paths was developed for successful automated meningioma grade classification. Our model outperforms CNN using a single path for single or multimodal MR-based classification.

Purposes Preimplant diagnostic magnetic resonance imaging is the gold standard for image‐guided tandem‐and‐ovoids (T&O) brachytherapy for cervical cancer. However, high dose rate brachytherapy planning is typically done on postimplant CT‐based high‐risk clinical target volume (HR‐CTVCT) because the transfer of preimplant Magnetic resonance (MR)‐based HR‐CTV (HR‐CTVMR) to the postimplant planning CT is difficult due to anatomical changes caused by applicator insertion, vaginal packing, and the filling status of the bladder and rectum. This study aims to train a dual‐path convolutional neural network (CNN) for automatic segmentation of HR‐CTVCT on postimplant planning CT with guidance from preimplant diagnostic MR. Methods Preimplant T2‐weighted MR and postimplant CT images for 65 (48 for training, eight for validation, and nine for testing) patients were retrospectively solicited from our institutional database. MR was aligned to the corresponding CT using rigid registration. HR‐CTVCT and HR‐CTVMR were manually contoured on CT and MR by an experienced radiation oncologist. All images were then resampled to a spatial resolution of 0.5 × 0.5 × 1.25 mm. A dual‐path 3D asymmetric CNN architecture with two encoding paths was built to extract CT and MR image features. The MR was masked by HR‐CTVMR contour while the entire CT volume was included. The network put an asymmetric weighting of 18:6 for CT: MR. Voxel‐based dice similarity coefficient (DSCV), sensitivity, precision, and 95% Hausdorff distance (95‐HD) were used to evaluate model performance. Cross‐validation was performed to assess model stability. The study cohort was divided into a small tumor group (<20 cc), medium tumor group (20–40 cc), and large tumor group (>40 cc) based on the HR‐CTVCT for model evaluation. Single‐path CNN models were trained with the same parameters as those in dual‐path models. Results For this patient cohort, the dual‐path CNN model improved each of our objective findings, including DSCV, sensitivity, and precision, with an average improvement of 8%, 7%, and 12%, respectively. The 95‐HD was improved by an average of 1.65 mm compared to the single‐path model with only CT images as input. In addition, the area under the curve for different networks was 0.86 (dual‐path with CT and MR) and 0.80 (single‐path with CT), respectively. The dual‐path CNN model with asymmetric weighting achieved the best performance with DSCV of 0.65 ± 0.03 (0.61–0.70), 0.79 ± 0.02 (0.74–0.85), and 0.75 ± 0.04 (0.68–0.79) for small, medium, and large group. 95‐HD were 7.34 (5.35–10.45) mm, 5.48 (3.21–8.43) mm, and 6.21 (5.34–9.32) mm for the three size groups, respectively. Conclusions An asymmetric CNN model with two encoding paths from preimplant MR (masked by HR‐CTVMR) and postimplant CT images was successfully developed for automatic segmentation of HR‐CTVCT for T&O brachytherapy patients.