End-to-end validation of fiducial tracking accuracy in robotic radiosurgery using MRI-only simulation imaging.

BACKGROUND: Image-guided radiation-therapy (IGRT)-based robotic radiosurgery using magnetic resonance imaging (MRI)-only simulation could allow for improved target definition with highly conformal radiotherapy treatments. Fiducial marker (FM)-based alignment is used with robotic radiosurgery treatments of sites such as the prostate because it aids in accurate target localization. Synthetic CT (sCT) images are generated in the MRI-only workflow but FMs used for IGRT appear as signal voids in MRIs and do not appear in MR-generated sCTs, hindering the ability to use sCTs for fiducial-based IGRT. PURPOSE: In this study we evaluate the fiducial tracking accuracy for a novel artificial fiducial insertion method in sCT images that allows for fiducial marker tracking in robotic radiosurgery, using MRI-only simulation imaging (MRI-only workflow). METHODS: Artificial fiducial markers were inserted into sCT images at the site of the real marker implantation as visible in MRI. Two phantoms were used in this study. A custom anthropomorphic pelvis phantom was designed to validate the tracking accuracy for a variety of artificial fiducials in an MRI-only workflow. A head phantom containing a hidden target and orthogonal film pair inserts was used to perform end-to-end tests of artificial fiducial configurations inserted in sCT images. The setup and end-to-end targeting accuracy of the MRI-only workflow were compared to the computed tomography (CT)-based standard. Each phantom had six FMs implanted with a minimum spacing of 2 cm. For each phantom a bulk-density sCT was generated, and artificial FMs were inserted at the implantation location. Several methods of FM insertion were tested including: (1) replacing HU with a fixed value (10000HU) (voxel-burned); (2) using a representative fiducial image derived from a linear combination of fiducial templates (composite-fiducial); (3) computationally simulating FM signal voids using a digital phantom containing FMs and inserting the corresponding signal void into sCT images (simulated-fiducial). All tests were performed on a CyberKnife system (Accuray, Sunnyvale, CA). Treatment plans and digital-reconstructed-radiographs were generated from the original CT and sCTs with embedded fiducials and used to align the phantom on the treatment couch. Differences in the initial phantom alignment (3D translations/rotations) and tracking parameters between CT-based plans and sCT-based plans were analyzed. End-to-end plans for both scenarios were generated and analyzed following our clinical protocol. RESULTS: For all plans, the fiducial tracking algorithm was able to identify the fiducial locations. The mean FM-extraction uncertainty for the composite and simulated FMs was below 48% for fiducials in both the anthropomorphic pelvis and end-to-end phantoms, which is below the 70% treatment uncertainty threshold. The total targeting error was within tolerance (<0.95 mm) for end-to-end tests of sCT images with the composite and head-on simulated FMs (0.26, 0.44, and 0.35 mm for the composite fiducial in sCT, head-on simulated fiducial in sCT, and fiducials in original CT, respectively. CONCLUSIONS: MRI-only simulation for robotic radiosurgery could potentially improve treatment accuracy and reduce planning margins. Our study has shown that using a composite-derived or simulated FM in conjunction with sCT images, MRI-only workflow can provide clinically acceptable setup accuracy in line with CT-based standards for FM-based robotic radiosurgery.

Paired conditional generative adversarial network for highly accelerated liver 4D MRI.

Purpose.4D MRI with high spatiotemporal resolution is desired for image-guided liver radiotherapy. Acquiring densely sampling k-space data is time-consuming. Accelerated acquisition with sparse samples is desirable but often causes degraded image quality or long reconstruction time. We propose the Reconstruct Paired Conditional Generative Adversarial Network (Re-Con-GAN) to shorten the 4D MRI reconstruction time while maintaining the reconstruction quality.Methods.Patients who underwent free-breathing liver 4D MRI were included in the study. Fully- and retrospectively under-sampled data at 3, 6 and 10 times (3×, 6× and 10×) were first reconstructed using the nuFFT algorithm. Re-Con-GAN then trained input and output in pairs. Three types of networks, ResNet9, UNet and reconstruction swin transformer (RST), were explored as generators. PatchGAN was selected as the discriminator. Re-Con-GAN processed the data (3D +t) as temporal slices (2D +t). A total of 48 patients with 12 332 temporal slices were split into training (37 patients with 10 721 slices) and test (11 patients with 1611 slices). Compressed sensing (CS) reconstruction with spatiotemporal sparsity constraint was used as a benchmark. Reconstructed image quality was further evaluated with a liver gross tumor volume (GTV) localization task using Mask-RCNN trained from a separate 3D static liver MRI dataset (70 patients; 103 GTV contours).Results.Re-Con-GAN consistently achieved comparable/better PSNR, SSIM, and RMSE scores compared to CS/UNet models. The inference time of Re-Con-GAN, UNet and CS are 0.15, 0.16, and 120 s. The GTV detection task showed that Re-Con-GAN and CS, compared to UNet, better improved the dice score (3× Re-Con-GAN 80.98%; 3× CS 80.74%; 3× UNet 79.88%) of unprocessed under-sampled images (3× 69.61%).Conclusion.A generative network with adversarial training is proposed with promising and efficient reconstruction results demonstrated on an in-house dataset. The rapid and qualitative reconstruction of 4D liver MR has the potential to facilitate online adaptive MR-guided radiotherapy for liver cancer.

MRI-only based material mass density and relative stopping power estimation via deep learning for proton therapy: a preliminary study.

Magnetic Resonance Imaging (MRI) is increasingly being used in treatment planning due to its superior soft tissue contrast, which is useful for tumor and soft tissue delineation compared to computed tomography (CT). However, MRI cannot directly provide mass density or relative stopping power (RSP) maps, which are required for calculating proton radiotherapy doses. Therefore, the integration of artificial intelligence (AI) into MRI-based treatment planning to estimate mass density and RSP directly from MRI has generated significant interest. A deep learning (DL) based framework was developed to establish a voxel-wise correlation between MR images and mass density as well as RSP. To facilitate the study, five tissue substitute phantoms were created, representing different tissues such as skin, muscle, adipose tissue, 45% hydroxyapatite (HA), and spongiosa bone. The composition of these phantoms was based on information from ICRP reports. Additionally, two animal tissue phantoms, simulating pig brain and liver, were prepared for DL training purposes. The phantom study involved the development of two DL models. The first model utilized clinical T1 and T2 MRI scans as input, while the second model incorporated zero echo time (ZTE) MRI scans. In the patient application study, two more DL models were trained: one using T1 and T2 MRI scans as input, and another model incorporating synthetic dual-energy computed tomography (sDECT) images to provide accurate bone tissue information. The DECT empirical model was used as a reference to evaluate the proposed models in both phantom and patient application studies. The DECT empirical model was selected as the reference for evaluating the proposed models in both phantom and patient application studies. In the phantom study, the DL model based on T1, and T2 MRI scans demonstrated higher accuracy in estimating mass density and RSP for skin, muscle, adipose tissue, brain, and liver. The mean absolute percentage errors (MAPE) were 0.42%, 0.14%, 0.19%, 0.78%, and 0.26% for mass density, and 0.30%, 0.11%, 0.16%, 0.61%, and 0.23% for RSP, respectively. The DL model incorporating ZTE MRI further improved the accuracy of mass density and RSP estimation for 45% HA and spongiosa bone, with MAPE values of 0.23% and 0.09% for mass density, and 0.19% and 0.07% for RSP, respectively. These results demonstrate the feasibility of using an MRI-only approach combined with DL methods for mass density and RSP estimation in proton therapy treatment planning. By employing this approach, it is possible to obtain the necessary information for proton radiotherapy directly from MRI scans, eliminating the need for additional imaging modalities.

Multimodal imaging-based material mass density estimation for proton therapy using supervised deep learning.

OBJECTIVE: Mapping CT number to material property dominates the proton range uncertainty. This work aims to develop a physics-constrained deep learning-based multimodal imaging (PDMI) framework to integrate physics, deep learning, MRI, and advanced dual-energy CT (DECT) to derive accurate patient mass density maps. METHODS: Seven tissue substitute MRI phantoms were used for validation including adipose, brain, muscle, liver, skin, spongiosa, 45% hydroxyapatite (HA) bone. MRI images were acquired using T1 weighted Dixon and T2 weighted short tau inversion recovery sequences. Training inputs are from MRI and twin-beam dual-energy images acquired at 120 kVp with gold/tin filters. The feasibility investigation included an empirical model and four residual networks (ResNet) derived from different training inputs and strategies by PDMI framework. PRN-MR-DE and RN-MR-DE denote ResNet (RN) trained with and without a physics constraint (P) using MRI (MR) and DECT (DE) images. PRN-DE stands for RN trained with a physics constraint using only DE images. A retrospective study using institutional patient data was also conducted to investigate the feasibility of the proposed framework. RESULTS: For the tissue surrogate study, PRN-MR-DE, PRN-DE, and RN-MR-DE result in mean mass density errors: -0.72%/2.62%/-3.58% for adipose; -0.03%/-0.61%/-0.18% for muscle; -0.58%/-1.36%/-4.86% for 45% HA bone. The retrospective patient study indicated that PRN-MR-DE predicted the densities of soft tissue and bone within expected intervals based on the literature survey, while PRN-DE generated large density deviations. CONCLUSION: The proposed PDMI framework can generate accurate mass density maps using MRI and DECT images. The supervised learning can further enhance model efficacy, making PRN-MR-DE outperform RN-MR-DE. The patient investigation also shows that the framework can potentially improve proton range uncertainty with accurate patient mass density maps. ADVANCES IN KNOWLEDGE: PDMI framework is proposed for the first time to inform deep learning models by physics insights and leverage the information from MRI to derive accurate mass density maps.

Contrast-Enhanced Liver Magnetic Resonance Image Synthesis Using Gradient Regularized Multi-Modal Multi-Discrimination Sparse Attention Fusion GAN.

PURPOSES: To provide abdominal contrast-enhanced MR image synthesis, we developed an gradient regularized multi-modal multi-discrimination sparse attention fusion generative adversarial network (GRMM-GAN) to avoid repeated contrast injections to patients and facilitate adaptive monitoring. METHODS: With IRB approval, 165 abdominal MR studies from 61 liver cancer patients were retrospectively solicited from our institutional database. Each study included T2, T1 pre-contrast (T1pre), and T1 contrast-enhanced (T1ce) images. The GRMM-GAN synthesis pipeline consists of a sparse attention fusion network, an image gradient regularizer (GR), and a generative adversarial network with multi-discrimination. The studies were randomly divided into 115 for training, 20 for validation, and 30 for testing. The two pre-contrast MR modalities, T2 and T1pre images, were adopted as inputs in the training phase. The T1ce image at the portal venous phase was used as an output. The synthesized T1ce images were compared with the ground truth T1ce images. The evaluation metrics include peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and mean squared error (MSE). A Turing test and experts' contours evaluated the image synthesis quality. RESULTS: The proposed GRMM-GAN model achieved a PSNR of 28.56, an SSIM of 0.869, and an MSE of 83.27. The proposed model showed statistically significant improvements in all metrics tested with p-values < 0.05 over the state-of-the-art model comparisons. The average Turing test score was 52.33%, which is close to random guessing, supporting the model's effectiveness for clinical application. In the tumor-specific region analysis, the average tumor contrast-to-noise ratio (CNR) of the synthesized MR images was not statistically significant from the real MR images. The average DICE from real vs. synthetic images was 0.90 compared to the inter-operator DICE of 0.91. CONCLUSION: We demonstrated the function of a novel multi-modal MR image synthesis neural network GRMM-GAN for T1ce MR synthesis based on pre-contrast T1 and T2 MR images. GRMM-GAN shows promise for avoiding repeated contrast injections during radiation therapy treatment.

Generation of synthetic megavoltage CT for MRI-only radiotherapy treatment planning using a 3D deep convolutional neural network.

BACKGROUND: Megavoltage computed tomography (MVCT) has been implemented on many radiotherapy treatment machines for on-board anatomical visualization, localization, and adaptive dose calculation. Implementing an MR-only workflow by synthesizing MVCT from magnetic resonance imaging (MRI) would offer numerous advantages for treatment planning and online adaptation. PURPOSE: In this work, we sought to synthesize MVCT (sMVCT) datasets from MRI using deep learning to demonstrate the feasibility of MRI-MVCT only treatment planning. METHODS: MVCTs and T1-weighted MRIs for 120 patients treated for head-and-neck cancer were retrospectively acquired and co-registered. A deep neural network based on a fully-convolutional 3D U-Net architecture was implemented to map MRI intensity to MVCT HU. Input to the model were volumetric patches generated from paired MRI and MVCT datasets. The U-Net was initialized with random parameters and trained on a mean absolute error (MAE) objective function. Model accuracy was evaluated on 18 withheld test exams. sMVCTs were compared to respective MVCTs. Intensity-modulated volumetric radiotherapy (IMRT) plans were generated on MVCTs of four different disease sites and compared to plans calculated onto corresponding sMVCTs using the gamma metric and dose-volume-histograms (DVHs). RESULTS: MAE values between sMVCT and MVCT datasets were 93.3 ± 27.5, 78.2 ± 27.5, and 138.0 ± 43.4 HU for whole body, soft tissue, and bone volumes, respectively. Overall, there was good agreement between sMVCT and MVCT, with bone and air posing the greatest challenges. The retrospective dataset introduced additional deviations due to sinus filling or tumor growth/shrinkage between scans, differences in external contours due to variability in patient positioning, or when immobilization devices were absent from diagnostic MRIs. Dose distributions of IMRT plans evaluated for four test cases showed close agreement between sMVCT and MVCT images when evaluated using DVHs and gamma dose metrics, which averaged to 98.9 ± 1.0% and 96.8 ± 2.6% analyzed at 3%/3 mm and 2%/2 mm, respectively. CONCLUSIONS: MVCT datasets can be generated from T1-weighted MRI using a 3D deep convolutional neural network with dose calculation on a sample sMVCT in close agreement with the MVCT. These results demonstrate the feasibility of using MRI-derived sMVCT in an MR-only treatment planning workflow.

Quality Assurance for AI-Based Applications in Radiation Therapy.

Recent advancements in artificial intelligence (AI) in the domain of radiation therapy (RT) and their integration into modern software-based systems raise new challenges to the profession of medical physics experts. These AI algorithms are typically data-driven, may be continuously evolving, and their behavior has a degree of (acceptable) uncertainty due to inherent noise in training data and the substantial number of parameters that are used in the algorithms. These characteristics request adaptive, and new comprehensive quality assurance (QA) approaches to guarantee the individual patient treatment quality during AI algorithm development and subsequent deployment in a clinical RT environment. However, the QA for AI-based systems is an emerging area, which has not been intensively explored and requires interactive collaborations between medical doctors, medical physics experts, and commercial/research AI institutions. This article summarizes the current QA methodologies for AI modules of every subdomain in RT with further focus on persistent shortcomings and upcoming key challenges and perspectives.

Technical Note: A methodology for improved accuracy in stopping power estimation using MRI and CT.

PURPOSE: Proton therapy is becoming an increasingly popular cancer treatment modality due to the proton's physical advantage in that it deposits the majority of its energy at the distal end of its track where the tumor is located. The proton range in a material is determined from the stopping power ratio (SPR) of the material. However, SPR is typically estimated based on a computed tomography (CT) scan which can lead to range estimation errors due to the difference in x-ray and proton interactions in matter, which can preclude the ability to utilize protons to their full potential. Applications of magnetic resonance imaging (MRI) in radiotherapy have increased over the past decade and using MRI to calculate SPR directly could provide numerous advantages. The purpose of this study was to develop a practical implementation of a novel multimodal imaging method for estimating SPR and compare the results of this method to physical measurements in which values were computed directly using tissue substitute materials fabricated to mimic skin, muscle, adipose, and spongiosa bone. METHODS: For both the multimodal imaging method and physical measurements, SPR was calculated using the Bethe-Bloch equation from values of relative electron density and mean ionization potential determined for each tissue. Parameters used to estimate SPR using the multimodal imaging method were extracted from Dixon water-only and (1 H) proton density-weighted zero echo time MRI sequences and CT, with both kVCT and MVCT used separately to evaluate the performance of each. For comparison, SPR was also computed from kVCT using the stoichiometric method, the current clinical standard. RESULTS: Results showed that our multimodal imaging approach using MRI with either kVCT or MVCT was in close agreement to SPR calculated from physical measurements for the four tissue substitutes evaluated. Using MRI and MVCT, SPR values estimated using our method were within 1% of physical measurements and were more accurate than the stoichiometric method for the tissue types studied. CONCLUSIONS: We have demonstrated the methodology for improved estimation of SPR using the proposed multimodal imaging framework.

Oral isotretinoin and topical retinoid use in a series of young patients with ocular melanoma.

PURPOSE: To describe the first series of six young uveal melanoma (UM) patients with oral isotretinoin and/or topical retinoid therapy prior to diagnosis. OBSERVATIONS: The case series is based on clinical observations at our UM quaternary referral center. Six UM patient cases are reported, ages 16-44 years old. All had been using either oral (isotretinoin) and/or topical (tretinoin or tazarotene) retinoid treatment (3 months-~10 years) prior to or at the time of diagnosis (3 of 6 cases). All patients had ocular complaints on presentation, and the onset of certain symptoms corresponded with the course of retinoids. Other potential risk factors or relevant history included Caucasian background, cone-rod dystrophy and active smoker status (Case 2), family history of UM and pregnancy at time of diagnosis (Case 3), past smoking and possible secondary Chernobyl exposure as a baby (Case 5). All patients were treated with proton beam radiotherapy and currently have no sign of recurrent or metastatic disease. CONCLUSIONS AND IMPORTANCE: Retinoid therapy has been linked to various benign and/or reversible effects on the anterior and posterior eye, though pathophysiology remains not well understood. Uveal melanoma (UM) is a rare cancer diagnosis in young adults. We report here the first case series of young UM patients with a history of retinoid use and ocular complaints. No causal link is claimed and further systematic epidemiologic and biologic study of retinoid therapy and ocular impact may provide additional relevant data, particularly in young ocular melanoma patients.

Practice Considerations for Proton Beam Radiation Therapy of Uveal Melanoma During the Coronavirus Disease Pandemic: Particle Therapy Co-Operative Group Ocular Experience.

Uveal melanoma (UM) is a rare but life-threatening cancer of the eye. In light of the coronavirus disease (COVID-19) pandemic, hospitals and proton eye therapy facilities must analyze several factors to ensure appropriate treatment protocols for patients and provider teams. Practice considerations to limit COVID-19 transmission in the proton ocular treatment setting for UM are necessary. The Particle Therapy Co-Operative Group is the largest international community of particle/proton therapy providers. Participating experts have current or former affiliation with the member institutions of the Particle Therapy Co-Operative Group Ocular subcommittee with long-standing high-volume proton ocular programs. The practices reviewed in this document must be taken in conjunction with local hospital procedures, multidisciplinary recommendations, and regional/national guidelines, as each community may have its unique needs, supplies, and protocols. Importantly, as the pandemic evolves, so will the strategies and recommendations. Given the unique circumstances for UM patients, along with indications of potential ophthalmologic transmission as a result of health care providers working in close proximity to patients and intrinsic infectious risk from eyelashes, tears, and hair, practice strategies may be adapted to reduce the risk of viral transmission. Certainly, providers and health care systems will continue to examine and provide as safe and effective care as possible for patients in the current environment.

Structural basis for the assembly of the mitotic motor Kinesin-5 into bipolar tetramers.

Chromosome segregation during mitosis depends upon Kinesin-5 motors, which display a conserved, bipolar homotetrameric organization consisting of two motor dimers at opposite ends of a central rod. Kinesin-5 motors crosslink adjacent microtubules to drive or constrain their sliding apart, but the structural basis of their organization is unknown. In this study, we report the atomic structure of the bipolar assembly (BASS) domain that directs four Kinesin-5 subunits to form a bipolar minifilament. BASS is a novel 26-nm four-helix bundle, consisting of two anti-parallel coiled-coils at its center, stabilized by alternating hydrophobic and ionic four-helical interfaces, which based on mutagenesis experiments, are critical for tetramerization. Strikingly, N-terminal BASS helices bend as they emerge from the central bundle, swapping partner helices, to form dimeric parallel coiled-coils at both ends, which are offset by 90°. We propose that BASS is a mechanically stable, plectonemically-coiled junction, transmitting forces between Kinesin-5 motor dimers during microtubule sliding. DOI: http://dx.doi.org/10.7554/eLife.02217.001.