Prostate-specific membrane antigen positron emission tomography/computed tomography (PSMA PET/CT) and contrast-enhanced magnetic resonance imaging (MRI) are extensively used for the clinical diagnosis of prostate cancer (PCa). However, both modalities are prone to misdiagnoses or missed lesions. Fusing these complementary data sources, specifically the combined CT-PET image data from PSMA PET/CT scans and contrast-enhanced MRI, may improve diagnostic accuracy, with precise spatial registration being a crucial prerequisite for effective image fusion. While previous studies have used software tools for MRI-PSMA PET/CT fusion, most rely on MRI-CT-based anatomical registration and treat PET as a secondary overlay, thereby underutilizing PSMA's tumor-specific metabolicinformation. To propose a global and local information-based registration network (GLNet) that integrates PSMA PET/CT's functional-semantic features with MRI's high-resolution soft-tissue details to improve PCa lesiondiagnosis. To improve prostate image registration, GLNet was designed using semantic gating convolutional (SGC) modules and a convolutional long short-term memory network based on a U-shaped channel (U-CLSTM). Specifically, SGC modules enhance perception of the prostate gland using global information, while U-CLSTM improves attention to local tumor regions. The dataset comprised 77 clinical cases, each verified by two experienced physicians through clinical biopsy. After data augmentation, 244 cases were used for training and validation, and 64 cases for testing. GLNet's performance was compared against state-of-the-art methods: symmetric normalization (SyN), VoxelMorph (VM), volume tweening network (VTN), and recursive deformable pyramid (RDP). Statistical analyses were conducted using the Kruskal-Wallis test with Bonferroni correction for pairwise comparisons, and effect sizes were assessed using Cohen'sd. GLNet achieved Dice similarity coefficient (DSC) of 0.76 0.11, HD95 of 9.32 3.13 mm, average symmetric surface distance (ASD) of 1.69 0.65 mm, and a near-zero negative Jacobian proportion of for prostate gland registration. In contrast to other networks, GLNet demonstrated significant improvements (p 0.001), with DSC increasing by - , 5th-percentile Hausdorff distance (HD95) decreasing by 1.69-30.03 mm, and ASD reducing by 0.24-15.44 mm. Cohen's d values indicated large effect sizes. For local lesion detection, GLNet achieved precision, recall, and an F1-score of 0.86, which outperformed other methods by - in precision, - in recall, and 0.21-0.37F1-score. This study presents GLNet, a deep learning-based non-rigid registration network that fuses PSMA PET/CT and contrast-enhanced MRI. GLNet outperforms existing methods in registration accuracy and lesion detection, thereby offering a promising approach for integrating structural and functional imaging in clinical PCadiagnosis.

This study investigated the use of diffusion MRI models for diagnosing osteoporosis in women. Traditional methods, like DXA, struggle to assess bone quality. The research found that CTRW and FROC models effectively distinguished between healthy and osteoporotic bones, offering a promising approach for bone quality assessment and fracture risk prediction. This study aims to evaluate the diagnostic efficacy of the conventional diffusion-weighted imaging (DWI), continuous-time random walk (CTRW), and fractional order calculus (FROC) models for osteoporosis in women. A total of 131 women with an average age of 60.6 ± 8.5 years underwent magnetic resonance imaging (MRI) and dual-energy X-ray absorptiometry (DXA) of the lumbar spine. Diffusion metrics were derived from regions of interest (ROIs) on the b = 0 map, and applied to the quantitative map of conventional DWI (ADC), CTRW (αCTRW, βCTRW, and DCTRW), and FROC (µFROC, βFROC, and DFROC) models. These metrics were compared among three groups of normal, osteopenia, and osteoporosis subjects. Receiver operating characteristic (ROC) curves evaluated their diagnostic performance, and Spearman correlation assessed the relationship between diffusion parameters and clinical factors. P < 0.05 was considered statistically significant. ADC, DCTRW, DFROC, and µFROC values were significantly different in the osteoporosis and osteopenia groups compared to the normal group (p = 0.001 ∼ 0.014). The DCTRW and DFROC metrics exhibited superior diagnostic performance, with the areas under the ROC curves (AUC) values of 0.699 and 0.697, respectively, surpassing the AUC of the conventional ADC of 0.687. Furthermore, a composite model combining αCTRW, βCTRW, and DCTRW achieved an AUC of 0.722 for differentiating between the normal and osteoporosis groups, outperforming individual diffusion metrics and the combined FROC model. Moreover, Spearman correlations analysis showed that ADC, DCTRW, DFROC and µFROC metrics exhibited significant correlation with FRAX (Fracture Risk Assessment Tool) scores. The CTRW diffusion metrics demonstrate significant potential as biomarkers for osteoporosis diagnosis in women, offering a valuable method for assessing bone quality and predicting fracture risk.

Deep learning-based super-resolution is a promising solution for restoring dynamic magnetic resonance imaging (dMRI) from undersampled acquisitions; however, physiological motion precludes obtaining perfectly aligned low- and high-resolution (LR-HR) training pairs. Previous studies have circumvented this limitation by retrospectively simulating LR from HR images, introducing a domain gap that impairs performance on realdata. This study proposes a generic registration-assisted super-resolution framework (RegSR) that enables direct supervised learning on clinically-acquired, misaligned LR-HR pairs. Inspired by our finding that improved registration accuracy directly enhances super-resolution fidelity, we incorporate three improvements into our framework. First, RegSR capitalizes on a synergistic interplay where super-resolution outputs reduce image-quality discrepancies and registration dynamically corrects spatial offsets, enabling pixel-level supervision for both tasks to enhance their performance mutually. Furthermore, we introduce a multi-scale recursive registration network (MRReg) that estimates deformation fields in a deep-to-shallow manner over feature maps, yielding precise spatial corrections amidst noise and artifacts in LR images. Finally, a dual-coordinate training scheme is designed to decouple super-resolution and registration, ensuring that each module specializes exclusively in its role without functionalinterference. Evaluations using an abdominal four-dimensional MRI dataset (20 training, six validation cases) and a cardiac cine MRI dataset (100 training, 50 validation cases) show that RegSR significantly outperforms state-of-the-art methods in both structural fidelity and visual realism. Quantitatively, RegSR reduces the MAE mean absolute error by 8.15%, increases the structural similarity index by 3.47% and the peak signal-to-noise ratio PSNR by 2.48%, achieves the best learned perceptual image patch similarity LPIPS score, and ranks second in the natural image quality evaluator. Moreover, RegSR is compatible with diverse super-resolution backbones, consistently improving their performance under misaligned trainingconditions. RegSR provides a robust, generalizable solution for supervised super-resolution training on real-world dMRI, effectively addressing motion-induced misalignment while enhancing reconstructionquality.

PurposeTo develop clinically relevant test cases for commissioning Model‐Based Dose Calculation Algorithms (MBDCAs) for 192Ir High Dose Rate (HDR) gynecologic brachytherapy following the workflow proposed by the TG‐186 report and the WGDCAB report 372.Acquisition and validation methodsTwo cervical cancer intracavitary HDR brachytherapy models were developed based on a real patient, using either uniformly structured regions or realistic segmentation. The patient's computed tomography (CT) images were processed, converted to a series of digital imaging and communications in medicine (DICOM) CT images, and imported into two treatment planning systems (TPSs), the Oncentra Brachy and BrachyVision. The original segmentation of the clinical case was augmented to enable a thorough dosimetric analysis. The actual clinical treatment plan was generally maintained, with the source replaced by a generic 192Ir HDR source. Dose to medium in medium calculations were performed using the MBDCA option of each TPS, and three different Monte Carlo (MC) simulation codes. MC results demonstrated agreement within statistical uncertainty, while comparisons between the commercial TPS MBDCAs and a general‐purpose MC code highlighted both the advantages and limitations of the studied MBDCAs, suggesting potential approaches to overcome the challenges.Data format and usage notesThe datasets for the developed cases are available online at https://doi.org/10.5281/zenodo.15720996. The DICOM files include the treatment plan for each case, TPS, and the corresponding reference MC dose data. The package also contains a TPS‐ and case‐specific user guide for commissioning the MBDCAs, as well as files necessary to replicate the MC simulations.Potential applicationsThe provided datasets and proposed methodology can serve as a commissioning framework for TPSs that employ MBDCAs, as well as a benchmark for brachytherapy researchers using MC methods and MBDCA developers. They also facilitate intercomparisons of MBDCA performance and provide a quality assurance resource for evaluating future TPS software updates.

LATTICE, a form of spatially fractionated radiation therapy (SFRT) that delivers high-dose peaks and low-dose valleys within the target volume, has been clinically utilized for treating bulky tumors. However, its application to small-to-medium-sized target volumes remains challenging due to beam size limitations. To address the challenge of applying LATTICE radiation therapy to small-to-medium-sized targets, this work proposes a novel proton LATTICE (pLATTICE) modality using minibeams, namely minibeam-pLATTICE, that can extend the LATTICE approach for small-to-medium target volumes. Three minibeam-pLATTICE methods are introduced. (1) M0: a fixed minibeam aperture orientation (e.g., 0°) for all beam angles; (2) M1: alternated minibeam aperture orientations (e.g., between 0° and 90°), for consecutive beam angles; (3) M2: multiple minibeam aperture orientations (e.g., 0° and 90°) for each beam angle. The purpose of M1 or M2 is to correct anisotropic dose distribution at lattice peaks due to the planar spatial modulation of minibeams. For each minibeam-pLATTICE method, an optimization problem is formulated to optimize dose uniformity in target peaks and valleys, as well as dose-volume-histogram-based objectives. This optimization problem is solved using iterative convex relaxation and alternating direction method of multipliers (ADMM). Three minibeam-pLATTICE methods are validated to demonstrate the feasibility of minibeam-pLATTICE for two clinical head-and-neck (HN), one abdominal, and one brain case. The advantages of this modality over conventional beam (CONV) pLATTICE are evaluated by comparing peak-to-valley dose ratio (PVDR) and dose delivered to organs at risk (OAR). All three minibeam-pLATTICE modalities achieved improved plan quality compared to CONV, with M2 yielding the best results. For instance, in one HN case, the following improvements were observed: PVDR increased to 3.73 (M2), compared to 3.27 (CONV), 3.72 (M0), and 3.49 (M1), while the mean dose to the mandible was reduced to 0.18 Gy (M2), compared to 0.33 Gy (CONV), 0.17 Gy (M0), and 0.14 Gy (M1). A novel minibeam-pLATTICE modality is proposed that can generate lattice dose patterns for small-to-medium target volumes, which are not achievable with conventional pLATTICE due to beam size limitations. Peak dose anisotropy due to 1D planar minibeam apertures is corrected through inverse treatment planning with alternating or multiple minibeam apertures per beam angle.

Ultrahigh dose rate (UHDR) pencil beam scanning (PBS) proton therapy represents an emerging treatment modality that potentially reduces normal-tissue toxicities, termed the FLASH effect. Despite rapid clinical translation, accurate delivery of dose and dose rate is critical, and current quality assurance and beam monitoring methods have limited capabilities for detecting subtle delivery errors in both spatial and temporal domains. The limitations of existing dosimetry tools make robust characterization and validation of treatment plans during patient-specific quality assurance (PSQA) challenging. To test a previously validated, high-resolution scintillation imaging dosimetry (SID) system for detecting clinically relevant deviations in proton beam spot position and intensity during UHDR particle beam therapy. The secondary aim of this study was to investigate the impact of spot position and intensity errors on dose rate, emphasizing the need for high spatial and temporal resolution detection systems. Treatment plans were created for a Varian ProBeam system operating in FLASH mode. Two types of plans were developed, delivered, and imaged: a uniform diamond-shaped and a more complex plan derived from a stereotactic lung treatment protocol. A high-speed (4500 frames per second) imaging system was used to capture temporally and spatially resolved data of light output from a scintillator at isocenter during both types of UHDR PBS deliveries. Image processing was performed in MATLAB, calculating relevant treatment parameters such as cumulative dose, dose per spot, temporal dose deposition throughout the treatment field (dose rate mapping), and dose/dose rate area histograms. The imaging system was able to detect deviations in spot position as low as 0.5±0.3mm and in intensity as low as 7 cGy per spot. Imaging different preclinical treatment fields demonstrated the impact of potential treatment errors on dose rates and dose rate area histograms, with deviations in spot position of 3mm demonstrating an impact of±8% dose rate variations, for example. The spatial and temporal aspects of UHDR PBS deliveries were investigated, highlighting the importance of current high-resolution detectors. High-resolution scintillation imaging effectively identifies simulated beam delivery errors in UHDR proton therapy, revealing critical relationships between spatial accuracy and dose rate distribution.

Dose Computation is a key component of radiotherapy planning. As the number of cases in radiation therapy grows, the need for fast planning increases. However, existing dose computation approaches based on physics can be slow or not accurate enough. Deep learning based approaches offer a potential solution for fast and accurate dosecalculation. We propose a novel physics-informed deep learning based AI dose calculation method that is able to calculate the plan dose of clinical many field VMAT and IMRT plans to high accuracy and with highspeed. A novel two-stage approach is introduced. In stage one, incoming fluence from all fields is propagated using a Beer-Lambert law approach and accumulated per voxel in spherical harmonics coefficients. These coefficients together with the CT volume constitute the input to the stage two image-to-image neural network that predicts the actual dose. We performed large scale data generation on 1641 clinical plans from three different body sites. Using a special data augmentation scheme, over 100000 training input/outputs were used fortraining. The model was evaluated on clinical plans from multiple body regions using several gamma pass rates, relative and absolute errors as well as dose profiles. At a run-time of 1.6 s on a RTX 4090, the average gamma pass rate over all sites was 99.1% for 2%/2mm and 94.4% for 1%/1mm. Few to many field plan doses can be calculated quickly and to highaccuracy.

Deep learning has achieved remarkable success in medical image segmentation, particularly in ultrasound imaging, where deep neural networks have demonstrated near-expert performance. However, these models typically assume that training and test data follow the same distribution-an assumption that often fails in real-world clinical practice due to domain shifts caused by variations in imaging devices, acquisition protocols, and operator techniques. These discrepancies can significantly degrade model performance. Existing solutions-such as supervised fine-tuning, unsupervised domain adaptation, and domain generalization-require either costly labeled data or access to source domain data, limiting their scalability and clinical applicability. To address domain shift in real-world ultrasound image segmentation, this study proposes a test-time adaptation (TTA) framework that eliminates the need for source data or target labels, while ensuring robustness against distributional drift and catastrophic forgetting. We present Prototype Bank-Driven Test-Time Adaptation (PBTTA), a novel TTA framework consisting of two key modules: (1) the Dynamic Statistics Fusion Module (DSFM), which enables domain-level adaptation by dynamically adjusting batch normalization layers using fused statistics from the test sample and source domain; and (2) the Prototype Bank-Guided Semantic Adaptation Module (PBSAM), which maintains a dynamic prototype bank for each semantic class to support semantic-level adaptation. PBTTA employs a dual-classifier strategy that combines a prototype-based classifier for stable semantic guidance and a parameter-based classifier for flexible decision-making. Notably, PBTTA does not require backpropagation to update model parameters during test time adaptation phase, ensuring efficient and stable adaptation. PBTTA achieves state-of-the-art performance across both ultrasound breast and thyroid tumor segmentation tasks. On average, it improves the Dice score by 15.04% (to 64.82%) for breast tumor segmentation and by 8.88% (to 57.45%) for thyroid tumor segmentation, compared to non-adaptive baselines. Moreover, PBTTA exhibits excellent robustness under continuous domain shifts and effectively mitigates catastrophic forgetting.

Cirrhosis is the leading cause of liver disease-related morbidity and mortality worldwide. The destruction and remodeling of fibrous tissue, regenerated nodules, and microvascular system are the key pathological changes in the course of cirrhosis. Therefore, comprehensive visualization and analysis of the three-dimensional (3D) morphology of these characteristic structures using an appropriate imaging technique can provide a new approach for deep understanding of the spatial pathology of cirrhosis. To realize 3D virtual histopathology assessment of key microscopic structures of representative cirrhosis, such as biliary cirrhosis, hepatitis B cirrhosis (Hep B-cirrhosis), and alcoholic cirrhosis via iodine-enhanced x-ray phase-contrast CT (PCCT). Ten patients with biliary cirrhosis, 10 patients with Hep B-cirrhosis and 6 patients with alcoholic cirrhosis were included in the study. The integrated 3D virtual histopathology evaluation system of human cirrhosis was constructed through sample collection, iodine staining, PCCT imaging, 3D reconstruction, and quantitative evaluation. 3D observation and quantitative evaluation of key pathological anatomical structures, such as fibrous tissues, regenerated nodules, and microvascular system, were realized in all patients with cirrhosis through the 3D virtual histopathology evaluation system. 3D co-construction and spatial anatomy of fibrous tissues, regenerated nodules, and microvascular structure in patients with biliary cirrhosis, Hep B-cirrhosis, and alcoholic cirrhosis were performed by iodine-stained 3D virtual histopathology technology, which can be virtually sliced at any point and in any direction. Further 3D quantitative evaluation revealed: the fibrosis volume ratio in biliary cirrhosis, Hep B-cirrhosis, and alcoholic cirrhosis was 24.95±6.06 %, 11.34±5.05%, and 15.27±6.77%, respectively. The nodule volume in the three types of cirrhosis was 5.66×108±4.27×108 µm3, 7.73×109±1.88×109 µm3, and 1.36×109±7.71×108 µm3 respectively, and the septal thickness was 347.19±128.49, 184.06±70.84, and 134.77±41.64µm, respectively. In addition, the pseudo-lobule and single nodule structure of cirrhosis can be observed with high precision in 3D. A 3D digital pathological database of cirrhosis containing various microscopic structures and key pathological features can be established through the integrated virtual histopathology evaluation system, strengthening the arsenal of research instrumentation available for section-free virtual pathology of cirrhosis.