Medical physics最新文献

{"title":"Grating-based x-ray dark-field mammography: Assessing complementary imaging information in simple cystic lesions and typical fibroadenoma","authors":"Karin Hellerhoff,&nbsp;Wolfgang Gottwald,&nbsp;Kirsten Taphorn,&nbsp;Daniel Berthe,&nbsp;Michael Braun,&nbsp;Kai Wagner,&nbsp;Sandra Resch,&nbsp;Dominik John,&nbsp;Lisa Heck,&nbsp;Lorenz Birnbacher,&nbsp;Julia Herzen,&nbsp;Susanne Grandl","doi":"10.1002/mp.17603","DOIUrl":"10.1002/mp.17603","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>A significant proportion of false positive recalls of mammography-screened women is due to benign breast cysts and simple fibroadenomas. These lesions appear mammographically as smooth-shaped dense masses and require the recalling of women for a breast ultrasound to obtain complementary imaging information. They can be identified safely by ultrasound with no need for further assessment or treatment.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Purpose</h3>\u0000 \u0000 <p>Grating-based x-ray dark-field breast imaging allows contrast formation based on both attenuation and small-angle x-ray scattering and provides complementary imaging information in one single acquisition.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>Experiments with ex-vivo mastectomy samples were performed with a three-grating Talbot-Lau interferometer using a laboratory-based polychromatic x-ray source. Attenuation and dark-field images were correlated to clinical mammography and complementary diagnostic imaging techniques.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>Benign breast lesions with homogeneous internal structures such as fibroadenomas and simple fluid-filled cysts, typically presenting as dense breast lesions in standard mammography, showed a signal drop in the dark-field image. Complicated cysts provided a higher dark-field signal.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusions</h3>\u0000 \u0000 <p>The results presented show that grating-based x-ray dark-field mammography could provide complementary imaging information in one single acquisition, eliminating the need for a second examination to identify harmless cysts and simple fibroadenomas.</p>\u0000 </section>\u0000 </div>","PeriodicalId":18384,"journal":{"name":"Medical physics","volume":"52 4","pages":"2145-2154"},"PeriodicalIF":3.2,"publicationDate":"2025-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/mp.17603","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142928336","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":"Multi-angle acquisition and 3D composite reconstruction for organ-targeted PET using planar detectors","authors":"Anirudh Shahi,&nbsp;Harutyun Poladyan,&nbsp;Edward Anashkin,&nbsp;Borys Komarov,&nbsp;Brandon Baldassi,&nbsp;Madeline Rapley,&nbsp;Alexey Babich,&nbsp;Oleksandr Bubon,&nbsp;Alla Reznik","doi":"10.1002/mp.17606","DOIUrl":"10.1002/mp.17606","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;This study investigates a multi-angle acquisition method aimed at improving image quality in organ-targeted PET detectors with planar detector heads. Organ-targeted PET technologies have emerged to address limitations of conventional whole-body PET/CT systems, such as restricted axial field-of-view (AFOV), limited spatial resolution, and high radiation exposure associated with PET procedures. The AFOV in organ-targeted PET can be adjusted to the organ of interest, minimizing unwanted signals from other parts of the body, thus improving signal collection efficiency and reducing the dose of administered radiotracer. However, while planar detector PET technology allows for quasi-3D image reconstruction due to the separation between detector heads, it suffers from degraded axial spatial resolution and, consequently, reduced recovery coefficients (RCs) along the axial direction perpendicular to the detectors.&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;The purpose of this study was to evaluate the concept of multi-angle image acquisition with two planar PET detectors and composite full 3D image reconstruction. This leverages data collection from multiple polar angles to improve the axial spatial resolution in the direction perpendicular to the detector heads. In such, the concept allows to overcome the intrinsic limitations of planar detectors in axial resolution.&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;This study evaluates the improvement in the quality of images acquired with the Radialis organ-targeted PET camera through multi-angle image acquisition, in both experimental and simulated imaging scenarios. This includes the use of custom-made phantom with fillable spherical hot inserts, the NEMA NU4-2008 image quality (IQ) phantom, and simulations with a digital brain phantom. The analysis involves the comparison of line profiles drawn through the spherical hot inserts, image uniformity, RCs, and the reduction of smearing observed in the axial planes with and without the multi-angle acquisition strategy.&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;Significant improvements were observed in reducing smearing, enhancing image uniformity, and increasing RCs using the evaluated multi-angle acquisition method. In the composite images, the hot spheres appear more symmetrical in all planes. The image uniformity, calculated from the IQ phantom, improves from 7.79% and 10.98%, as measured in the images from the individual acquisitions, to 2.72% in the composite image. There is also an overall improvement in the R","PeriodicalId":18384,"journal":{"name":"Medical physics","volume":"52 4","pages":"2507-2519"},"PeriodicalIF":3.2,"publicationDate":"2024-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/mp.17606","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142901543","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":"Automatic calculation method for stenosis ratio based on dialysis access ultrasound image segmentation","authors":"Fengxin Shi,&nbsp;Dongming Zhu,&nbsp;Jia Zhi,&nbsp;Guocun Hou,&nbsp;Yaoyao Cui,&nbsp;Xiaocong Wang","doi":"10.1002/mp.17579","DOIUrl":"10.1002/mp.17579","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;Dialysis Access (DA) stenosis impacts hemodialysis efficiency and patient health, necessitating exams for early lesion detection. Ultrasound is widely used due to its non-invasive, cost-effective nature. Assessing all patients in large hemodialysis facilities strains resources and relies on operator expertise. Furthermore, it heavily relies on the experience and expertise of the operator. Therefore, it is essential to explore methods for the automatic analysis of DA ultrasound images to accurately calculate the stenosis ratios, thereby enhancing both diagnostic accuracy and treatment efficiency.&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 is aimed at employing image segmentation networks to conduct precise segmentation of the ultrasound images of DA lumens and automatically classify the types of stenosis. The segmentation outcomes are processed by means of morphological processing techniques for the automatic calculation of the DA stenosis ratio, thus enhancing the daily diagnostic efficiency of physicians and providing a substantial quantitative foundation for clinical decision-making.&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;Firstly, our study introduces a deep neural network-based approach for vascular lumen segmentation and classification, termed Vessel Lumen Segmentation and Classification-Net (VLSC-Net), aimed at the precise segmentation of the DA lumen in ultrasound images. We conducted comparative analyses of our network against U-Net, TransUNet, MultiResUnet, and ResUNet using metrics such as mean Intersection over Union (mIoU), Dice score, Accuracy, Hausdorff Distance (HD), and Average Symmetric Surface Distance (ASSD). A five-fold cross-validation was performed on a dataset comprising 1710 images for both comparison experiments and ablation studies; specifically, the training set included 1368 images while the test set contained 342 images. The significance of observed differences was assessed using the Mann-Whitney &lt;i&gt;U&lt;/i&gt;-test. To prevent the increase in the chance of making a Type I error (false positive) that occurs when many simultaneous tests are being conducted, we used the Bonferroni correction to address the problem of multiple comparisons. Since we did four groups of comparisons, the significance level (&lt;span&gt;&lt;/span&gt;&lt;math&gt;\u0000 &lt;semantics&gt;\u0000 &lt;mi&gt;α&lt;/mi&gt;\u0000 &lt;annotation&gt;$alpha$&lt;/annotation&gt;\u0000 &lt;/semantics&gt;&lt;/math&gt;) is adjusted by dividing it by 4. Secondly, we utilized morphological processing alongside feature extraction techniques to accurately delineate the edges of the lumen. This facilitated precise measurements of critical stenosis segment parameters. Finally, we au","PeriodicalId":18384,"journal":{"name":"Medical physics","volume":"52 3","pages":"1661-1678"},"PeriodicalIF":3.2,"publicationDate":"2024-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142901540","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":"Multiple attention channels aggregated network for multimodal medical image fusion","authors":"Jingxue Huang,&nbsp;Tianshu Tan,&nbsp;Xiaosong Li,&nbsp;Tao Ye,&nbsp;Yanxiong Wu","doi":"10.1002/mp.17607","DOIUrl":"10.1002/mp.17607","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;In clinical practices, doctors usually need to synthesize several single-modality medical images for diagnosis, which is a time-consuming and costly process. With this background, multimodal medical image fusion (MMIF) techniques have emerged to synthesize medical images of different modalities, providing a comprehensive and objective interpretation of the lesion.&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;Although existing MMIF approaches have shown promising results, they often overlook the importance of multiscale feature diversity and attention interaction, which are essential for superior visual outcomes. This oversight can lead to diminished fusion performance. To bridge the gaps, we introduce a novel approach that emphasizes the integration of multiscale features through a structured decomposition and attention interaction.&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;Our method first decomposes the source images into three distinct groups of multiscale features by stacking different numbers of diverse branch blocks. Then, to extract global and local information separately for each group of features, we designed the convolutional and Transformer block attention branch. These two attention branches make full use of channel and spatial attention mechanisms and achieve attention interaction, enabling the corresponding feature channels to fully capture local and global information and achieve effective inter-block feature aggregation.&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;For the MRI-PET fusion type, MACAN achieves average improvements of 24.48%, 27.65%, 19.24%, 27.32%, 18.51%, and 10.33% over the compared methods in terms of Q&lt;sub&gt;cb&lt;/sub&gt;, AG, SSIM, SF, Q&lt;sub&gt;abf&lt;/sub&gt;, and VIF metrics, respectively. Similarly, for the MRI-SPECT fusion type, MACAN outperforms the compared methods with average improvements of 29.13%, 26.43%, 18.20%, 27.71%, 16.79%, and 10.38% in the same metrics. In addition, our method demonstrates promising results in segmentation experiments. Specifically, for the T2-T1ce fusion, it achieves a Dice coefficient of 0.60 and a Hausdorff distance of 15.15. Comparable performance is observed for the Flair-T1ce fusion, with a Dice coefficient of 0.60 and a Hausdorff distance of 13.27.&lt;/p&gt;\u0000 &lt;/section&gt;\u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Conclusion&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;The proposed multiple attention channels aggregated network (MACAN) can effectively retain the complementary information from source images. The evaluation of MACAN through medical image fusion and segmentation experiments on public datasets demonstrated","PeriodicalId":18384,"journal":{"name":"Medical physics","volume":"52 4","pages":"2356-2374"},"PeriodicalIF":3.2,"publicationDate":"2024-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142901548","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":"A unified deep-learning framework for enhanced patient-specific quality assurance of intensity-modulated radiation therapy plans","authors":"Hui Khee Looe,&nbsp;Philipp Reinert,&nbsp;Julius Carta,&nbsp;Björn Poppe","doi":"10.1002/mp.17601","DOIUrl":"10.1002/mp.17601","url":null,"abstract":"&lt;div&gt;\u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Background&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;Modern radiation therapy techniques, such as intensity-modulated radiation therapy (IMRT) and volumetric-modulated arc therapy (VMAT), use complex fluence modulation strategies to achieve optimal patient dose distribution. Ensuring their accuracy necessitates rigorous patient-specific quality assurance (PSQA), traditionally done through pretreatment measurements with detector arrays. While effective, these methods are labor-intensive and time-consuming. Independent calculation-based methods leveraging advanced dose algorithms provide a reduced workload but cannot account for machine performance during delivery.&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 introduces a novel unified deep-learning (DL) framework to enhance PSQA. The framework can combine the strengths of measurement- and calculation-based approaches.&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 comprehensive artificial training dataset, comprising 400,000 samples, was generated based on a rigorous mathematical model that describes the physical processes of radiation transport and interaction within both the medium and detector. This artificial data was used to pretrain the DL models, which were subsequently fine-tuned with a measured dataset of 400 IMRT segments to capture the machine-specific characteristics. Additional measurements of five IMRT plans were used as the unseen test dataset. Within the unified framework, a forward prediction model uses plan parameters to predict the measured dose distributions, while the backward prediction model reconstructs these parameters from actual measurements. The former enables a detailed control point (CP)-wise analysis. At the same time, the latter facilitates the reconstruction of treatment plans from the measurements and, subsequently, dose recalculation in the treatment planning system (TPS), as well as an independent second check software (VERIQA). This method has been tested with an OD 1600 SRS and an OD 1500 detector array with distinct spatial resolution and detector arrangement in combination with a dedicated upsampling model for the latter.&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 final models could deliver highly accurate predictions of the measurements in the forward direction and the actual delivered plan parameters in the backward direction. In the forward direction, the test plans reached median gamma passing rates better than 94% for the OD 1600 SRS measurements. The upsampled OD 1500 measurements show similar performance with similar median gamma passing rates but a slightly ","PeriodicalId":18384,"journal":{"name":"Medical physics","volume":"52 3","pages":"1878-1892"},"PeriodicalIF":3.2,"publicationDate":"2024-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/mp.17601","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142883980","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":"Characterization of LiF TLD-100 in carbon ion beams for remote audits","authors":"Paige A. Taylor,&nbsp;Alfredo Mirandola,&nbsp;Mario Ciocca,&nbsp;Shannon Hartzell,&nbsp;Giuseppe Magro,&nbsp;Paola Alvarez,&nbsp;Christine B. Peterson,&nbsp;Christopher R. Peeler,&nbsp;Eugene J. Koay,&nbsp;Rebecca M. Howell,&nbsp;Stephen F. Kry","doi":"10.1002/mp.17605","DOIUrl":"10.1002/mp.17605","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;A passive dosimeter framework for the measurement of dose in carbon ion beams has yet to be characterized or implemented for regular use.&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 work determined the dose calculation correction factors for absorbed dose in thermoluminescent dosimeters (TLDs) in a therapeutic carbon ion beam. TLD could be a useful tool for remote audits, particularly in the context of clinical trials as new protocols are developed for carbon ion radiotherapy.&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;TLD-100 were irradiated in a carbon ion beam at the Centro Nazionale di Adroterapia Oncologica (CNAO) in Pavia, Italy. The dose correction factors for linearity, fading, and beam quality were characterized. Fading was characterized from 5 to 100 days post-irradiation. For linearity, the TLDs were irradiated to absorbed doses ranging from 1 to 15 Gy in both the entrance of a high-energy pristine carbon ion peak and the center of a 2 cm spread-out Bragg peak. For beam quality, the TLD was irradiated to the same absorbed dose (3 Gy) in several pristine carbon ion Bragg peaks, as well as in several spread-out Bragg peaks. Each correction factor was calculated and compared to photon correction factors. The correction factors were also compared between high and low dose-averaged linear energy transfer (LET&lt;sub&gt;D&lt;/sub&gt;) in the carbon ion beams. The absorbed dose was compared between ion chamber and TLD-100 in the several tissue substitute phantom materials, applying the carbon ion TLD correction factors.&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;There was no statistically significant difference in the TLD fading correction factor between photons, low LET&lt;sub&gt;D&lt;/sub&gt; carbon ion beams, or high LET&lt;sub&gt;D&lt;/sub&gt; carbon ion beams. The TLD linearity correction factor did differ between photons, low LET&lt;sub&gt;D&lt;/sub&gt; carbon ions, and high LET&lt;sub&gt;D&lt;/sub&gt; carbon ions. The beam quality correction factor was large and changed linearly with LET&lt;sub&gt;D&lt;/sub&gt;. The overall uncertainty of the carbon ion absorbed dose calculation was 3.9% at the one-sigma level, driven largely by a 3.5% uncertainty in the beam quality correction. TLD measurements were within 1.2% of ion chamber measurements in the phantom material for polyethylene, solid water (Gammex and Sun Nuclear), acrylic, blue water, and techtron HPV. TLD measurements in balsa wood were within 3.0% and cork was 6.6% low compared to ion chamber.&lt;/p&gt;\u0000 &lt;/section&gt;\u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Conclusion&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;TLD-100 can be used for passive dosimetry in a therapeutic car","PeriodicalId":18384,"journal":{"name":"Medical physics","volume":"52 3","pages":"1858-1866"},"PeriodicalIF":3.2,"publicationDate":"2024-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142883963","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":"An AI dose-influence matrix engine for robust pencil beam scanning protons therapy","authors":"Yaoying Liu,&nbsp;Xuying Shang,&nbsp;Nan Li,&nbsp;Zishen Wang,&nbsp;Chunfeng Fang,&nbsp;Yue Zou,&nbsp;Xiaoyun Le,&nbsp;Gaolong Zhang,&nbsp;Shouping Xu","doi":"10.1002/mp.17602","DOIUrl":"10.1002/mp.17602","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;Rapid planning is of tremendous value in proton pencil beam scanning (PBS) therapy in overcoming range uncertainty. However, the dose calculation of the dose influence matrix (D&lt;sub&gt;ij&lt;/sub&gt;) in robust PBS plan optimization is time-consuming and requires substantial acceleration to enhance efficiency.&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 accelerate the D&lt;sub&gt;ij&lt;/sub&gt; calculations in PBS therapy, we developed an AI-D&lt;sub&gt;ij&lt;/sub&gt; engine integrated into our in-house treatment planning system (TPS).&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;The AI-D&lt;sub&gt;ij&lt;/sub&gt; engine calculates spot dose using a transformer-based spot dose calculation model (SDM), which takes CT volumes (CT-bars, 256 &lt;span&gt;&lt;/span&gt;&lt;math&gt;\u0000 &lt;semantics&gt;\u0000 &lt;mo&gt;×&lt;/mo&gt;\u0000 &lt;annotation&gt;$ times $&lt;/annotation&gt;\u0000 &lt;/semantics&gt;&lt;/math&gt; 16 &lt;span&gt;&lt;/span&gt;&lt;math&gt;\u0000 &lt;semantics&gt;\u0000 &lt;mo&gt;×&lt;/mo&gt;\u0000 &lt;annotation&gt;$ times $&lt;/annotation&gt;\u0000 &lt;/semantics&gt;&lt;/math&gt; 16 voxels, 3 mm resolution) and energy (a float value) as inputs and outputs the spot dose distribution (256 &lt;span&gt;&lt;/span&gt;&lt;math&gt;\u0000 &lt;semantics&gt;\u0000 &lt;mo&gt;×&lt;/mo&gt;\u0000 &lt;annotation&gt;$ times $&lt;/annotation&gt;\u0000 &lt;/semantics&gt;&lt;/math&gt; 16 &lt;span&gt;&lt;/span&gt;&lt;math&gt;\u0000 &lt;semantics&gt;\u0000 &lt;mo&gt;×&lt;/mo&gt;\u0000 &lt;annotation&gt;$ times $&lt;/annotation&gt;\u0000 &lt;/semantics&gt;&lt;/math&gt; 16). The SDM was trained on over 200 000 CT-bars and Monte Carlo (MC) spot dose (spanning energy levels from 70 to 225 MeV). Clinical-implemented treatment plans for the head, lung, and liver, initially created on Raystation, were replanned using our AI-D&lt;sub&gt;ij&lt;/sub&gt; engine under identical gantry angles and uncertainties settings. After optimizing the spot weight, each in-house plan was recalculated using MCsquare for MC dose evaluation. The dose-volume histogram (DVH) metrics from the in-house TPS and Raystation were compared, evaluating both the optimized and MC doses.&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;In optimization, the differences of DVH metrics (%, Value&lt;sub&gt;in-house&lt;/sub&gt;—Value&lt;sub&gt;Raystation&lt;/sub&gt;) across all uncertainty scenarios between the in-house and Raystation plans were 0.93 ± 2.04% for clinical target volume (CTV) and −5.94 ± 12.19% for organ at risks (OARs). For the MC doses, the differences were 2.48 ± 2.78% for CTV and −5.47 ± 14.16% for OARs. The time cost of a robust AI-D&lt;sub&gt;ij&lt;/sub&gt; calculation can be within 2s on an RTX3090 GPU.&lt;/p&gt;\u0000 &lt;/section&gt;\u0000 ","PeriodicalId":18384,"journal":{"name":"Medical physics","volume":"52 3","pages":"1903-1913"},"PeriodicalIF":3.2,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142879351","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":"T1-contrast enhanced MRI generation from multi-parametric MRI for glioma patients with latent tumor conditioning","authors":"Zach Eidex,&nbsp;Mojtaba Safari,&nbsp;Richard L. J. Qiu,&nbsp;David S. Yu,&nbsp;Hui-Kuo Shu,&nbsp;Hui Mao,&nbsp;Xiaofeng Yang","doi":"10.1002/mp.17600","DOIUrl":"10.1002/mp.17600","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>Gadolinium-based contrast agents (GBCAs) are commonly used in MRI scans of patients with gliomas to enhance brain tumor characterization using T1-weighted (T1W) MRI. However, there is growing concern about GBCA toxicity. This study develops a deep-learning framework to generate T1-postcontrast (T1C) from pre-contrast multiparametric MRI.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Purpose</h3>\u0000 \u0000 <p>We propose the tumor-aware vision transformer (TA-ViT) model that predicts high-quality T1C images. The predicted tumor region is significantly improved (<i>p</i> &lt; 0.001) by conditioning the transformer layers from predicted segmentation maps through the adaptive layer norm zero mechanism. The predicted segmentation maps were generated with the multi-parametric residual (MPR) ViT model and transformed into a latent space to produce compressed, feature-rich representations. The TA-ViT model was applied to T1w and T2-FLAIR to predict T1C MRI images of 501 glioma cases from an open-source dataset. Selected patients were split into training (<i>N</i> = 400), validation (<i>N</i> = 50), and test (<i>N</i> = 51) sets. Model performance was evaluated with the peak-signal-to-noise ratio (PSNR), normalized cross-correlation (NCC), and normalized mean squared error (NMSE).</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>Both qualitative and quantitative results demonstrate that the TA-ViT model performs superior against the benchmark MPR-ViT model. Our method produces synthetic T1C MRI with high soft tissue contrast and more accurately synthesizes both the tumor and whole brain volumes. The synthesized T1C images achieved remarkable improvements in both tumor and healthy tissue regions compared to the MPR-ViT model. For healthy tissue and tumor regions, the results were as follows: NMSE: 8.53 ± 4.61E-4; PSNR: 31.2 ± 2.2; NCC: 0.908 ± 0.041 and NMSE: 1.22 ± 1.27E-4, PSNR: 41.3 ± 4.7, and NCC: 0.879 ± 0.042, respectively.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusion</h3>\u0000 \u0000 <p>The proposed method generates synthetic T1C images that closely resemble real T1C images. Future development and application of this approach may enable contrast-agent-free MRI for brain tumor patients, eliminating the risk of GBCA toxicity and simplifying the MRI scan protocol.</p>\u0000 </section>\u0000 </div>","PeriodicalId":18384,"journal":{"name":"Medical physics","volume":"52 4","pages":"2064-2073"},"PeriodicalIF":3.2,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142879379","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":"Automatic Pavlov ratio measurement method based on spinal landmarks identification by a deep-learning model","authors":"Yongli Wang,&nbsp;Chi Huang,&nbsp;Junhao Zhou,&nbsp;Xueyuan Zhang,&nbsp;Fei Ren,&nbsp;Benbo Zhang,&nbsp;Xiaowen Wang,&nbsp;Xiyue Cheng,&nbsp;Kai Cao,&nbsp;Yibo Dou,&nbsp;Peng Cao","doi":"10.1002/mp.17594","DOIUrl":"10.1002/mp.17594","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>Cervical canal stenosis is one of the important pathogenic factors of cervical spondylosis. The accuracy of the Pavlov ratio measurement is crucial for the diagnosis and treatment of cervical spinal stenosis. Manual measurement is influenced by observer variability, accompanied by its inefficiency, which affects clinical evaluation.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Purpose</h3>\u0000 \u0000 <p>To automatically and accurately measure the Pavlov ratio, we develop a novel deep-learning model by detecting keypoints of cervical spine and measure the Pavlov ratio on plain lateral cervical spine radiographs.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>We developed a two-stage deep-learning model; in the first stage, we employ the YOLOX model as the object detection network to locate the ROIs containing the vertebral bodies and spinous processes; in the second stage, we introduce the high-resolution net (HRNet) as keypoint detection network and a series of deconvolutional networks (DNs) as the heatmap-based regressor. Based on the mentioned combining algorithms, we can rapidly detect the 38 keypoints in plain lateral cervical spine radiographs, and then measure the Pavlov ratio of the cervical spine. Radiographs from Shanghai Changhai Hospital (a total of 874) were split into training and test subsets (787 and 87 radiographs, respectively). One hundred twelve cases from Shanghai Changzheng Hospital and 108 cases from Shanghai Fourth People's Hospital are used as external validation datasets.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>Our proposed model successfully achieved the objective of automating the recognition of spinal landmarks with the mean absolute error (MAE)ranged from 0.05 to 0.08, and the symmetric mean absolute percentage error (SMAPE) ranged from 4.54% to 6.43%. The achieved accuracy is comparable to that of seasoned medical professionals and notably surpasses the performance of junior physicians (SMAPE ranged from 8.74% to 26.19%). Furthermore, our model demonstrated excellent accuracy in external validation experiments (SMAPE ranged from 4.40% to 5.95%).</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusion</h3>\u0000 \u0000 <p>This study presents a novel YOLOX-HRNet-DN model to assist landmarks identification on lateral cervical spine radiographs and demonstrates excellent accuracy in measuring the Pavlov ratio. The proposed method could provide a potential tool for the automatic estimation of the Pavlov ratio to improve the efficiency and accuracy of the treatment workflow.</p>\u0000 </section>\u0000 </div>","PeriodicalId":18384,"journal":{"name":"Medical physics","volume":"52 3","pages":"1536-1545"},"PeriodicalIF":3.2,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142883961","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 denoising approach to improve shear wave phase velocity map reconstruction in ultrasound elastography","authors":"Phidakordor Sahshong,&nbsp;Akash Chandra,&nbsp;Karla P. Mercado-Shekhar,&nbsp;Manish Bhatt","doi":"10.1002/mp.17581","DOIUrl":"10.1002/mp.17581","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;Measurement noise often leads to inaccurate shear wave phase velocity estimation in ultrasound shear wave elastography. Filtering techniques are commonly used for denoising the shear wavefields. However, these filters are often not sufficient, especially in fatty tissues where the signal-to-noise ratio (SNR) can be very low.&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;The purpose of this study is to develop a deep learning approach for denoising shear wavefields in ultrasound shear wave elastography. This may lead to improved reconstruction of shear wave phase velocity image maps.&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;The study addresses noise by transforming particle velocity data into a time-frequency representation. A neural network with encoder and decoder convolutional blocks effectively decomposes the input and extracts the signal of interest, improving the SNR in high-noise scenarios. The network is trained on simulated phantoms with elasticity values ranging from 3  to 60 kPa. A total of 1 85 570 samples with 80%–20&lt;span&gt;&lt;/span&gt;&lt;math&gt;\u0000 &lt;semantics&gt;\u0000 &lt;mo&gt;%&lt;/mo&gt;\u0000 &lt;annotation&gt;$%$&lt;/annotation&gt;\u0000 &lt;/semantics&gt;&lt;/math&gt; split were used for training and validation. The approach is tested on experimental phantom and ex-vivo goat liver tissue data. Performance was compared with the traditional filtering methods such as bandpass, median, and wavelet filtering. Kruskal–Wallis one-way analysis of variance was performed to check statistical significance. Multiple comparisons were performed using the Mann–Whitney U test and Holm–Bonferroni adjustment of &lt;span&gt;&lt;/span&gt;&lt;math&gt;\u0000 &lt;semantics&gt;\u0000 &lt;mrow&gt;\u0000 &lt;mi&gt;p&lt;/mi&gt;\u0000 &lt;mo&gt;−&lt;/mo&gt;\u0000 &lt;mi&gt;values&lt;/mi&gt;\u0000 &lt;/mrow&gt;\u0000 &lt;annotation&gt;$p-{rm values}$&lt;/annotation&gt;\u0000 &lt;/semantics&gt;&lt;/math&gt;.&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 results are evaluated using SNR and the percentage of pixels that can be reconstructed in the phase velocity maps. The SNR levels in experimental data improved from –2 to 9.9 dB levels to 15.6 to 30.3 dB levels. Kruskal–Wallis one-way analysis showed statistical significance (&lt;span&gt;&lt;/span&gt;&lt;math&gt;\u0000 &lt;semantics&gt;\u0000 &lt;mrow&gt;\u0000 &lt;mi&gt;p&lt;/mi&gt;\u0000 &lt;mo&gt;&lt;&lt;/mo&gt;\u0000 &lt;mn&gt;0.05&lt;/mn&gt;\u0000 &lt;/mrow&gt;\u0000 &lt;annotation&gt;$p&lt;0.05$&lt;/annotation&gt;\u0000 &lt;/semantics&gt;&lt;/math&gt;). Multiple comparisons wit","PeriodicalId":18384,"journal":{"name":"Medical physics","volume":"52 3","pages":"1481-1499"},"PeriodicalIF":3.2,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142879324","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}