Full-dose whole-body PET synthesis from low-dose PET using high-efficiency denoising diffusion probabilistic model: PET consistency model.

PURPOSE: Positron Emission Tomography (PET) has been a commonly used imaging modality in broad clinical applications. One of the most important tradeoffs in PET imaging is between image quality and radiation dose: high image quality comes with high radiation exposure. Improving image quality is desirable for all clinical applications while minimizing radiation exposure is needed to reduce risk to patients. METHODS: We introduce PET Consistency Model (PET-CM), an efficient diffusion-based method for generating high-quality full-dose PET images from low-dose PET images. It employs a two-step process, adding Gaussian noise to full-dose PET images in the forward diffusion, and then denoising them using a PET Shifted-window Vision Transformer (PET-VIT) network in the reverse diffusion. The PET-VIT network learns a consistency function that enables direct denoising of Gaussian noise into clean full-dose PET images. PET-CM achieves state-of-the-art image quality while requiring significantly less computation time than other methods. Evaluation with normalized mean absolute error (NMAE), peak signal-to-noise ratio (PSNR), multi-scale structure similarity index (SSIM), normalized cross-correlation (NCC), and clinical evaluation including Human Ranking Score (HRS) and Standardized Uptake Value (SUV) Error analysis shows its superiority in synthesizing full-dose PET images from low-dose inputs. RESULTS: In experiments comparing eighth-dose to full-dose images, PET-CM demonstrated impressive performance with NMAE of 1.278 ± 0.122%, PSNR of 33.783 ± 0.824 dB, SSIM of 0.964 ± 0.009, NCC of 0.968 ± 0.011, HRS of 4.543, and SUV Error of 0.255 ± 0.318%, with an average generation time of 62 s per patient. This is a significant improvement compared to the state-of-the-art diffusion-based model with PET-CM reaching this result 12× faster. Similarly, in the quarter-dose to full-dose image experiments, PET-CM delivered competitive outcomes, achieving an NMAE of 0.973 ± 0.066%, PSNR of 36.172 ± 0.801 dB, SSIM of 0.984 ± 0.004, NCC of 0.990 ± 0.005, HRS of 4.428, and SUV Error of 0.151 ± 0.192% using the same generation process, which underlining its high quantitative and clinical precision in both denoising scenario. CONCLUSIONS: We propose PET-CM, the first efficient diffusion-model-based method, for estimating full-dose PET images from low-dose images. PET-CM provides comparable quality to the state-of-the-art diffusion model with higher efficiency. By utilizing this approach, it becomes possible to maintain high-quality PET images suitable for clinical use while mitigating the risks associated with radiation. The code is availble at https://github.com/shaoyanpan/Full-dose-Whole-body-PET-Synthesis-from-Low-dose-PET-Using-Consistency-Model.

High-resolution 3T to 7T ADC map synthesis with a hybrid CNN-transformer model.

BACKGROUND: 7 Tesla (7T) apparent diffusion coefficient (ADC) maps derived from diffusion-weighted imaging (DWI) demonstrate improved image quality and spatial resolution over 3 Tesla (3T) ADC maps. However, 7T magnetic resonance imaging (MRI) currently suffers from limited clinical unavailability, higher cost, and increased susceptibility to artifacts. PURPOSE: To address these issues, we propose a hybrid CNN-transformer model to synthesize high-resolution 7T ADC maps from multimodal 3T MRI. METHODS: The Vision CNN-Transformer (VCT), composed of both Vision Transformer (ViT) blocks and convolutional layers, is proposed to produce high-resolution synthetic 7T ADC maps from 3T ADC maps and 3T T1-weighted (T1w) MRI. ViT blocks enabled global image context while convolutional layers efficiently captured fine detail. The VCT model was validated on the publicly available Human Connectome Project Young Adult dataset, comprising 3T T1w, 3T DWI, and 7T DWI brain scans. The Diffusion Imaging in Python library was used to compute ADC maps from the DWI scans. A total of 171 patient cases were randomly divided into 130 training cases, 20 validation cases, and 21 test cases. The synthetic ADC maps were evaluated by comparing their similarity to the ground truth volumes with the following metrics: peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and mean squared error (MSE). In addition, RESULTS: The results are as follows: PSNR: 27.0 ± 0.9 dB, SSIM: 0.945 ± 0.010, and MSE: 2.0E-3 ± 0.4E-3. Both qualitative and quantitative results demonstrate that VCT performs favorably against other state-of-the-art methods. We have introduced various efficiency improvements, including the implementation of flash attention and training on 176×208 resolution images. These enhancements have resulted in the reduction of parameters and training time per epoch by 50% in comparison to ResViT. Specifically, the training time per epoch has been shortened from 7.67 min to 3.86 min. CONCLUSION: We propose a novel method to predict high-resolution 7T ADC maps from low-resolution 3T ADC maps and T1w MRI. Our predicted images demonstrate better spatial resolution and contrast compared to 3T MRI and prediction results made by ResViT and pix2pix. These high-quality synthetic 7T MR images could be beneficial for disease diagnosis and intervention, producing higher resolution and conformal contours, and as an intermediate step in generating synthetic CT for radiation therapy, especially when 7T MRI scanners are unavailable.

MRI-based prostate cancer classification using 3D efficient capsule network.

BACKGROUND: Prostate cancer (PCa) is the most common cancer in men and the second leading cause of male cancer-related death. Gleason score (GS) is the primary driver of PCa risk-stratification and medical decision-making, but can only be assessed at present via biopsy under anesthesia. Magnetic resonance imaging (MRI) is a promising non-invasive method to further characterize PCa, providing additional anatomical and functional information. Meanwhile, the diagnostic power of MRI is limited by qualitative or, at best, semi-quantitative interpretation criteria, leading to inter-reader variability. PURPOSES: Computer-aided diagnosis employing quantitative MRI analysis has yielded promising results in non-invasive prediction of GS. However, convolutional neural networks (CNNs) do not implicitly impose a frame of reference to the objects. Thus, CNNs do not encode the positional information properly, limiting method robustness against simple image variations such as flipping, scaling, or rotation. Capsule network (CapsNet) has been proposed to address this limitation and achieves promising results in this domain. In this study, we develop a 3D Efficient CapsNet to stratify GS-derived PCa risk using T2-weighted (T2W) MRI images. METHODS: In our method, we used 3D CNN modules to extract spatial features and primary capsule layers to encode vector features. We then propose to integrate fully-connected capsule layers (FC Caps) to create a deeper hierarchy for PCa grading prediction. FC Caps comprises a secondary capsule layer which routes active primary capsules and a final capsule layer which outputs PCa risk. To account for data imbalance, we propose a novel dynamic weighted margin loss. We evaluate our method on a public PCa T2W MRI dataset from the Cancer Imaging Archive containing data from 976 patients. RESULTS: Two groups of experiments were performed: (1) we first identified high-risk disease by classifying low + medium risk versus high risk; (2) we then stratified disease in one-versus-one fashion: low versus high risk, medium versus high risk, and low versus medium risk. Five-fold cross validation was performed. Our model achieved an area under receiver operating characteristic curve (AUC) of 0.83 and 0.64 F1-score for low versus high grade, 0.79 AUC and 0.75 F1-score for low + medium versus high grade, 0.75 AUC and 0.69 F1-score for medium versus high grade and 0.59 AUC and 0.57 F1-score for low versus medium grade. Our method outperformed state-of-the-art radiomics-based classification and deep learning methods with the highest metrics for each experiment. Our divide-and-conquer strategy achieved weighted Cohen's Kappa score of 0.41, suggesting moderate agreement with ground truth PCa risks. CONCLUSIONS: In this study, we proposed a novel 3D Efficient CapsNet for PCa risk stratification and demonstrated its feasibility. This developed tool provided a non-invasive approach to assess PCa risk from T2W MR images, which might have potential to personalize the treatment of PCa and reduce the number of unnecessary biopsies.

CBCT-Based synthetic CT image generation using conditional denoising diffusion probabilistic model.

BACKGROUND: Daily or weekly cone-beam computed tomography (CBCT) scans are commonly used for accurate patient positioning during the image-guided radiotherapy (IGRT) process, making it an ideal option for adaptive radiotherapy (ART) replanning. However, the presence of severe artifacts and inaccurate Hounsfield unit (HU) values prevent its use for quantitative applications such as organ segmentation and dose calculation. To enable the clinical practice of online ART, it is crucial to obtain CBCT scans with a quality comparable to that of a CT scan. PURPOSE: This work aims to develop a conditional diffusion model to perform image translation from the CBCT to the CT distribution for the image quality improvement of CBCT. METHODS: The proposed method is a conditional denoising diffusion probabilistic model (DDPM) that utilizes a time-embedded U-net architecture with residual and attention blocks to gradually transform the white Gaussian noise sample to the target CT distribution conditioned on the CBCT. The model was trained on deformed planning CT (dpCT) and CBCT image pairs, and its feasibility was verified in brain patient study and head-and-neck (H&N) patient study. The performance of the proposed algorithm was evaluated using mean absolute error (MAE), peak signal-to-noise ratio (PSNR) and normalized cross-correlation (NCC) metrics on generated synthetic CT (sCT) samples. The proposed method was also compared to four other diffusion model-based sCT generation methods. RESULTS: In the brain patient study, the MAE, PSNR, and NCC of the generated sCT were 25.99 HU, 30.49 dB, and 0.99, respectively, compared to 40.63 HU, 27.87 dB, and 0.98 of the CBCT images. In the H&N patient study, the metrics were 32.56 HU, 27.65 dB, 0.98 and 38.99 HU, 27.00, 0.98 for sCT and CBCT, respectively. Compared to the other four diffusion models and one Cycle generative adversarial network (Cycle GAN), the proposed method showed superior results in both visual quality and quantitative analysis. CONCLUSIONS: The proposed conditional DDPM method can generate sCT from CBCT with accurate HU numbers and reduced artifacts, enabling accurate CBCT-based organ segmentation and dose calculation for online ART.

Synthetic CT generation from MRI using 3D transformer-based denoising diffusion model.

BACKGROUND AND PURPOSE: Magnetic resonance imaging (MRI)-based synthetic computed tomography (sCT) simplifies radiation therapy treatment planning by eliminating the need for CT simulation and error-prone image registration, ultimately reducing patient radiation dose and setup uncertainty. In this work, we propose a MRI-to-CT transformer-based improved denoising diffusion probabilistic model (MC-IDDPM) to translate MRI into high-quality sCT to facilitate radiation treatment planning. METHODS: MC-IDDPM implements diffusion processes with a shifted-window transformer network to generate sCT from MRI. The proposed model consists of two processes: a forward process, which involves adding Gaussian noise to real CT scans to create noisy images, and a reverse process, in which a shifted-window transformer V-net (Swin-Vnet) denoises the noisy CT scans conditioned on the MRI from the same patient to produce noise-free CT scans. With an optimally trained Swin-Vnet, the reverse diffusion process was used to generate noise-free sCT scans matching MRI anatomy. We evaluated the proposed method by generating sCT from MRI on an institutional brain dataset and an institutional prostate dataset. Quantitative evaluations were conducted using several metrics, including Mean Absolute Error (MAE), Peak Signal-to-Noise Ratio (PSNR), Multi-scale Structure Similarity Index (SSIM), and Normalized Cross Correlation (NCC). Dosimetry analyses were also performed, including comparisons of mean dose and target dose coverages for 95% and 99%. RESULTS: MC-IDDPM generated brain sCTs with state-of-the-art quantitative results with MAE 48.825 ± 21.491 HU, PSNR 26.491 ± 2.814 dB, SSIM 0.947 ± 0.032, and NCC 0.976 ± 0.019. For the prostate dataset: MAE 55.124 ± 9.414 HU, PSNR 28.708 ± 2.112 dB, SSIM 0.878 ± 0.040, and NCC 0.940 ± 0.039. MC-IDDPM demonstrates a statistically significant improvement (with p < 0.05) in most metrics when compared to competing networks, for both brain and prostate synthetic CT. Dosimetry analyses indicated that the target dose coverage differences by using CT and sCT were within ± 0.34%. CONCLUSIONS: We have developed and validated a novel approach for generating CT images from routine MRIs using a transformer-based improved DDPM. This model effectively captures the complex relationship between CT and MRI images, allowing for robust and high-quality synthetic CT images to be generated in a matter of minutes. This approach has the potential to greatly simplify the treatment planning process for radiation therapy by eliminating the need for additional CT scans, reducing the amount of time patients spend in treatment planning, and enhancing the accuracy of treatment delivery.

Early in vivo Radiation Damage Quantification for Pediatric Craniospinal Irradiation Using Longitudinal MRI for Intensity Modulated Proton Therapy.

Purpose: Proton vertebral body sparing craniospinal irradiation (CSI) treats the thecal sac while avoiding the anterior vertebral bodies in an effort to reduce myelosuppression and growth inhibition. However, robust treatment planning needs to compensate for proton range uncertainty, which contributes unwanted doses within the vertebral bodies. This work aimed to develop an early in vivo radiation damage quantification method using longitudinal magnetic resonance (MR) scans to quantify the dose effect during fractionated CSI. Methods and Materials: Ten pediatric patients were enrolled in a prospective clinical trial of proton vertebral body sparing CSI, in which they received 23.4 to 36 Gy. Monte Carlo robust planning was used, with spinal clinical target volumes defined as the thecal sac and neural foramina. T1/T2-weighted MR scans were acquired before, during, and after treatments to detect a transition from hematopoietic to less metabolically active fatty marrow. MR signal intensity histograms at each time point were analyzed and fitted by multi-Gaussian models to quantify radiation damage. Results: Fatty marrow filtration was observed in MR images as early as the fifth fraction of treatment. Maximum radiation-induced marrow damage occurred 40 to 50 days from the treatment start, followed by marrow regeneration. The mean damage ratios were 0.23, 0.41, 0.59, and 0.54, corresponding to 10, 20, 40, and 60 days from the treatment start. Conclusions: We demonstrated a noninvasive method for identifying early vertebral marrow damage based on radiation-induced fatty marrow replacement. The proposed method can be potentially used to quantify the quality of CSI vertebral sparing and preserve metabolically active hematopoietic bone marrow.

Rapid unpaired CBCT-based synthetic CT for CBCT-guided adaptive radiotherapy.

In this work, we demonstrate a method for rapid synthesis of high-quality CT images from unpaired, low-quality CBCT images, permitting CBCT-based adaptive radiotherapy. We adapt contrastive unpaired translation (CUT) to be used with medical images and evaluate the results on an institutional pelvic CT dataset. We compare the method against cycleGAN using mean absolute error, structural similarity index, root mean squared error, and Frèchet Inception Distance and show that CUT significantly outperforms cycleGAN while requiring less time and fewer resources. The investigated method improves the feasibility of online adaptive radiotherapy over the present state-of-the-art.

Uncertainty in projections of future lake thermal dynamics is differentially driven by lake and global climate models.

Freshwater ecosystems provide vital services, yet are facing increasing risks from global change. In particular, lake thermal dynamics have been altered around the world as a result of climate change, necessitating a predictive understanding of how climate will continue to alter lakes in the future as well as the associated uncertainty in these predictions. Numerous sources of uncertainty affect projections of future lake conditions but few are quantified, limiting the use of lake modeling projections as management tools. To quantify and evaluate the effects of two potentially important sources of uncertainty, lake model selection uncertainty and climate model selection uncertainty, we developed ensemble projections of lake thermal dynamics for a dimictic lake in New Hampshire, USA (Lake Sunapee). Our ensemble projections used four different climate models as inputs to five vertical one-dimensional (1-D) hydrodynamic lake models under three different climate change scenarios to simulate thermal metrics from 2006 to 2099. We found that almost all the lake thermal metrics modeled (surface water temperature, bottom water temperature, Schmidt stability, stratification duration, and ice cover, but not thermocline depth) are projected to change over the next century. Importantly, we found that the dominant source of uncertainty varied among the thermal metrics, as thermal metrics associated with the surface waters (surface water temperature, total ice duration) were driven primarily by climate model selection uncertainty, while metrics associated with deeper depths (bottom water temperature, stratification duration) were dominated by lake model selection uncertainty. Consequently, our results indicate that researchers generating projections of lake bottom water metrics should prioritize including multiple lake models for best capturing projection uncertainty, while those focusing on lake surface metrics should prioritize including multiple climate models. Overall, our ensemble modeling study reveals important information on how climate change will affect lake thermal properties, and also provides some of the first analyses on how climate model selection uncertainty and lake model selection uncertainty interact to affect projections of future lake dynamics.

Impact of Age on Overall Survival Among Children With Wilms Tumor: A Population-based Registry Analysis.

OBJECTIVES: International trials have reported conflicting findings on whether the association between age and worse overall survival (OS) among children with Wilms tumor (WT) is due to age as an independent prognostic factor or the observation of more advanced disease at older ages. We sought to further elucidate this relationship using a population-based registry analysis. METHODS: The Surveillance, Epidemiology, and End Results database was queried for all patients diagnosed with WT under the age of 20. The association between age and OS was assessed using multivariable Cox proportional hazards regression. RESULTS: In this study, 3463 patients (54% female) were diagnosed with WT between 1975 and 2016. More advanced stage, larger primary tumor size, lymph node involvement, disease requiring radiotherapy, and omission of surgery were associated with worse OS ( P <0.05). More advanced stage, larger primary tumor size, and disease requiring radiotherapy were also associated with older age, whereas bilateral disease was associated with younger age ( P <0.001). On average, each year of age conferred an incremental hazard ratio (HR) of 1.07 (95% CI, 1.01 to 1.12, P =0.018) independent of relevant covariates. The rise in adjusted OS HR was most pronounced after the transitions in diagnosis age from 2 to 3 (HR age 3-15 vs. 0-2 1.77, 95% CI, 1.11 to 2.82, P =0.016) and from 15 to 16 (HR age 16-19 vs. 3-15 2.58, 95% CI, 1.06 to 6.25, P =0.036). CONCLUSIONS: Diagnosis of pediatric WT at an older age was found to be independently associated with worse OS. Although additional prospective studies are warranted to examine tumor biology and other potential correlates, more aggressive treatment of older children based on age, especially as they approach early adulthood, may be considered in the multidisciplinary management of WT.

Patterns of Progression in Patients With Newly Diagnosed Glioblastoma Treated With 5-mm Margins in a Phase 1/2 Trial of 5-Fraction Stereotactic Radiosurgery With Concurrent and Adjuvant Temozolomide.

PURPOSE: In patients with newly diagnosed glioblastoma (GBM), tumor margins of at least 20 mm are the standard of care. We sought to determine the pattern of tumor progression in patients treated with 5-fraction stereotactic radiosurgery with 5-mm margins. METHODS AND MATERIALS: Thirty adult patients with newly diagnosed GBM were treated with 5-fraction stereotactic radiosurgery in escalated doses from 25 to 40 Gy with a 5-mm total treatment margin. Progression was scored as "in-field" if the recurrent tumor was within or contiguous with the 5-mm margin, "marginal" if between 5 and 20 mm, and "distant" if entirely occurring greater than 20 mm. As geometric patterns of progression do not reflect the biologic dose received, we calculated the minimum equi-effective dose in 2 Gy (EQD2) per day at the site of tumor recurrence. Progression was "dosimetrically in-field" if covered by a minimum EQD2 per day of 48 Gy10. RESULTS: From 2010 to 2016, 27 patients had progressed. Progression was in-field in 17 (63%), marginal in 3 (11%), and distant in 7 (26%) patients. In the 3 patients with marginal progression, the minimum EQD2 to recurrent tumor were 48 Gy10, 56 Gy10 (both considered dosimetrically in-field), and 7 Gy10 (ie, dosimetrically out-of-field). Median overall survival was 12.1 months for in-field (95% confidence interval [CI], 8.9-17.6), 15.1 months (95% CI, 10.1 to not achieved) for marginal, and 21.4 months (95% CI, 11.2-33.5) for distant progression. Patients with radiation necrosis were less likely to have in-field progression (1 of 7; 14%) compared with those without radiation necrosis (16 of 20; 80%; P = .003); those with necrosis had a median overall survival of 27.2 months (95% CI, 11.2-48.3) compared with 11.7 months (95% CI, 8.9-17.6) for patients with no necrosis (P = .077). CONCLUSIONS: In patients with newly diagnosed GBM treated with a 5-mm clinical target volume margin, 3 patients (11%) had marginal progression within 5 to 20 mm; only 1 patient (4%) may have dosimetrically benefitted from conventional 20-mm margins. Radiation necrosis was associated with in-field tumor control.

Landmark tracking in liver US images using cascade convolutional neural networks with long short-term memory.

Accurate tracking of anatomic landmarks is critical for motion management in liver radiation therapy. Ultrasound (US) is a safe, low-cost technology that is broadly available and offer real-time imaging capability. This study proposed a deep learning-based tracking method for the US image-guided radiation therapy. The proposed cascade deep learning model is composed of an attention network, a mask region-based convolutional neural network (mask R-CNN), and a long short-term memory (LSTM) network. The attention network learns a mapping from an US image to a suspected area of landmark motion in order to reduce the search region. The mask R-CNN then produces multiple region-of-interest proposals in the reduced region and identifies the proposed landmark via three network heads: bounding box regression, proposal classification, and landmark segmentation. The LSTM network models the temporal relationship among the successive image frames for bounding box regression and proposal classification. To consolidate the final proposal, a selection method is designed according to the similarities between sequential frames. The proposed method was tested on the liver US tracking datasets used in the medical image computing and computer assisted interventions 2015 challenges, where the landmarks were annotated by three experienced observers to obtain their mean positions. Five-fold cross validation on the 24 given US sequences with ground truths shows that the mean tracking error for all landmarks is 0.65 ± 0.56 mm, and the errors of all landmarks are within 2 mm. We further tested the proposed model on 69 landmarks from the testing dataset that have the similar image pattern with the training pattern, resulting in a mean tracking error of 0.94 ± 0.83 mm. The proposed deep-learning model was implemented on a graphics processing unit (GPU), tracking 47-81 frames s-1. Our experimental results have demonstrated the feasibility and accuracy of our proposed method in tracking liver anatomic landmarks using US images, providing a potential solution for real-time liver tracking for active motion management during radiation therapy.

Abdomen CT multi-organ segmentation using token-based MLP-Mixer.

BACKGROUND: Manual contouring is very labor-intensive, time-consuming, and subject to intra- and inter-observer variability. An automated deep learning approach to fast and accurate contouring and segmentation is desirable during radiotherapy treatment planning. PURPOSE: This work investigates an efficient deep-learning-based segmentation algorithm in abdomen computed tomography (CT) to facilitate radiation treatment planning. METHODS: In this work, we propose a novel deep-learning model utilizing U-shaped multi-layer perceptron mixer (MLP-Mixer) and convolutional neural network (CNN) for multi-organ segmentation in abdomen CT images. The proposed model has a similar structure to V-net, while a proposed MLP-Convolutional block replaces each convolutional block. The MLP-Convolutional block consists of three components: an early convolutional block for local features extraction and feature resampling, a token-based MLP-Mixer layer for capturing global features with high efficiency, and a token projector for pixel-level detail recovery. We evaluate our proposed network using: (1) an institutional dataset with 60 patient cases and (2) a public dataset (BCTV) with 30 patient cases. The network performance was quantitatively evaluated in three domains: (1) volume similarity between the ground truth contours and the network predictions using the Dice score coefficient (DSC), sensitivity, and precision; (2) surface similarity using Hausdorff distance (HD), mean surface distance (MSD) and residual mean square distance (RMS); and (3) the computational complexity reported by the number of network parameters, training time, and inference time. The performance of the proposed network is compared with other state-of-the-art networks. RESULTS: In the institutional dataset, the proposed network achieved the following volume similarity measures when averaged over all organs: DSC = 0.912, sensitivity = 0.917, precision = 0.917, average surface similarities were HD = 11.95 mm, MSD = 1.90 mm, RMS = 3.86 mm. The proposed network achieved DSC = 0.786 and HD = 9.04 mm on the public dataset. The network also shows statistically significant improvement, which is evaluated by a two-tailed Wilcoxon Mann-Whitney U test, on right lung (MSD where the maximum p-value is 0.001), spinal cord (sensitivity, precision, HD, RMSD where p-value ranges from 0.001 to 0.039), and stomach (DSC where the maximum p-value is 0.01) over all other competing networks. On the public dataset, the network report statistically significant improvement, which is shown by the Wilcoxon Mann-Whitney test, on pancreas (HD where the maximum p-value is 0.006), left (HD where the maximum p-value is 0.022) and right adrenal glands (DSC where the maximum p-value is 0.026). In both datasets, the proposed method can generate contours in less than 5 s. Overall, the proposed MLP-Vnet demonstrates comparable or better performance than competing methods with much lower memory complexity and higher speed. CONCLUSIONS: The proposed MLP-Vnet demonstrates superior segmentation performance, in terms of accuracy and efficiency, relative to state-of-the-art methods. This reliable and efficient method demonstrates potential to streamline clinical workflows in abdominal radiotherapy, which may be especially important for online adaptive treatments.

Male pelvic multi-organ segmentation using token-based transformer Vnet.

Objective. This work aims to develop an automated segmentation method for the prostate and its surrounding organs-at-risk in pelvic computed tomography to facilitate prostate radiation treatment planning.Approach. In this work, we propose a novel deep learning algorithm combining a U-shaped convolutional neural network (CNN) and vision transformer (VIT) for multi-organ (i.e. bladder, prostate, rectum, left and right femoral heads) segmentation in male pelvic CT images. The U-shaped model consists of three components: a CNN-based encoder for local feature extraction, a token-based VIT for capturing global dependencies from the CNN features, and a CNN-based decoder for predicting the segmentation outcome from the VIT's output. The novelty of our network is a token-based multi-head self-attention mechanism used in the transformer, which encourages long-range dependencies and forwards informative high-resolution feature maps from the encoder to the decoder. In addition, a knowledge distillation strategy is deployed to further enhance the learning capability of the proposed network.Main results. We evaluated the network using: (1) a dataset collected from 94 patients with prostate cancer; (2) and a public dataset CT-ORG. A quantitative evaluation of the proposed network's performance was performed on each organ based on (1) volume similarity between the segmented contours and ground truth using Dice score, segmentation sensitivity, and precision, (2) surface similarity evaluated by Hausdorff distance (HD), mean surface distance (MSD) and residual mean square distance (RMS), (3) and percentage volume difference (PVD). The performance was then compared against other state-of-art methods. Average volume similarity measures obtained by the network overall organs were Dice score = 0.91, sensitivity = 0.90, precision = 0.92, average surface similarities were HD = 3.78 mm, MSD = 1.24 mm, RMS = 2.03 mm; average percentage volume difference was PVD = 9.9% on the first dataset. The network also obtained Dice score = 0.93, sensitivity = 0.93, precision = 0.93, average surface similarities were HD = 5.82 mm, MSD = 1.16 mm, RMS = 1.24 mm; average percentage volume difference was PVD = 6.6% on the CT-ORG dataset.Significance. In summary, we propose a token-based transformer network with knowledge distillation for multi-organ segmentation using CT images. This method provides accurate and reliable segmentation results for each organ using CT imaging, facilitating the prostate radiation clinical workflow.

Phase I/II Dose-Escalation Trial of 3-Fraction Stereotactic Radiosurgery for Resection Cavities From Large Brain Metastases: Health-related Quality of Life Outcomes.

OBJECTIVES: We investigated differences in quality of life (QoL) in patients enrolled on a phase I/II dose-escalation study of 3-fraction resection cavity stereotactic radiosurgery (SRS) for large brain metastases. METHODS: Eligible patients had 1 to 4 brain metastases, one of which was a resection cavity 4.2 to 33.5 cm3. European Organization for Research and Treatment of Cancer (EORTC) quality of life questionnaires core-30 (QLQ-30) and brain cancer specific module (QLQ-BN20) were obtained before SRS and at each follow-up. Nine scales were analyzed (global health status; physical, social, and emotional functioning; motor dysfunction, communication deficit, fatigue, insomnia, and future uncertainty). QoL was assessed with mixed effects models. Differences ≥10 points with q-value (adjusted P-value to account for multiplicity of testing) <0.10 were considered significant. RESULTS: Between 2009 and 2014, 50 enrolled patients completed 277 QoL questionnaires. Median questionnaire follow-up was 11.8 months. After SRS, insomnia demonstrated significant improvement (q=0.032, -17.7 points at 15 mo post-SRS), and future uncertainty demonstrated significant worsening (q=0.018, +9.9 points at 15 mo post-SRS). Following intracranial progression and salvage SRS, there were no significant QoL changes. The impact of salvage whole brain radiotherapy could not be assessed because of limited data (n=4 patients). In the 28% of patients that had adverse radiation effect, QoL had significant worsening in 3 metrics (physical functioning, q=0.024, emotional functioning q=0.001, and future uncertainty, q=0.004). CONCLUSIONS: For patients treated with 3-fraction SRS for large brain metastasis cavities, 8 of 9 QoL metrics were unchanged or improved after initial SRS. Intracranial tumor progression and salvage SRS did not impact QoL. Adverse radiation effect may be associated with at least short-term QoL impairments, but requires further investigation.

Synthetic CT-aided multiorgan segmentation for CBCT-guided adaptive pancreatic radiotherapy.

PURPOSE: The delineation of organs at risk (OARs) is fundamental to cone-beam CT (CBCT)-based adaptive radiotherapy treatment planning, but is time consuming, labor intensive, and subject to interoperator variability. We investigated a deep learning-based rapid multiorgan delineation method for use in CBCT-guided adaptive pancreatic radiotherapy. METHODS: To improve the accuracy of OAR delineation, two innovative solutions have been proposed in this study. First, instead of directly segmenting organs on CBCT images, a pretrained cycle-consistent generative adversarial network (cycleGAN) was applied to generating synthetic CT images given CBCT images. Second, an advanced deep learning model called mask-scoring regional convolutional neural network (MS R-CNN) was applied on those synthetic CT to detect the positions and shapes of multiple organs simultaneously for final segmentation. The OAR contours delineated by the proposed method were validated and compared with expert-drawn contours for geometric agreement using the Dice similarity coefficient (DSC), 95th percentile Hausdorff distance (HD95), mean surface distance (MSD), and residual mean square distance (RMS). RESULTS: Across eight abdominal OARs including duodenum, large bowel, small bowel, left and right kidneys, liver, spinal cord, and stomach, the geometric comparisons between automated and expert contours are as follows: 0.92 (0.89-0.97) mean DSC, 2.90 mm (1.63-4.19 mm) mean HD95, 0.89 mm (0.61-1.36 mm) mean MSD, and 1.43 mm (0.90-2.10 mm) mean RMS. Compared to the competing methods, our proposed method had significant improvements (p < 0.05) in all the metrics for all the eight organs. Once the model was trained, the contours of eight OARs can be obtained on the order of seconds. CONCLUSIONS: We demonstrated the feasibility of a synthetic CT-aided deep learning framework for automated delineation of multiple OARs on CBCT. The proposed method could be implemented in the setting of pancreatic adaptive radiotherapy to rapidly contour OARs with high accuracy.

Artificial intelligence in tumor subregion analysis based on medical imaging: A review.

Medical imaging is widely used in the diagnosis and treatment of cancer, and artificial intelligence (AI) has achieved tremendous success in medical image analysis. This paper reviews AI-based tumor subregion analysis in medical imaging. We summarize the latest AI-based methods for tumor subregion analysis and their applications. Specifically, we categorize the AI-based methods by training strategy: supervised and unsupervised. A detailed review of each category is presented, highlighting important contributions and achievements. Specific challenges and potential applications of AI in tumor subregion analysis are discussed.

A review on medical imaging synthesis using deep learning and its clinical applications.

This paper reviewed the deep learning-based studies for medical imaging synthesis and its clinical application. Specifically, we summarized the recent developments of deep learning-based methods in inter- and intra-modality image synthesis by listing and highlighting the proposed methods, study designs, and reported performances with related clinical applications on representative studies. The challenges among the reviewed studies were then summarized with discussion.

A phase I/II trial of 5-fraction stereotactic radiosurgery with 5-mm margins with concurrent temozolomide in newly diagnosed glioblastoma: primary outcomes.

BACKGROUND: We sought to determine the maximum tolerated dose (MTD) of 5-fraction stereotactic radiosurgery (SRS) with 5-mm margins delivered with concurrent temozolomide in newly diagnosed glioblastoma (GBM). METHODS: We enrolled adult patients with newly diagnosed glioblastoma to 5 days of SRS in a 3 + 3 design on 4 escalating dose levels: 25, 30, 35, and 40 Gy. Dose limiting toxicity (DLT) was defined as Common Terminology Criteria for Adverse Events grades 3-5 acute or late CNS toxicity, including adverse radiation effect (ARE), the imaging correlate of radiation necrosis. RESULTS: From 2010 to 2015, thirty patients were enrolled. The median age was 66 years (range, 51-86 y). The median target volume was 60 cm3 (range, 14.7-137.3 cm3). DLT occurred in 2 patients: one for posttreatment cerebral edema and progressive disease at 3 weeks (grade 4, dose 40 Gy); another patient died 1.5 weeks following SRS from postoperative complications (grade 5, dose 40 Gy). Late grades 1-2 ARE occurred in 8 patients at a median of 7.6 months (range 3.2-12.6 mo). No grades 3-5 ARE occurred. With a median follow-up of 13.8 months (range 1.7-64.4 mo), the median survival times were: progression-free survival, 8.2 months (95% CI: 4.6-10.5); overall survival, 14.8 months (95% CI: 10.9-19.9); O6-methylguanine-DNA methyltransferase hypermethylated, 19.9 months (95% CI: 10.5-33.5) versus 11.3 months (95% CI: 8.9-17.6) for no/unknown hypermethylation (P = 0.03), and 27.2 months (95% CI: 11.2-48.3) if late ARE occurred versus 11.7 months (95% CI: 8.9-17.6) for no ARE (P = 0.08). CONCLUSIONS: The per-protocol MTD of 5-fraction SRS with 5-mm margins with concurrent temozolomide was 40 Gy in 5 fractions. ARE was limited to grades 1-2 and did not statistically impact survival.

Radiation, Immune Checkpoint Blockade and the Abscopal Effect: A Critical Review on Timing, Dose and Fractionation.

The combination of radiation and immunotherapy is currently an exciting avenue of pre-clinical and clinical investigation. The synergy between these two treatment modalities has the potential to expand the role of radiation from a purely local therapy, to a role in advanced and metastatic disease. Tumor regression outside of the irradiated field, known as the abscopal effect, is a recognized phenomenon mediated by lymphocytes and enhanced by checkpoint blockade. In this review, we summarize the known mechanistic data behind the immunostimulatory effects of radiation and how this is enhanced by immunotherapy. We also provide pre-clinical data supporting specific radiation timing and optimal dose/fractionation for induction of a robust anti-tumor immune response with or without checkpoint blockade. Importantly, these data are placed in a larger context of understanding T-cell exhaustion and the impact of immunotherapy on this phenotype. We also include relevant pre-clinical studies done in non-tumor systems. We discuss the published clinical trials and briefly summarize salient case reports evaluating the abscopal effect. Much of the data discussed here remains at the preliminary stage, and a number of interesting avenues of research remain under investigation.

Phase 1/2 Trial of 5-Fraction Stereotactic Radiosurgery With 5-mm Margins With Concurrent and Adjuvant Temozolomide in Newly Diagnosed Supratentorial Glioblastoma: Health-Related Quality of Life Results.

PURPOSE: We report a longitudinal assessment of health-related quality of life (HRQOL) in patients with glioblastoma (GBM) treated on a prospective dose escalation trial of 5-fraction stereotactic radiosurgery (25-40 Gy in 5 fractions) with concurrent and adjuvant temozolomide. METHODS: HRQOL was assessed using the European Organization for Research and Treatment of Cancer (EORTC) quality of life questionnaire core-30 (QLQ-C30) general, the EORTC quality of life questionnaire-brain cancer specific module (QLQ-BN20), and the M.D. Anderson Symptom Inventory-Brain Tumor (MDASI-BT). Questionnaires were completed at baseline and at every follow-up visit after completion of radiosurgery. Changes from baseline for 9 predefined HRQOL measures (global quality of life, physical functioning, social functioning, emotional functioning, motor dysfunction, communication deficit, fatigue, insomnia, and future uncertainty) were calculated at every time point. RESULTS: With a median follow-up time of 10.4 months (range, 0.4-52 months), 139 total HRQOL questionnaires were completed by the 30 patients on trial. Compliance with HRQOL assessment was 76% at 12 months. Communication deficit significantly worsened over time, with a decline of 1.7 points per month (P=.008). No significant changes over time were detected in the other 8 scales of our primary analysis, including global quality of life. Although 8 patients (27%) experienced adverse radiation effects (ARE) on this dose escalation trial, it was not associated with a statistically significant decline in any of the primary HRQOL scales. Disease progression was associated with communication deficit, with patients experiencing an average worsening of 13.9 points per month after progression compared with 0.7 points per month before progression (P=.01). CONCLUSION: On this 5-fraction dose escalation protocol for newly diagnosed GBM, overall HRQOL remained stable and appears similar to historical controls of 30 fractions of radiation therapy. Tumor recurrence was associated with worsening communication deficit, and ARE did not correlate with a decline in HRQOL.