Chang, Chih‐Wei

Abstract Background High‐resolution MRI is essential for accurate diagnosis and treatment planning, but its clinical acquisition is often constrained by long scanning times, which increase patient discomfort and reduce scanner throughput. While super‐resolution (SR) techniques offer a post‐acquisition solution to enhance resolution, existing deep learning approaches face trade‐offs between reconstruction fidelity and computational efficiency, limiting their clinical applicability. Purpose This study aims to develop an efficient and accurate deep learning framework for MRI SR that preserves fine anatomical detail while maintaining low computational overhead, enabling practical integration into clinical workflows. Materials and Methods We propose a novel SR framework based on multi‐head selective state‐space models (MHSSM) integrated with a lightweight channel multilayer perceptron (MLP). The model employs 2D patch extraction with hybrid scanning strategies (vertical, horizontal, and diagonal) to capture long‐range dependencies while mitigating pixel forgetting. Each MambaFormer block combines MHSSM, depthwise convolutions, and gated channel mixing to balance local and global feature representation. The framework was trained and evaluated on two distinct datasets: 7T brain T1 MP2RAGE maps (142 subjects) and 1.5T prostate T2w MRI (334 subjects). Performance was compared against multiple baselines including Bicubic interpolation, GAN‐based (CycleGAN, Pix2pix, SPSR), transformer‐based (SwinIR), Mamba‐based (MambaIR), and diffusion‐based (I 2 SB, Res‐SRDiff) methods. Results The proposed model demonstrated superior performance across all evaluation metrics while maintaining exceptional computational efficiency. On the 7T brain dataset, our method achieved the highest structural similarity (SSIM: ) and peak signal‐to‐noise ratio (PSNR: dB), along with the best perceptual quality scores (LPIPS: ; GMSD: ). These results represented statistically significant improvements over all baselines (), including a 2.1% SSIM gain over SPSR and a 2.4% PSNR improvement over Res‐SRDiff. For the prostate dataset, the model similarly outperformed competing approaches, achieving SSIM of , PSNR of dB, LPIPS of , and GMSD of . Notably, our framework accomplished these results with only 0.9 million parameters and 57 GFLOPs, representing reductions of 99.8% in parameters and 97.5% in computational operations compared to Res‐SRDiff, while also substantially outperforming SwinIR and MambaIR in both accuracy and efficiency metrics. Conclusion The proposed framework provides a computationally efficient yet accurate solution for MRI SR, delivering well‐defined anatomical details and improved perceptual fidelity across anatomically distinct datasets. By significantly reducing computational demands while maintaining state‐of‐the‐art performance, the model offers strong potential for feasibility toward clinical translation and scalable integration into future imaging workflows.

Abstract Background Standardizing beam modeling in the treatment planning system is challenging due to machine‐specific configuration variations. Because of the proton therapy system (PTS) complexity and continuous development, there is no vendor's representative (“golden”) beam data like in LINACs at this stage. Purpose The primary goal of this study is to create a PTS‐specific repository of source model parameters and beam commissioning data for scanning proton therapy treatment planning systems and establish a set of reference values with associated bands of variations for this data. Methods We conducted a survey of 31 PTSs at 27 proton therapy centers to gather beam commissioning source model parameters used in their treatment planning system, ensuring a diverse selection of PTSs from major vendors: Hitachi, IBA, Varian, and Mevion. For each proton therapy center, we collected (i) beam meterset calibration in protons per MU, (ii) in‐air spot size at isocenter in terms of standard deviation in x‐ (crossline, σ x ) and y‐ (inline, σ y ) directions, (iii) in‐air angular spread at isocenter in x‐direction (θ x ) and y‐direction (θ y ) and (iv) distal falloff. For each PTS, we plotted each parameter as a function of nominal energy and performed polynomial regression analysis with optimal model selection based on Akaike Information Criterion. We calculated intraclass correlation coefficients (ICC) to quantify inter‐PTS variability and generated uncertainty bands representing standard deviations across PTSs for each parameter. Additionally, we computed percentage deviations of each individual PTS from the overall multi‐vendor mean to identify systematic vendor‐specific patterns and outliers across the 31 total PTSs analyzed. Results Multi‐vendor beam parameter analysis across 31 PTSs revealed systematic vendor‐specific patterns in inter‐PTS consistency and energy dependencies. Beam meterset calibration demonstrated excellent inter‐PTS consistency across most vendors (ICC: Varian ProBeam ≈ 0, IBA Proteus ONE = 0.006, Mevion S250i with HYPERSCAN = 0.015), with IBA Proteus PLUS systems showing moderate variation (ICC = 0.156 for the dedicated nozzle, ICC = 0.248, for the universal nozzle). Spot size and angular spread variability were highly vendor‐dependent, ranging from excellent consistency in IBA Proteus ONE to substantial variation in IBA Proteus PLUS with the universal nozzle (angular spread ICC = 0.566). Distal falloff maintained excellent consistency across all vendors (ICC < 0.023), indicating reliable energy spread characteristics. Uncertainty band analysis revealed characteristic energy‐dependent patterns, with most systems showing larger uncertainties at lower energies for spot size and angular spread, while IBA Proteus PLUS with the universal nozzle exhibited the largest uncertainty bands overall. Percentage deviation analysis demonstrated vendor‐specific clustering patterns, with some systems showing systematic positive or negative deviations from the multi‐vendor mean. Conclusions The reference data provided in this work will help to cross‐check the beam model during treatment planning system commissioning. Furthermore, this information is useful for Monte Carlo applications and research, where beam characteristics are required to set up phase space parameters, thereby avoiding the need to model the entire PTS. Finally, the results of this study will have indispensable educational value by providing valuable insights into the characteristics and capabilities of different PTSs.

AbstractPurposeMetallic implants have been correlated to local control failure for spinal sarcoma and chordoma patients due to the uncertainty of implant delineation from computed tomography (CT). Such uncertainty can compromise the proton Monte Carlo dose calculation (MCDC) accuracy. A component method is proposed to determine the dimension and volume of the implants from CT images.MethodsThe proposed component method leverages the knowledge of surgical implants from medical supply vendors to predefine accurate contours for each implant component, including tulips, screw bodies, lockers, and rods. A retrospective patient study was conducted to demonstrate the feasibility of the method. The reference implant materials and samples were collected from patient medical records and vendors, Medtronic and NuVasive. Additional CT images with extensive features, such as extended Hounsfield units and various reconstruction diameters, were used to quantify the uncertainty of implant contours.ResultsFor in vivo patient implant estimation, the reference and the component method differences were 0.35, 0.17, and 0.04 cm3for tulips, screw bodies, and rods, respectively. The discrepancies by a conventional threshold method were 5.46, 0.76, and 0.05 cm3, respectively. The mischaracterization of implant materials and dimensions can underdose the clinical target volume coverage by 20 cm3for a patient with eight lumbar implants. The tulip dominates the dosimetry uncertainty as it can be made from titanium or cobalt–chromium alloys by different vendors.ConclusionsA component method was developed and demonstrated using phantom and patient studies with implants. The proposed method provides more accurate implant characterization for proton MCDC and can potentially enhance the treatment quality for proton therapy. The current proof‐of‐concept study is limited to the implant characterization for lumbar spine. Future investigations could be extended to cervical spine and dental implants for head‐and‐neck patients where tight margins are required to spare organs at risk.