Medical physics最新文献

{"title":"Hybrid artificial intelligence echogenic components-based diagnosis of adnexal masses on ultrasound","authors":"Roni Yoeli-Bik,&nbsp;Heather M. Whitney,&nbsp;Hui Li,&nbsp;Agnes Bilecz,&nbsp;Jacques S. Abramowicz,&nbsp;Li Lan,&nbsp;Ryan E. Longman,&nbsp;Maryellen L. Giger,&nbsp;Ernst Lengyel","doi":"10.1002/mp.17983","DOIUrl":"https://doi.org/10.1002/mp.17983","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>Adnexal masses are heterogeneous and have varied sonographic presentations, making them difficult to diagnose correctly.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Purpose</h3>\u0000 \u0000 <p>Our study aimed to develop an innovative hybrid artificial intelligence/computer-aided diagnosis (AI/CADx)-based pipeline to distinguish between benign and malignant adnexal masses on ultrasound imaging based upon automatic segmentation and echogenic-based classification.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>The retrospective study was conducted on a consecutive dataset of patients with an adnexal mass. There was one image per mass. Mass borders were segmented from the background via a supervised U-net algorithm. Masses were spatially subdivided automatically into their hypo- and hyper-echogenic components by a physics-driven unsupervised clustering algorithm. The dataset was separated by patient into a training/validation set (95 masses; 70%) and an independent held-out test set (41 masses; 30%). Eight component-based radiomic features plus a binary measure of the presence or absence of solid components were used to train a linear discriminant analysis classifier to distinguish between malignant and benign masses. Classification performance was evaluated using the area under the receiver operating characteristic curve (AUC), along with sensitivity, specificity, negative predictive value, positive predictive value, and accuracy at target 95% sensitivity.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>The cohort included 133 patients with 136 adnexal masses. In distinguishing between malignant and benign masses, the pipeline achieved an AUC of 0.90 [0.84, 0.95] on the training/validation set and 0.93 [0.83, 0.98] on the independent test set. Strong diagnostic performance was observed at the target 95% sensitivity.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusion</h3>\u0000 \u0000 <p>A novel hybrid AI/CADx echogenic components-based ultrasound imaging pipeline can distinguish between malignant and benign adnexal masses with strong diagnostic performance.</p>\u0000 </section>\u0000 </div>","PeriodicalId":18384,"journal":{"name":"Medical physics","volume":"52 7","pages":""},"PeriodicalIF":3.2,"publicationDate":"2025-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/mp.17983","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144635406","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Use of a deep learning neural network to generate bone suppressed images for markerless lung tumor tracking","authors":"Jason Luce,&nbsp;Mandeep Kaur,&nbsp;Joseph Dingillo,&nbsp;Andrew Keeler,&nbsp;Mathias Lehmann,&nbsp;Daniel Morf,&nbsp;Liangjia Zhu,&nbsp;Hyejoo Kang,&nbsp;Ha Nguyen,&nbsp;Michal Walczak,&nbsp;Matthew M. Harkenrider,&nbsp;John C. Roeske","doi":"10.1002/mp.17949","DOIUrl":"https://doi.org/10.1002/mp.17949","url":null,"abstract":"&lt;div&gt;\u0000 \u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Background&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;Markerless tumor tracking (MTT) is being considered for real-time motion management of lung tumors. However, bony structures in conventional x-ray images can obfuscate the tumor, increasing tracking difficulty. Bone suppression using dual energy subtraction (DES) can improve tumor visibility but requires additional hardware or software that is not currently available with commercial on-board imaging (OBI) systems.&lt;/p&gt;\u0000 &lt;/section&gt;\u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Purpose&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;This study compares DES images to synthetic DES (sDES) images generated by a U-net neural network, examining both image quality and tracking results.&lt;/p&gt;\u0000 &lt;/section&gt;\u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Methods&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;High (120 kV) and low (60 kV) energy image pairs were obtained over 180-degree rotation using fast-kV switching for a motion phantom and 20 lung cancer patients. DES images were generated offline using weighted logarithmic subtraction. A U-net was then trained to transform 120 kV images into sDES images. Images from the phantom (2694 image pairs) and 20 patients (4499 image pairs), were divided into training, validation, and test sets consisting of 70%, 15%, and 15% of the images, and used for network training and evaluation. The similarity between sDES images and ground truth DES images were evaluated using histogram comparison, structural similarity index measure (SSIM), peak signal-to-noise ratio (PSNR), and the 2D correlation coefficient (2DCC). Separately, a template-tracking algorithm was used to predict tumor location on patient and phantom sDES images. Since there was no ground truth location for the patient images, the predicted locations of the tumor in the HE and sDES images were compared against the predicted locations in the DES images. For the phantom images, tracking success rate (TSR) was defined as the percentage of images in which the predicted and ground truth tumor location differed by &lt;2 mm, missing frames (MF) was defined as the percentage of images in which the tracking algorithm failed, and the mean absolute error (MAE) was also calculated from the differences between predicted and ground truth locations of the tumor.&lt;/p&gt;\u0000 &lt;/section&gt;\u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Results&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;Histogram count comparisons showed good agreement between the pixel distribution of sDES and DES images. Average SSIM, PSNR, and 2DCC scores for sDES images were 0.80 ± 0.05, 28.9 ± 3.4, and 0.97 ± 0.03 for phantom images, and 0.85 ± 0.04, 26.2 ± 3.5, and 0.97 ± 0.03 for patient images. For the patient images, the median tracking difference was 0.5 mm for HE versus DES images,","PeriodicalId":18384,"journal":{"name":"Medical physics","volume":"52 7","pages":""},"PeriodicalIF":3.2,"publicationDate":"2025-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/mp.17949","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144624759","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"ICD lead and primary metal artifact detection and inpainting in cardiac CT images","authors":"Trevor McKeown,&nbsp;H Michael Gach,&nbsp;Yao Hao,&nbsp;Hongyu An,&nbsp;Clifford G. Robinson,&nbsp;Phillip S. Cuculich,&nbsp;Deshan Yang","doi":"10.1002/mp.17947","DOIUrl":"https://doi.org/10.1002/mp.17947","url":null,"abstract":"&lt;div&gt;\u0000 \u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Background&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;Quantifying cardiac motion on pre-treatment CT imaging for stereotactic arrhythmia radiotherapy patients is difficult due to image artifacts caused by metal leads of implantable cardioverter-defibrillators (ICDs). The CT scanners’ onboard metal artifact reduction tool does not sufficiently reduce these artifacts. More advanced artifact reduction techniques require the raw CT projection data and thus do not apply to already reconstructed CT images. New methods are needed to accurately reduce the primary metal artifacts from ICD leads in already reconstructed CTs to recover the otherwise lost anatomical information.&lt;/p&gt;\u0000 &lt;/section&gt;\u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Purpose&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;To develop a methodology to automatically detect the ICD lead wires and surrounding primary metal artifacts in cardiac CT scans and inpaint the affected volume with anatomically consistent structures and values.&lt;/p&gt;\u0000 &lt;/section&gt;\u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Methods&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;Breath-hold ECG-gated 4DCT scans of 12 patients who underwent cardiac radiation therapy for treating ventricular tachycardia were collected. The primary metal artifacts in the images caused by the ICD leads were manually contoured. A 2D U-Net deep learning (DL) model was developed to segment the metal artifacts automatically using eight patients for training, two for validation, and two for testing. A dataset of 592 synthetic CTs was prepared by adding segmented metal artifacts from the patient 4DCT images to artifact-free cardiac CTs of 148 patients. A 3D image inpainting DL model was trained to refill the metal artifact portion in the synthetic images with realistic image contents that approached the ground truth artifact-free images. The trained inpainting model was evaluated by analyzing the automated segmentation results of the four heart chambers with and without artifacts on the synthetic dataset. Additionally, the raw cardiac patient images with metal artifacts were processed using the inpainting model and the results of metal artifact reduction were qualitatively inspected.&lt;/p&gt;\u0000 &lt;/section&gt;\u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Results&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;The artifact detection model worked well and produced a Dice score of 0.958 ± 0.008. The inpainting model for synthesized cases was able to recreate images nearly identical to the ground truth with a structural similarity index of 0.988 ± 0.012. With the chamber segmentations on the artifact-free images as the reference, the average surface Dice scores improved from 0.684 ± 0.247 to 0.964 ± 0.067 and the Hausdorff distance reduced from 3.4 ± 3.9 mm to 0.7 ± 0.7 mm. The inpainting model's use on cardiac patient CTs was visually inspected and the artifact-inpain","PeriodicalId":18384,"journal":{"name":"Medical physics","volume":"52 7","pages":""},"PeriodicalIF":3.2,"publicationDate":"2025-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144624402","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Implicit neural prior-guided diffusion for spectral CT reconstruction","authors":"Yizhong Wang,&nbsp;Ningning Liang,&nbsp;Shaoyu Wang,&nbsp;Jie Guo,&nbsp;Xinrui Zhang,&nbsp;Zhizhong Zheng,&nbsp;Ailong Cai,&nbsp;Lei Li,&nbsp;Bin Yan","doi":"10.1002/mp.17946","DOIUrl":"https://doi.org/10.1002/mp.17946","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>Spectral computed tomography (CT) plays a crucial role in various fields. However, the cumulative radiation dose from repeated x-ray CT examinations has raised concerns about potential health risks. Reducing the projection view is an effective strategy to reduce the radiation dose, but this will lead to a notable degradation in image quality, resulting in streaking artifacts.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Purpose</h3>\u0000 \u0000 <p>This work aims to develop a novel spectral CT reconstruction method to alleviate the ill-posed nature of the sparse sampling image reconstruction, while suppressing streaking artifacts and recovering detailed structures.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>In the scope of this work, we propose an implicit neural representation (INR) prior-guided diffusion (NeRDiff) method for spectral CT reconstruction, effectively combining the capabilities of implicit prior representation of INR and detail recovery of score-based generative models (SGM). NeRDiff includes two key designed phases: gradient-penalized INR learning and Pos-INR guided SGM reconstruction. In the first phase, an improved INR is devised and utilized to enhance the network's ability of representing complex signals by applying the variable-periodic activation function in multilayer perception network and adopting a dual-domain loss function. In the second phase, the INR prior is incorporated as a prior guiding Langevin dynamics sampling in the reverse diffusion process of SGM. In addition, a unified mathematical model and an efficient algorithm are proposed to enhance reconstruction stability.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>Quantitative and qualitative assessments on ultra-sparse-view datasets from numerical simulation and preclinical mouse underscore the superiority of NeRDiff over alternative methods. Especially in the simulation experiment, the NeRDiff method achieves improvement of at least 4.75 and 1.70 dB in PSNR under 20-view compared to the SGM proposed by Song et al. (Song-CT) and the wavelet-improved score-based generative model (WSGM).</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusions</h3>\u0000 \u0000 <p>In this work, we propose the NeRDiff method for highly ill-defined spectral CT reconstruction tasks. We have conducted a series of experiments in the ultra-sparse-view reconstruction task, and the experimental results consistently demonstrate the remarkable capabilities of NeRDiff in terms of anti-artifact performance and detail preservation.</p>\u0000 </section>\u0000 </div>","PeriodicalId":18384,"journal":{"name":"Medical physics","volume":"52 7","pages":""},"PeriodicalIF":3.2,"publicationDate":"2025-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144624833","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Virtual imaging trials are paving the way for the future of medical imaging","authors":"Andrew D. A. Maidment,&nbsp;Liesbeth Vancoillie","doi":"10.1002/mp.17959","DOIUrl":"https://doi.org/10.1002/mp.17959","url":null,"abstract":"&lt;p&gt;Over the past 5 years, virtual imaging trials (VITs) have gained significant momentum, driving advancements in the field of medical imaging. While several laboratories have been developing VITs with specific foci for years, the establishment of the National Center for Virtual Imaging Trials by the NIH and other recent efforts has brought broader recognition and visibility to the discipline. Since then, VITs have evolved into a global initiative, with active programs emerging across Europe and beyond. This shift reflects not only a geographic expansion but a fundamental transformation in how imaging research is approached—providing a platform for collaboration, innovation, and international engagement.&lt;/p&gt;&lt;p&gt;The 2024 VITM conference exemplified the growing importance of the field. More than a traditional scientific meeting, it showcased the strength of a global, interdisciplinary community dedicated to shaping the future of medical imaging. The event attracted a broad spectrum of participants, including students, researchers, industry professionals, and regulatory representatives. This diversity fostered dynamic discussions and affirmed that VITs are poised to become foundational to the development and evaluation of imaging technologies. We are excited to see this movement grow into a true community, where collaboration and shared knowledge are at the forefront.&lt;/p&gt;&lt;p&gt;Looking ahead to VITM 2025 in Manchester, the momentum continues to build, demonstrating the increased interest in VITs. Submitted abstracts span a wide range of topics and disciplines, highlighting the versatility and broad appeal of VITs. Interest in the field was further evident at SPIE 2025, where the findings from VITM 2024 were presented. The overwhelmingly positive response highlights the essential role of VITs, which are shaping the future of medical imaging research through a dynamic, evolving community that continues to innovate.&lt;/p&gt;&lt;p&gt;At their core, VITs provide a controlled, repeatable, and ethical framework for evaluating imaging technologies. Rooted in physical principles, VITs enable systematic approaches to testing, protocol optimization, and safe evaluation of new technologies, which will better ensure patient safety and exam efficacy. As adoption grows, the field is attracting increasing attention from physicists, engineers, clinicians, and policymakers—each recognizing the role VITs can play in accelerating progress while maintaining safety and rigor.&lt;/p&gt;&lt;p&gt;What is most striking is the global reach of this movement. The 2024 conference brought together participants from around the world, confirming that VITs have moved beyond niche status to become a truly international phenomenon. This global collaboration, powered by interdisciplinary expertise, is essential to the continued evolution of the field. It is through this shared commitment and interdisciplinary collaboration that VITs will continue to grow and evolve, driving innovation and advancing the field of m","PeriodicalId":18384,"journal":{"name":"Medical physics","volume":"52 7","pages":""},"PeriodicalIF":3.2,"publicationDate":"2025-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/mp.17959","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144634966","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Helical-like scan and upright CBCT imaging algorithms based on robotic-arm system","authors":"Tong Lin,&nbsp;Tianling Lyu,&nbsp;Jiashun Wang,&nbsp;Zhan Wu,&nbsp;Yan Xi,&nbsp;Dillenseger Jean-Louis,&nbsp;Wentao Zhu,&nbsp;Hao Tang,&nbsp;Shipeng Xie,&nbsp;Yang Chen","doi":"10.1002/mp.17997","DOIUrl":"https://doi.org/10.1002/mp.17997","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>Upright position CT scans enable body imaging under realistic conditions and have been widely adopted in rehabilitation medicine. However, they face challenges such as limited acquisition angles, floor stability issues, and a restricted field of view (FoV) along the <i>Z</i>-axis.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Purpose</h3>\u0000 \u0000 <p>The objective of this study is to propose an algorithm that enables high-quality image reconstruction in lightweight robotic-arm cone-beam CT (CBCT) systems, addressing challenges related to mechanical vibrations, a limited <i>Z</i>-axis scanning range, and inhomogeneous sampling.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>A long <i>Z</i>-axis helical steel ball phantom and a greedy ball-positioning algorithm are proposed to enhance geometrical calibration accuracy. A data completeness-driven method optimizes the scanning pitch for rapid full-body scans without significant image degradation. Additionally, a normalized projection-based FDK-style algorithm enhances reconstruction quality under reverse helical scanning constraints.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>The proposed upright reverse helical CBCT system demonstrated competitive reconstruction accuracy, achieving RMSE values of 0.0421 for Shepp–Logan, 0.3163 for foam-like, and 115.08 for VHP phantoms. Additionally, the proposed algorithm maintained computational efficiency, completing reconstructions in 45.3, 64.0, and 189.4 s, respectively, significantly outperforming iterative methods while preserving image quality. Furthermore, it significantly reduced radiation dose compared to conventional helical CT, achieving dose reductions from 460 to 50.7 mGy.cm for a 32 cm phantom and from 1050.0 to 112.6 mGy cm for a 16 cm water phantom.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusions</h3>\u0000 \u0000 <p>This work provides a robust solution for long-length <i>Z</i>-axis imaging in upright positions, as well as for unstable and nonstandard projection sampling. The proposed framework holds potential for advancing the use of robotic-arm upright CBCT systems in orthopedic functional evaluations and other clinical applications.</p>\u0000 </section>\u0000 </div>","PeriodicalId":18384,"journal":{"name":"Medical physics","volume":"52 7","pages":""},"PeriodicalIF":3.2,"publicationDate":"2025-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144635147","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Super-resolution CBCT on a new generation flat panel imager of a C-arm gantry linear accelerator","authors":"Licheng Kuo,&nbsp;Feifei Li,&nbsp;Yabo Fu,&nbsp;Hao Zhang,&nbsp;Laura A. Cervino,&nbsp;Jean M. Moran,&nbsp;Xiang Li,&nbsp;Tianfang Li","doi":"10.1002/mp.18000","DOIUrl":"https://doi.org/10.1002/mp.18000","url":null,"abstract":"&lt;div&gt;\u0000 \u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Background&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;Kilovoltage cone-beam computed tomography (kV CBCT) is vital for image-guided radiotherapy (IGRT). The new RTI4343iL panel on the Varian TrueBeam LINAC offers higher resolution but requires binning to achieve practical frame rates, leading to projection resolution loss. Existing super-resolution (SR) techniques have been applied to enhance CBCT image quality but primarily operate in the image domain, struggling to restore resolution loss in the projection domain.&lt;/p&gt;\u0000 &lt;/section&gt;\u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Purpose&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;This study aimed to evaluate the feasibility of a deep learning (DL) SR model, based on a conditional Generative Adversarial Networks (cGANs) architecture, for enhancing the spatial resolution of CBCT acquired with the new RTI4343iL panel in the projection domain. We hypothesize that projection-domain deblurring will primarily depend on the detector and minimally on patient anatomy, enhancing primary signal resolution without significantly altering scatter distribution. The study quantitatively assessed the impact of SR-enhanced projections on the quality of reconstructed CBCT images.&lt;/p&gt;\u0000 &lt;/section&gt;\u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Methods&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;A DLSR model was developed to enhance CBCT resolution in the projection domain.  For data acquisition, a Varian TrueBeam system equipped with the RTI4343iL panel was used, which features a native high-resolution image size of 2848 × 2144 pixels, but operates in 2 × 8 binning mode (1424 × 268 pixels) during CBCT scans to mitigate data readout speed limitations. Following thorax CBCT protocols, 576 pairs of CBCT projections were acquired at two resolutions using Rando, Longman, and Steeve phantoms. Of these, 460 pairs were allocated for model training, while 116 were reserved for validation. Model testing involved 144 Dynamic Thorax projections and CBCT reconstructions utilizing Catphan 604 phantoms. The DL SR model was built on a cGANs framework with a U-Net generator. Image enhancement was quantitatively evaluated with metrics including peak signal-to-noise ratio (PSNR), mean square error (MSE), structural similarity index measure (SSIM), feature similarity index measure (FSIM), and mean absolute percentage error (MAPE).&lt;/p&gt;\u0000 &lt;/section&gt;\u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Results&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;The DL SR model effectively enhanced image resolution, producing SR projections with greater detail and improved structural clarity. Quantitative analysis showed that the SR-enhanced projections outperformed upscaled low-resolution (LR) projections with higher PSNR (44.4 vs. 43.7, &lt;i&gt;p&lt;/i&gt; &lt; 0.001), lower MSE (187,083.7 vs. 205,364.4, &lt;i&gt;p&lt;/i&gt; &lt; 0.001), and improved MAPE (7.6% vs. 13.5%, &lt;i&gt;p&lt;/","PeriodicalId":18384,"journal":{"name":"Medical physics","volume":"52 7","pages":""},"PeriodicalIF":3.2,"publicationDate":"2025-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144635367","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Implementations of modulation complexity scores and their correlations with treatment plan quality in stereotactic radiation therapy","authors":"Mathieu Gaudreault,&nbsp;Phu Hoang Nguyen,&nbsp;Catherine Lawford,&nbsp;Rick Franich,&nbsp;Nicholas Hardcastle","doi":"10.1002/mp.17961","DOIUrl":"https://doi.org/10.1002/mp.17961","url":null,"abstract":"&lt;div&gt;\u0000 \u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Background&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;During the delivery of contemporary stereotactic radiation therapy treatment, the radiation dose is dynamically shaped by the multileaf collimator (MLC). The modulation complexity score (MCS) is a metric that quantifies MLC apertures. However, inconsistent definitions of the MCS have been introduced in the literature. Furthermore, investigations of correlations between complexity metrics and dosimetric plan quality remain scarce.&lt;/p&gt;\u0000 &lt;/section&gt;\u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Purpose&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;We aim to highlight differences between MCS definitions and assess their correlation with treatment plan quality in curated datasets of stereotactic radiation therapy treatment plans.&lt;/p&gt;\u0000 &lt;/section&gt;\u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Methods&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;Volumetric modulated arc therapy treatment plans from planning challenges of multi-metastasis stereotactic radiosurgery (SRS), pancreas stereotactic ablative body radiotherapy (SABR), and vertebral SABR were considered. According to the challenge guidelines, the quality of each plan was scored from 0 to 150. To quantify complexity, the two most used interpretations of the MCS were computed. In the first interpretation (beamMCS), the area aperture variability (AAV) was normalized by a virtual area constructed with the most open position of each leaf over all control points of the arc. In the second interpretation (cpMCS), the AAV was normalized by the virtual maximal leaf opening in each control point. Each quantity ranged between 0 (complex plan) and 1 (not complex plan). The Spearman correlation coefficient (&lt;span&gt;&lt;/span&gt;&lt;math&gt;\u0000 &lt;semantics&gt;\u0000 &lt;msub&gt;\u0000 &lt;mi&gt;r&lt;/mi&gt;\u0000 &lt;mi&gt;s&lt;/mi&gt;\u0000 &lt;/msub&gt;\u0000 &lt;annotation&gt;$r_{s}$&lt;/annotation&gt;\u0000 &lt;/semantics&gt;&lt;/math&gt;) and its associated &lt;i&gt;p&lt;/i&gt;-value were calculated between MCS and plan score. The process was repeated by stratifying the data per site, treatment planning system (TPS), and MLC type (conventional versus high definition).&lt;/p&gt;\u0000 &lt;/section&gt;\u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Results&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;The plans of 366 treatments were considered in the SRS (&lt;i&gt;n&lt;/i&gt; = 107), pancreas (&lt;i&gt;n&lt;/i&gt; = 137), and vertebral (&lt;i&gt;n&lt;/i&gt; = 122) planning challenge. The plan score ranged from 86.2 to 148.3 (median = 135). All plans considered, the complexity was higher with beamMCS than cpMCS (median &lt;span&gt;&lt;/span&gt;&lt;math&gt;\u0000 &lt;semantics&gt;\u0000 &lt;mo&gt;±&lt;/mo&gt;\u0000 &lt;annotation&gt;$pm$&lt;/annotation&gt;\u0000 &lt;/semantics&gt;&lt;","PeriodicalId":18384,"journal":{"name":"Medical physics","volume":"52 7","pages":""},"PeriodicalIF":3.2,"publicationDate":"2025-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/mp.17961","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144624752","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development and experimental validation of an in-house treatment planning system with greedy energy layer optimization for fast IMPT","authors":"Aoxiang Wang,&nbsp;Ya-Nan Zhu,&nbsp;Jufri Setianegara,&nbsp;Yuting Lin,&nbsp;Peng Xiao,&nbsp;Qingguo Xie,&nbsp;Hao Gao","doi":"10.1002/mp.17941","DOIUrl":"https://doi.org/10.1002/mp.17941","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>Intensity-modulated proton therapy (IMPT) using pencil beam technique scans tumor in a layer by layer, then spot by spot manner. It can provide highly conformal dose to tumor targets and spare nearby organs-at-risk (OAR). Fast delivery of IMPT can improve patient comfort and reduce motion-induced uncertainties. Since energy layer switching time dominants the plan delivery time, reducing the number of energy layers is important for improving delivery efficiency. Although various energy layer optimization (ELO) methods exist, they are rarely experimentally validated or clinically implemented, since it is technically challenging to integrate these methods into commercially available treatment planning system (TPS) that is not open-source.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Purpose</h3>\u0000 \u0000 <p>This work develops and experimentally validates an in-house TPS (IH-TPS) that incorporates a novel ELO method for the purpose of fast IMPT.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>The dose calculation accuracy of IH-TPS is verified against the measured beam data and the RayStation TPS. For treatment planning, a novel ELO method via greed selection algorithm is proposed to reduce energy layer switching time and total plan delivery time. To validate the planning accuracy of IH-TPS, the 3D gamma index is calculated between IH-TPS plans and RayStation plans for various scenarios. Patient-specific quality-assurance (QA) verifications are conducted to experimentally verify the delivered dose from the IH-TPS plans for several clinical cases.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>Dose distributions in IH-TPS matched with those from RayStation TPS, with 3D gamma index results exceeding 95% (2 mm, 2%). The ELO method significantly reduced the delivery time while maintaining plan quality. For instance, in a brain case, the number of energy layers was reduced from 78 to 40 (reduction of 38 layers), leading to a 62% reduction in total delivery time. Patient-specific QA validation with the IBA ProteusONE proton machine confirmed a &gt; 95% pass rate for all cases.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusions</h3>\u0000 \u0000 <p>An IH-TPS equipped with a novel ELO algorithm is developed and experimentally validated for the purpose of fast IMPT, with enhanced delivery efficiency and preserved plan quality.</p>\u0000 </section>\u0000 </div>","PeriodicalId":18384,"journal":{"name":"Medical physics","volume":"52 7","pages":""},"PeriodicalIF":3.2,"publicationDate":"2025-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144624835","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep learning model for coronary artery segmentation and quantitative stenosis detection in angiographic images","authors":"Baixiang Huang,&nbsp;Yu Luo,&nbsp;Guangyu Wei,&nbsp;Songyan He,&nbsp;Yushuang Shao,&nbsp;Xueying Zeng,&nbsp;Qing Zhang","doi":"10.1002/mp.17970","DOIUrl":"https://doi.org/10.1002/mp.17970","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 <p>Coronary artery disease (CAD) is a leading cause of cardiovascular-related mortality, and accurate stenosis detection is crucial for effective clinical decision-making. Coronary angiography remains the gold standard for diagnosing CAD, but manual analysis of angiograms is prone to errors and subjectivity.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Purpose</h3>\u0000 <p>This study aims to develop a deep learning-based approach for the automatic segmentation of coronary arteries from angiographic images and the quantitative detection of stenosis, thereby improving the accuracy and efficiency of CAD diagnosis.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 <p>We propose a novel deep learning-based method for the automatic segmentation of coronary arteries in angiographic images, coupled with a dynamic cohort method for stenosis detection. The segmentation model combines the MedSAM and VM-UNet architectures to achieve high-performance results. After segmentation, the vascular centerline is extracted, vessel diameter is computed, and the degree of stenosis is measured with high precision, enabling accurate identification of arterial stenosis.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 <p>On the mixed dataset (including the ARCADE, DCA1, and GH datasets), the model achieved an average IoU of 0.6308, with sensitivity and specificity of 0.9772 and 0.9903, respectively. On the ARCADE dataset, the average IoU was 0.6303, with sensitivity of 0.9832 and specificity of 0.9933. Additionally, the stenosis detection algorithm achieved a true positive rate of 0.5867 and a positive predictive value of 0.5911, demonstrating the effectiveness of our model in analyzing coronary angiography images.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusions</h3>\u0000 <p>SAM-VMNet offers a promising tool for the automated segmentation and detection of coronary artery stenosis. The model's high accuracy and robustness provide significant clinical value for the early diagnosis and treatment planning of CAD. The code and examples are available at https://github.com/qimingfan10/SAM-VMNet.</p>\u0000 </section>\u0000 </div>","PeriodicalId":18384,"journal":{"name":"Medical physics","volume":"52 7","pages":""},"PeriodicalIF":3.2,"publicationDate":"2025-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144634967","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}