Medical physics最新文献

{"title":"Correlation of ultrasound attenuation with proton density fat fraction across multiple organs in healthy volunteers.","authors":"Adrien Rohfritsch, Jules Courgenay, Antoine Biénassis, Elorri Olhagaray, Manon Basso, Benjamin Leporq, Benoit Allignet, David Melodelima","doi":"10.1002/mp.70475","DOIUrl":"10.1002/mp.70475","url":null,"abstract":"<p><strong>Background: </strong>Local determination of the attenuation in biological tissues has been the focus of extensive research over the past decades. Its characterization is of major interest for both noninvasive thermal therapies and diagnostic applications. Numerous ultrasound (US)-based methods have been investigated in recent years to assess attenuation in vivo.</p><p><strong>Purpose: </strong>In this article, we aim to map US attenuation in four organs of human volunteers: liver, pancreas, kidney, and breast. We propose to compare the mean attenuation values obtained in each tissue with the corresponding proton density fat fraction (PDFF) derived from quantitative magnetic resonance imaging (qMRI). This comparison allows us to (i) present a direct calculation method of the local US attenuation and (ii) investigate the relationship between the average fat content of each organ and its global US attenuation.</p><p><strong>Methods: </strong>The ultrasonic measurement method is in line with techniques originating from the spectral difference method. Here, the attenuation coefficient (AC) is estimated by insonifying tissues with a single plane wave and acquiring the backscattered echoes. This approach avoids the need for a reference medium to compensate for diffraction and focusing effects. The method is characterized and validated on a calibrated phantom and compared with two commonly used techniques on ex vivo liver tissues. Subsequently, attenuation maps and average values obtained from US imaging in healthy volunteers are compared with PDFF values measured by qMRI. Hepatic ( <math> <semantics><mrow><mi>n</mi> <mo>=</mo> <mn>12</mn></mrow> <annotation>$n = 12$</annotation></semantics> </math> ) renal ( <math> <semantics><mrow><mi>n</mi> <mo>=</mo> <mn>12</mn></mrow> <annotation>$n = 12$</annotation></semantics> </math> ), pancreatic ( <math> <semantics><mrow><mi>n</mi> <mo>=</mo> <mn>8</mn></mrow> <annotation>$n = 8$</annotation></semantics> </math> ) and breast ( <math> <semantics><mrow><mi>n</mi> <mo>=</mo> <mn>3</mn></mrow> <annotation>$n = 3$</annotation></semantics> </math> ) tissues were analyzed. Statistical significance was assessed using a paired t-test. To account for multiple comparisons, a Bonferroni correction was applied, resulting in an adjusted 5% significance threshold of <math> <semantics><mrow><mi>p</mi> <mo><</mo> <mn>0.0125</mn></mrow> <annotation>$p<0.0125$</annotation></semantics> </math> . Effect sizes were also reported using Cohen's <math><semantics><mi>d</mi> <annotation>$d$</annotation></semantics> </math> parameter. Effect sizes were considered large for <math> <semantics><mrow><mi>d</mi> <mo>≥</mo> <mn>0.8</mn></mrow> <annotation>$d ge 0.8$</annotation></semantics> </math> .</p><p><strong>Results: </strong>Measurements on the calibrated phantom showed relative errors between the measured mean values and the manufacturer values of 2% and 9%, respectively. Average AC of each organ was included in the confiden","PeriodicalId":94136,"journal":{"name":"Medical physics","volume":"53 5","pages":"e70475"},"PeriodicalIF":3.2,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13158173/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147871057","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"AAPM Spring Clinical Meeting - Abstract.","authors":"","doi":"10.1002/mp.70460","DOIUrl":"10.1002/mp.70460","url":null,"abstract":"","PeriodicalId":94136,"journal":{"name":"Medical physics","volume":"53 5","pages":"e70460"},"PeriodicalIF":3.2,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147825226","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A parallel algorithm for generating Pareto-optimal radiosurgery treatment plans.","authors":"Joakim da Silva, Daniel Hernández Escobar, Tor Kjellsson Lindblom, Håkan Nordström, Jens Sjölund","doi":"10.1002/mp.70454","DOIUrl":"10.1002/mp.70454","url":null,"abstract":"<p><strong>Background: </strong>Using inverse planning tools to create radiosurgery treatment plans is an iterative process, where clinical trade-offs are explored by changing the relative importance given to different objectives and rerunning the optimizer until a desirable plan is found. Simultaneously generating many plans corresponding to different objective weights, while the patient is awaiting treatment, would allow the planner to navigate clinical trade-offs interactively, without optimizing a new plan between each update.</p><p><strong>Purpose: </strong>We seek to optimize hundreds of Gamma Knife radiosurgery treatment plans, corresponding to different weightings of objectives, fast enough to allow interactive Pareto navigation of clinical trade-offs to be incorporated into the clinical workflow.</p><p><strong>Methods: </strong>We apply the alternating direction method of multipliers (ADMM) to the linear-program formulation of the optimization problem used in the clinical Lightning optimizer. We implement both a CPU and a GPU version of ADMM in Matlab and compare them to Matlab's built-in, single-threaded dual-simplex solver. The ADMM implementation is adapted to the optimization procedure used in the clinical software, with a bespoke algorithm for maximizing the overlap between low-dose points for different objective weights. The method is evaluated on a test dataset consisting of 20 cases from three different indications, with between one and nine targets and total target volumes ranging from 0.66 to 52 cm<sup>3</sup>.</p><p><strong>Results: </strong>The total optimization time to create 81 plans corresponding to different objective weightings varied from 63 to 520 s on CPU and from 1.8 to 40 s GPU, for the different test cases. As a reference, optimizing 81 plans using simplex took 100-51000 s, corresponding to ADMM speedups of 1.6-97 and 54-1500 times for the CPU and GPU, respectively. Increasing the number of plans to 441, corresponding to all combinations of slider values between 0.0 and 1.0 in steps of 0.05 in the clinical software, the total ADMM optimization time on GPU was between 3.0 and 110 s for the different test cases. Plan quality was evaluated by rerunning the ADMM optimization 20 times, each with a different random seed, for each test case and for nine objective weightings per case. The resulting relative differences in clinical metrics ( <math> <semantics><mrow><mi>mean</mi> <mo>±</mo> <mi>SD</mi></mrow> <annotation>${rm mean }pm{rm SD}$</annotation></semantics> </math> ) were 0.0 <math><semantics><mo>±</mo> <annotation>$pm$</annotation></semantics> </math> 0.2%, 0.0 <math><semantics><mo>±</mo> <annotation>$pm$</annotation></semantics> </math> 1.6%, 0.1 <math><semantics><mo>±</mo> <annotation>$pm$</annotation></semantics> </math> 0.8%, and 0.1 <math><semantics><mo>±</mo> <annotation>$pm$</annotation></semantics> </math> 3.0%, for coverage, selectivity, gradient index and beam-on time, respectively, compared to mean val","PeriodicalId":94136,"journal":{"name":"Medical physics","volume":"53 5","pages":"e70454"},"PeriodicalIF":3.2,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13158170/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147871072","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Passive cavitation imaging with p^th root coherence factor and sparse arrays: In vitro and in vivo assessment for histotripsy monitoring.","authors":"Abhinav Kumar Singh, Rishank Soni, Katia Flores Basterrechea, Kenneth Bader, Himanshu Shekhar","doi":"10.1002/mp.70397","DOIUrl":"10.1002/mp.70397","url":null,"abstract":"<p><strong>Background: </strong>Passive cavitation imaging (PCI) is under development to monitor histotripsy and other cavitation-mediated therapies. Image reconstruction using the conventional delay, sum, and integrate (DSI) beamforming approach produces PCI reconstructions with poor axial resolution and side lobe artifacts. Robust capon beamforming (RCB) improves imaging performance but is computationally expensive. Nonlinear beamforming approaches such as p^th root delay sum integrate (prDSI) and delay multiply and sum (DMAS) beamforming offer comparable or better performance than RCB without extensive computational overhead. However, enhancing imaging performance without compromising frame rates remains an active research area.</p><p><strong>Purpose: </strong>This work reports a coherence-factor modified with p^th root algebra p^th coherence factor-weighted delay sum and integrate (pCFwDSI) and evaluates its performance in vitro and in vivo. To reduce computational complexity, sparse array imaging was implemented with 32 and 16 transducer elements. We also employed graphical processing unit (GPU) computation to achieve real time frame rates.</p><p><strong>Methods: </strong>Histotripsy bubble clouds were generated in vitro in a red blood cell-doped phantom and in vivo in a porcine femoral vein using focused sources with 1 MHz and 1.5 MHz center frequencies. The acoustic emissions were received passively with a curvilinear (C5-2v) and linear (L11-5v) array transducer, respectively. Beamforming was performed using RCB, prDSI, and pCFwDSI with 128, 32 and 16 elements. The performance achieved was compared using the following metrics: -6 dB axial width, signal-to-interference ratio (SIR), binary statistical analysis, and structural similarity index measure (SSIM).</p><p><strong>Results: </strong>The pCFwDSI approach performed the best in terms of axial width and SIR, and prDSI showed intermediate performance between pCFwDSI and RCB. For binary statistical metrics, the performance achieved with p = 3 and 128 elements was similar for both approaches (within 2% of each other). In sparse array images implemented with 16 elements, grating lobes were observed in RCB and prDSI, but were suppressed in pCFwDSI. The SSIM of the sparse array (16 elements) with pCFwDSI (p = 3) was 96.34% relative to the images generated with the full aperture of 128 elements. Frame rates ranged from 18 to 91 Hz for pCFwDSI using RF data from 128 to 16 elements, respectively, which were similar to standard DSI.</p><p><strong>Conclusions: </strong>These results demonstrate pCFwDSI can improve axial resolution, reduce artifacts, and achieve clinically-relevant frame rates without increasing computational and data storage overhead. These findings could be a step towards enabling improved real time PCI monitoring of histotripsy.</p>","PeriodicalId":94136,"journal":{"name":"Medical physics","volume":"53 4","pages":"e70397"},"PeriodicalIF":3.2,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13293573/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147597028","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Correction to \"Cross-scan fusion network: A registration-based framework for annotation-efficient 3D ultrasound segmentation in low back pain assessment\".","authors":"","doi":"10.1002/mp.70413","DOIUrl":"10.1002/mp.70413","url":null,"abstract":"","PeriodicalId":94136,"journal":{"name":"Medical physics","volume":"53 4","pages":"e70413"},"PeriodicalIF":3.2,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147616814","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Support vector machine-based MRI radiomics predict response to neoadjuvant therapy and progression-free-survival of Colorectal Liver Metastases patients.","authors":"Zhuo-Fu Li, Jia Guo, Chao Sun, Song Tian, Zi-Long Ma, Zhao-Xiang Ye","doi":"10.1002/mp.70445","DOIUrl":"10.1002/mp.70445","url":null,"abstract":"<p><strong>Background: </strong>The efficacy of neoadjuvant therapy (NAT) and surgical prognosis stratification in patients with colorectal cancer liver metastasis (CRLM) remain unclear.</p><p><strong>Purpose: </strong>This study aims to develop and validate two radiomics models using baseline and delta radiomics features to predict the response to NAT and prognosis in CRLM.</p><p><strong>Methods: </strong>Baseline and Delta MRI radiomics features were extracted from 116 CRLM patients who underwent NAT combined with hepatectomy in the training set. Radiomics and clinical features were selected using Boruta algorithm to construct predictive models. In the external test set, the predictive performance of both models was evaluated using the area under the curve (AUC), decision curve analysis (DCA), calibration curves, and Brier score. Additionally, the delta model was compared with the clinical risk score (CRS).</p><p><strong>Results: </strong>The two models contain 6 and 4 variables, respectively, for predicting treatment response and progression-free survival (PFS). Both the response model and delta model demonstrated comparable predictive performance in the external test set (AUC = 0.806 for both). Furthermore, the delta model demonstrated superior performance to CRS in predicting PFS (AUC: 0.806 vs. 0.623).</p><p><strong>Conclusions: </strong>Radiomics models based on baseline and delta MRI effectively predicted treatment response and postoperative PFS in CRLM patients, with the delta model showing superior accuracy for PFS prediction compared to CRS.</p>","PeriodicalId":94136,"journal":{"name":"Medical physics","volume":"53 4","pages":"e70445"},"PeriodicalIF":3.2,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147694280","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Masked pre-training and pseudo-vessel enhancement-based semi-supervised cerebral vascular segmentation.","authors":"Shuai Wang, Hao Wang, Ye Tang, Jixian Lin, Jinhua Yu, Guoqing Wu","doi":"10.1002/mp.70440","DOIUrl":"10.1002/mp.70440","url":null,"abstract":"<p><strong>Background: </strong>Accurate segmentation of cerebral vessels in computed tomography angiography (CTA) and computed tomography perfusion (CTP) images is essential for diagnosing cerebrovascular diseases. However, due to the scarcity of annotated data and the complexity of small and branching vessels, fully supervised deep learning methods face limitations in clinical scenarios.</p><p><strong>Purpose: </strong>This study aims to develop a semi-supervised learning framework that can achieve high-accuracy cerebrovascular segmentation using only limited labeled data, while improving robustness to and enhancing small vessel continuity.</p><p><strong>Methods: </strong>We propose a novel semi-supervised segmentation framework integrating three core components: (1) a dual-scale masked pre-training strategy, which jointly reconstructs masked vessel regions and performs segmentation to enhance vascular continuity; (2) pseudo-vessel augmentation, which simulates vessel-like artifacts to improve discrimination between true vessels and false positives; and (3) multi-level consistency losses, which enforce output consistency across different enhancement and model predictions to enhance learning under low supervision. The model was evaluated on 948 CTA and CTP scans using five annotation ratios (5%, 10%, 20%, 50%, and 100%).</p><p><strong>Results: </strong>With only 5% of labeled data, the proposed method achieved 98.7% of the performance of a fully supervised model. Under full supervision, it reached Dice scores of 0.8379 on CTP and 0.9177 on CTA, outperforming the second-best method by 1.12% and 0.87%, respectively.</p><p><strong>Conclusions: </strong>The proposed semi-supervised framework enables accurate cerebrovascular segmentation with minimal labeled data. It effectively enhances small vessel continuity, reduces over-segmentation from noise, and demonstrates strong robustness and generalizability, making it a promising solution for real-world clinical applications.</p>","PeriodicalId":94136,"journal":{"name":"Medical physics","volume":"53 4","pages":"e70440"},"PeriodicalIF":3.2,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147694277","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Refining feature representation for accurate fundus lesion segmentation.","authors":"Hao Sun, Enting Gao, Yongcheng Li, Dehui Xiang, Fan Lu, Yi Zhou, Weifang Zhu, Fei Shi, Baoqing Nie, Xinjian Chen, Lei Zhang, Jing Cai, Duo Peng, Tao Peng","doi":"10.1002/mp.70441","DOIUrl":"10.1002/mp.70441","url":null,"abstract":"<p><strong>Background: </strong>Accurate segmentation of retinal lesions is essential for early detection of age-related macular degeneration (AMD), particularly its key indicators, choroidal neovascularization (CNV) and choroidal non-perfusion (CNP). However, the highly variable shapes and appearances of lesions pose substantial challenges for automated segmentation.</p><p><strong>Purpose: </strong>To tackle these challenges, we propose a deep-learning model, the Retinal Feature Enhancement Network (RFENet), designed to improve the accuracy and robustness of retinal lesion segmentation under challenging imaging conditions.</p><p><strong>Methods: </strong>RFENet builds upon the UNeXt backbone and introduces two modules tailored for retinal lesion segmentation: an Adaptive Feature Refinement Unit (AFRU), which selectively emphasizes informative features, and an Optimized Channel-Wise Convolution Unit (OCCU), which captures fine structural details in irregular lesions. Two expert-annotated datasets were used: 1070 OCT B-scans from 83 CNV patients and 184 FFA images from 107 CNP patients. Images were split at the patient level into training (70%), validation (10%), and test (20%) sets. Performance was compared against state-of-the-art segmentation models, including UNet++, Swin-UNet, SelfReg-UNet, DAEFormer, and Mamba-UNet. Evaluation metrics included Dice coefficient and Intersection over Union (IoU). Statistical significance was assessed using paired two-tailed t-tests ( <math> <semantics><mrow><mi>α</mi> <mo>=</mo> <mn>0.05</mn></mrow> <annotation>$alpha = 0.05$</annotation></semantics> </math> ), and effect sizes were reported with Cohen's <math><semantics><mi>d</mi> <annotation>$d$</annotation></semantics> </math> .</p><p><strong>Results: </strong>On the CNV dataset, RFENet achieved a Dice of 82.50% and an IoU of 71.66%, with clear improvements over competing models. On the CNP dataset, RFENet achieved a Dice of 74.43% and an IoU of 60.80%, slightly surpassing the best benchmark. Most pairwise comparisons were statistically significant, including CNV compared with Swin-UNet and SelfReg-UNet (p <math><semantics><mo><</mo> <annotation>$<$</annotation></semantics> </math> 0.001) and CNP compared with DAEFormer (p <math><semantics><mo>=</mo> <annotation>$=$</annotation></semantics> </math> 0.035). Statistical analyses, including effect size evaluation, further confirmed the robustness of these improvements, with the most notable gains observed in the CNV dataset.</p><p><strong>Conclusions: </strong>RFENet demonstrated consistent improvements over strong benchmarks on both CNV and CNP tasks, with statistical evidence supporting the reliability of these gains. These results indicate that RFENet provides a reliable technical advance for automated segmentation of CNV and CNP lesions associated with AMD. To facilitate reproducibility and further research, the source code is publicly available at https://github.com/HaoSun223/RFENet.</p>","PeriodicalId":94136,"journal":{"name":"Medical physics","volume":"53 4","pages":"e70441"},"PeriodicalIF":3.2,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147694291","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Points of interest linear attention network for real-time non-rigid liver volume to surface registration.","authors":"Zeming Chen, Beiji Zou, Xiaoyan Kui, Yangyang Shi, Ding Lv, Liming Chen","doi":"10.1002/mp.17108","DOIUrl":"https://doi.org/10.1002/mp.17108","url":null,"abstract":"<p><strong>Background: </strong>In laparoscopic liver surgery, accurately predicting the displacement of key intrahepatic anatomical structures is crucial for informing the doctor's intraoperative decision-making. However, due to the constrained surgical perspective, only a partial surface of the liver is typically visible. Consequently, the utilization of non-rigid volume to surface registration methods becomes essential. But traditional registration methods lack the necessary accuracy and cannot meet real-time requirements.</p><p><strong>Purpose: </strong>To achieve high-precision liver registration with only partial surface information and estimate the displacement of internal liver tissues in real-time.</p><p><strong>Methods: </strong>We propose a novel neural network architecture tailored for real-time non-rigid liver volume to surface registration. The network utilizes a voxel-based method, integrating sparse convolution with the newly proposed points of interest (POI) linear attention module. POI linear attention module specifically calculates attention on the previously extracted POI. Additionally, we identified the most suitable normalization method RMSINorm.</p><p><strong>Results: </strong>We evaluated our proposed network and other networks on a dataset generated from real liver models and two real datasets. Our method achieves an average error of 4.23 mm and a mean frame rate of 65.4 fps in the generation dataset. It also achieves an average error of 8.29 mm in the human breathing motion dataset.</p><p><strong>Conclusions: </strong>Our network outperforms CNN-based networks and other attention networks in terms of accuracy and inference speed.</p>","PeriodicalId":94136,"journal":{"name":"Medical physics","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140961267","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Fast four-dimensional cone-beam computed tomography reconstruction using deformable convolutional networks.","authors":"Zhuoran Jiang,&nbsp;Yushi Chang,&nbsp;Zeyu Zhang,&nbsp;Fang-Fang Yin,&nbsp;Lei Ren","doi":"10.1002/mp.15806","DOIUrl":"https://doi.org/10.1002/mp.15806","url":null,"abstract":"<p><strong>Background: </strong>Although four-dimensional cone-beam computed tomography (4D-CBCT) is valuable to provide onboard image guidance for radiotherapy of moving targets, it requires a long acquisition time to achieve sufficient image quality for target localization. To improve the utility, it is highly desirable to reduce the 4D-CBCT scanning time while maintaining high-quality images. Current motion-compensated methods are limited by slow speed and compensation errors due to the severe intraphase undersampling.</p><p><strong>Purpose: </strong>In this work, we aim to propose an alternative feature-compensated method to realize the fast 4D-CBCT with high-quality images.</p><p><strong>Methods: </strong>We proposed a feature-compensated deformable convolutional network (FeaCo-DCN) to perform interphase compensation in the latent feature space, which has not been explored by previous studies. In FeaCo-DCN, encoding networks extract features from each phase, and then, features of other phases are deformed to those of the target phase via deformable convolutional networks. Finally, a decoding network combines and decodes features from all phases to yield high-quality images of the target phase. The proposed FeaCo-DCN was evaluated using lung cancer patient data.</p><p><strong>Results: </strong>(1) FeaCo-DCN generated high-quality images with accurate and clear structures for a fast 4D-CBCT scan; (2) 4D-CBCT images reconstructed by FeaCo-DCN achieved 3D tumor localization accuracy within 2.5 mm; (3) image reconstruction is nearly real time; and (4) FeaCo-DCN achieved superior performance by all metrics compared to the top-ranked techniques in the AAPM SPARE Challenge.</p><p><strong>Conclusion: </strong>The proposed FeaCo-DCN is effective and efficient in reconstructing 4D-CBCT while reducing about 90% of the scanning time, which can be highly valuable for moving target localization in image-guided radiotherapy.</p>","PeriodicalId":94136,"journal":{"name":"Medical physics","volume":"49 10","pages":"6461-6476"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9588592/pdf/nihms-1817259.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41176513","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}