Medical physics最新文献

{"title":"Predictive models of epidermal growth factor receptor mutation in lung adenocarcinoma using PET/CT-based radiomics features.","authors":"Zhikang Deng, Di Jin, Pei Huang, Changchun Wang, Yaohong Deng, Rong Xu, Bing Fan","doi":"10.1002/mp.17780","DOIUrl":"https://doi.org/10.1002/mp.17780","url":null,"abstract":"<p><strong>Background: </strong>Lung adenocarcinoma (LAC) comprises a substantial subset of non-small cell lung cancer (NSCLC) diagnoses, where epidermal growth factor receptor (EGFR) mutations play a pivotal role as indicators for therapeutic intervention with targeted agents. The emerging field of radiomics, which involves the extraction of numerous quantitative attributes from medical imaging, when coupled with positron emission tomography/ computed tomography (PET/CT) technology, has demonstrated promise in the prognostication of EGFR mutation status. The objective of this investigation is to construct and validate predictive models for EGFR mutations in LAC by leveraging PET/CT-derived radiomics features, thereby refining diagnostic precision and facilitating tailored treatment strategies.</p><p><strong>Purpose: </strong>The aim of this study was to develop a non-invasive radiomics model based on PET/CT with excellent performance for predicting the EGFR mutation status in LAC. Thus, it can provide the basis for the individualized treatment decision of patients.</p><p><strong>Methods: </strong>Positron emission tomography (PET), computed tomography (CT), clinical and pathological data of 112 patients with LAC admitted to our hospital from January 2019 to June 2023 were retrospectively analyzed. This research cohort encompassed 54 LAC patients with EGFR wild type and 58 LAC patients with EGFR mutated type. The participants were randomly assigned to the training group (n = 78) and the validation group (n = 34) in a 7:3 ratio. A sum of 3562 radiomics attributes were derived from PET/CT scans. The minimal absolute shrinkage and selection operator method was employed to identify 13 notable features. Based on these characteristics, support vector machine (SVM), gradient boosting decision tree (GBDT), random forest (RF) and extreme gradient boosting (XGBOOST) were constructed. The forecasting effectiveness of the model was assessed using the area under the receiver operating characteristic (ROC) Curve, the DeLong test, and decision curve analysis (DCA).</p><p><strong>Results: </strong>SVM performance in PET/CT radiomics model was higher than that of other machine learning models (training group areas under the curve [AUC] of 0.916 and validation group AUC of 0.945, respectively). The integration of radiomics and clinical data did not yield a superior predictive performance compared to the radiomics model alone in terms of estimating EGFR mutation status (AUC: 0.916 vs. 0.921, 0.945 vs. 0.955, p> 0.05, in both the training and validation groups).</p><p><strong>Conclusions: </strong>The SVM model has emerged as a commendable non-invasive technique, showing high precision and dependability in forecasting EGFR mutation statuses in individuals with LAC. The radiomics model derived from PET/CT scans holds promise as a prognostic indicator of EGFR mutations in LAC, offering a valuable tool that could refine personalized therapeutic strategies and ultimatel","PeriodicalId":94136,"journal":{"name":"Medical physics","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143756866","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 novel algorithm for automated analysis of coronary CTA-derived FFR in identifying ischemia-specific CAD: A multicenter study.","authors":"Hongqin Liang, Feng Wen, Li Kong, Yue Li, Feihua Jing, Zhiguo Sun, Jucai Zhang, Haipeng Zhang, Shan Meng, Jian Wang","doi":"10.1002/mp.17803","DOIUrl":"https://doi.org/10.1002/mp.17803","url":null,"abstract":"<p><strong>Background: </strong>Coronary artery fractional flow reserve derived from coronary computed tomography angiography (CTA) is increasingly favored due to its non-invasive nature.</p><p><strong>Purpose: </strong>We aim to validate the ability of a novel on-site analysis model for computed tomography derived fractional flow reserve (CT FFR) using deep learning and level set algorithms to identify lesion-specific ischemic coronary artery disease (CAD).</p><p><strong>Methods: </strong>A retrospective analysis was conducted on 198 vessels from 171 patients from four medical centers who underwent CTA and invasive fractional flow reserve (FFR) examinations. Using invasive FFR and invasive coronary angiography (ICA) as reference standards, a new model based on deep learning and level set algorithm, as well as an artificial intelligence (AI) platform based on deep learning, were used to compare CT FFR values and stenosis rates.</p><p><strong>Results: </strong>Compared with the ai platform, the new model has a single-vessel accuracy of 85.9% [95% confidence interval (95% CI) 80-90), higher than the AI platform's 66.7% (95% CI: 59.6-73.1). The sensitivity is 82.8% (95% CI: 72.8-89.7), specificity is 88.3% (95% CI: 80.5-93.4), and the area under the curve (AUC) is 0.9 (95% CI: 0.85-0.94). The stenosis rate measured by model was much higher than ICA (r = 0.84, p < 0.0001). Using the standard FFR threshold of 0.8, the new model accurately identified 24 vessels with FFR values between 0.75 and 0.8. The AI platform exhibits significant differences in accuracy within different stenosis ranges (p = 0.022).</p><p><strong>Conclusion: </strong>The novel CT FFR algorithm based on a combination of deep learning and level set algorithms to optimize coronary artery 3D reconstruction may have a potential value in fully automatic on-site analysis of specific coronary ischemia.</p>","PeriodicalId":94136,"journal":{"name":"Medical physics","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143766250","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":"Uncertainty quantification for CT dosimetry based on 10 281 subjects using automatic image segmentation and fast Monte Carlo calculations.","authors":"Zirui Ye, Bei Yao, Haoran Zheng, Li Tao, Ripeng Wang, Yankui Chang, Zhi Chen, Yingming Zhao, Wei Wei, Xie George Xu","doi":"10.1002/mp.17796","DOIUrl":"https://doi.org/10.1002/mp.17796","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Computed tomography (CT) scans are a major source of medical radiation exposure worldwide. In countries like China, the frequency of CT scans has grown rapidly, thus making available a large volume of organ dose information. With modern computational methods, we are now able to overcome challenges in automatic organ segmentation and rapid Monte Carlo (MC) dose calculations. We hypothesize that it is possible to process an extremely large number of patient-specific organ dose datasets in order to quantify and understand the range of CT dose uncertainties associated with inter-individual variability.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Purpose: &lt;/strong&gt;In this paper, we present a novel method that combines automatic image segmentation with GPU-accelerated MC simulations to reconstruct patient-specific organ doses for a large cohort of 10 281 individuals (6419 males and 3862 females) who underwent CT examinations at a Chinese hospital. Through data mining and comparison, we analyze organ dose distribution patterns to investigate possible uncertainty in CT dosimetry methods that rely on simplified phantoms population-averaged patient models.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;Our data-processing workflow involved three key steps. First, we collected and anonymized CT images and subjects' health metrics (age, sex, height, and weight) from the hospital's database. Second, we utilized a deep learning-based segmentation tool, DeepContour, to automatically delineate organs from the CT images, and then performed GPU-accelerated MC organ dose calculations using a validated GE scanner model and the ARCEHR-CT software. Finally, we conducted a comprehensive statistical analysis of doses for eight organs: lungs, heart, breasts, esophagus, stomach, liver, pancreas, and spleen.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;It took 16 days to process data for the entire cohorts-at a speed of 600 individual CT dose datasets per day-using a single NVIDIA RTX 3080 GPU card. The results show profound inter-individual variability in organ doses, even when only comparing subjects having similar body mass index (BMI) or water equivalent diameter (WED). Statistical analyses indicate that the data fitting-a method often used in analyzing the trend in CT dosimetry-can lead to relative errors exceeding as much as 50% for the data studied for this cohort. Statistical analyses also reveal quantitative correlations between organ doses and health metrics, including weight, BMI, WED, and size-specific dose estimate (SSDE), suggesting that these factors may still serve as surrogates for indirect dose estimation as long as the uncertainty is fully understood and tolerable. Interestingly, the CT scanner's tube current modulation reduces the average organ doses for the cohort as expected, but the individual organ dose variability remains similar to those from scans having a fixed tube current.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;Using newly available computational tools, this study has dem","PeriodicalId":94136,"journal":{"name":"Medical physics","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143756869","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":"Trade-off of different deep learning-based auto-segmentation approaches for treatment planning of pediatric craniospinal irradiation autocontouring of OARs for pediatric CSI.","authors":"Alana Thibodeau-Antonacci, Marija Popovic, Ozgur Ates, Chia-Ho Hua, James Schneider, Sonia Skamene, Carolyn Freeman, Shirin Abbasinejad Enger, James Man Git Tsui","doi":"10.1002/mp.17782","DOIUrl":"https://doi.org/10.1002/mp.17782","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;As auto-segmentation tools become integral to radiotherapy, more commercial products emerge. However, they may not always suit our needs. One notable example is the use of adult-trained commercial software for the contouring of organs at risk (OARs) of pediatric patients.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Purpose: &lt;/strong&gt;This study aimed to compare three auto-segmentation approaches in the context of pediatric craniospinal irradiation (CSI): commercial, out-of-the-box, and in-house.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;CT scans from 142 pediatric patients undergoing CSI were obtained from St. Jude Children's Research Hospital (training: 115; validation: 27). A test dataset comprising 16 CT scans was collected from the McGill University Health Centre. All images underwent manual delineation of 18 OARs. LimbusAI v1.7 served as the commercial product, while nnU-Net was trained for benchmarking. Additionally, a two-step in-house approach was pursued where smaller 3D CT scans containing the OAR of interest were first recovered and then used as input to train organ-specific models. Three variants of the U-Net architecture were explored: a basic U-Net, an attention U-Net, and a 2.5D U-Net. The dice similarity coefficient (DSC) assessed segmentation accuracy, and the DSC trend with age was investigated (Mann-Kendall test). A radiation oncologist determined the clinical acceptability of all contours using a five-point Likert scale.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;Differences in the contours between the validation and test datasets reflected the distinct institutional standards. The lungs and left kidney displayed an increasing age-related trend of the DSC values with LimbusAI on the validation and test datasets. LimbusAI contours of the esophagus were often truncated distally and mistaken for the trachea for younger patients, resulting in a DSC score of less than 0.5 on both datasets. Additionally, the kidneys frequently exhibited false negatives, leading to mean DSC values that were up to 0.11 lower on the validation set and 0.07 on the test set compared to the other models. Overall, nnU-Net achieved good performance for body organs but exhibited difficulty differentiating the laterality of head structures, resulting in a large variation of DSC values with the standard deviation reaching 0.35 for the lenses. All in-house models generally had similar DSC values when compared against each other and nnU-Net. Inference time on the test data was between 47-55 min on a Central Processing Unit (CPU) for the in-house models, while it was 1h 21m with a V100 Graphics Processing Unit (GPU) for nnU-Net.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;LimbusAI could not adapt well to pediatric anatomy for the esophagus and the kidneys. When commercial products do not suit the study population, the nnU-Net is a viable option but requires adjustments. In resource-constrained settings, the in-house model provides an alternative. Implementing an automated segmentation tool ","PeriodicalId":94136,"journal":{"name":"Medical physics","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143766254","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 CNN-transformer fusion network for predicting high-grade patterns in stage IA invasive lung adenocarcinoma.","authors":"Yali Tao, Rong Sun, Jian Li, Wenhui Wu, Yuanzhong Xie, Xiaodan Ye, Xiujuan Li, Shengdong Nie","doi":"10.1002/mp.17781","DOIUrl":"https://doi.org/10.1002/mp.17781","url":null,"abstract":"<p><strong>Background: </strong>Invasive lung adenocarcinoma (LUAD) with the high-grade patterns (HGPs) has the potential for rapid metastasis and frequent recurrence. Therefore, accurately predicting the presence of high-grade components is crucial for doctors to develop personalized treatment plans and improve patient prognosis.</p><p><strong>Purpose: </strong>To develop a CNN-transformer fusion network based on radiomics and clinical information for predicting the HGPs of LUAD.</p><p><strong>Methods: </strong>A total of 288 lesions in 288 patients with pathologically confirmed invasive LUAD were enrolled. Firstly, radiomics features were extracted from the entire tumor region on lung computed tomography (CT) images and then fused with clinical patient characteristics. Secondly, a structure was proposed that concatenated a convolutional neural network (CNN) and Transformer encoding blocks to mine and extract more comprehensive information. Finally, a classification prediction was performed through fully connected layers.</p><p><strong>Results: </strong>Accuracy, sensitivity, specificity, precision, and area under the receiver operating characteristic (ROC) curve (AUC) were utilized for evaluation of the model's classification prediction performance. Delong's test was used to compare the AUCs of different models for significance. The proposed model was effective with an accuracy of 0.86, sensitivity of 0.67, specificity of 0.94, precision of 0.74, and AUC of 0.91.</p><p><strong>Conclusions: </strong>The CNN-transformer fusion network, based on radiomics and clinical information, demonstrates good performance in predicting the presence of HGPs and can be employed to assist in the development of personalized treatment plans for patients with invasive LUAD.</p>","PeriodicalId":94136,"journal":{"name":"Medical physics","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143756815","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":"Impact of range uncertainties for intensity-modulated mixed electron-photon radiation therapy.","authors":"Veng Jean Heng, Marc-André Renaud, Monica Serban, Jan Seuntjens","doi":"10.1002/mp.17771","DOIUrl":"https://doi.org/10.1002/mp.17771","url":null,"abstract":"<p><strong>Background: </strong>In the context of mixed electron-photon radiation therapy (MBRT), while the necessity of robust optimization to setup uncertainties is well-established, range uncertainties have yet to be investigated.</p><p><strong>Purpose: </strong>This study provides the first assessment of the impact of range uncertainties on MBRT plans.</p><p><strong>Methods: </strong>The percent depth dose of 2 electron beams (6 MeV and 20 MeV) and 1 photon beam (6 MV) are calculated by Monte Carlo using EGSnrc in slab phantoms. Range uncertainties are simulated by generating two copies of the phantom with each voxel's mass density upscaled or downscaled by 3.5%. Two clinical plans for a leg sarcoma case and a post-mastectomy breast case were replanned with MBRT with 2 optimization methods: once without robust optimization and once with robust to both setup and range uncertainties.</p><p><strong>Results: </strong>Dose discrepancies between the percent depth doses of density-scaled phantoms and the nominal phantom were found to be much larger for electron beams than photons with maximum differences of 6.9% (6 MeV) and 5.5% (20 MeV) versus 1.6% (6 MV) of the maximum dose. In both clinical cases, the region of largest dose discrepancy between the range and nominal scenarios was found to be along the electron's beam path, starting immediately downstream from the target and within a few cm. Even without robust optimization, dose-volume histograms (DVHs) of all relevant structures were not meaningfully degraded under range scenarios. In the breast plan, the ipsilateral lung's V20Gy increased by 1.9% under the worst range scenario. No substantial change in the DVHs of range scenarios were observed between the robustly and non-robustly optimized plan.</p><p><strong>Conclusion: </strong>In the two investigated cases, robustness to range uncertainties was not improved in robustly optimized versus non-robustly optimized plans. A larger study comprising more patients and treatment sites remains to be performed to adequately assess the necessity of robust optimization of MBRT plans to range uncertainties.</p>","PeriodicalId":94136,"journal":{"name":"Medical physics","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143756857","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 novel skeletal muscle quantitative method and deep learning-based sarcopenia diagnosis for cervical cancer patients treated with radiotherapy.","authors":"Zhe Wu, Lihua Deng, Wanyang Wu, Bin Zeng, Cheng Xu, Li Liu, Mujun Liu, Yi Wu","doi":"10.1002/mp.17791","DOIUrl":"https://doi.org/10.1002/mp.17791","url":null,"abstract":"<p><strong>Background: </strong>Sarcopenia is associated with decreased survival in cervical cancer patients treated with radiotherapy. Cone-beam computed tomography (CBCT) was widely used in image-guided radiotherapy. Sarcopenia is assessed by the skeletal muscle index (SMI) of third lumbar vertebra (L3). Whereas, L3 is usually not included on the cervical cancer radiotherapy CBCT images.</p><p><strong>Purpose: </strong>We aimed to explore the usefulness of CBCT for evaluating SMI and deep learning (DL)-based automatic segmentation and sarcopenia diagnosis for cervical cancer radiotherapy patients. We evaluated the SMI through fifth lumbar vertebra (L5).</p><p><strong>Methods: </strong>First, L3, L5 skeletal muscle area (SMA) were measured on CT and CBCT. The agreement of L5 skeletal muscle segmentation on CBCT was evaluated using the intraclass correlation coefficient (ICC). The relationships between L5-SMI_CT and L3-SMI_CT, L5-SMI_CBCT were established and assessed by Pearson analysis, Bland-Altman plots. Second, the consequent CBCT images of 248 cervical cancer radiotherapy patients with whole L5 were collected as DL-based automatic segmentation. An independent external validation dataset was used. We proposed an end-to-end anatomical distance-guided dual branch feature fusion network to segment L5 skeletal muscle on CBCT images. The automatic segmentation results were used for sarcopenia diagnosis evaluation.</p><p><strong>Results: </strong>The ICC values were greater than 0.95. The Pearson correlation coefficients (PCC) between L5-SMI_CT and L3-SMI_CT is 0.894. The PCC between L5-SMI_CT and L5-SMI_CBCT is 0.917. The L3-SMI_CT could be estimated through L5-SMI_CBCT by a linear regression equation. The adjusted R² values were greater than 0.7. The dice similarity coefficient of automatic segmentation is 87.09%. Our proposed DL network predicted sarcopenia with 84.38% accuracy and 85.71% F1-score. In external validation dataset, the sarcopenia diagnosis accuracy and F1-score are 80% and 82.61%, respectively.</p><p><strong>Conclusion: </strong>The SMI quantitative measurement using CBCT for cervical cancer patients is feasible. And the DL network has the potential to assist in the sarcopenia diagnosis using CBCT images.</p>","PeriodicalId":94136,"journal":{"name":"Medical physics","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143766251","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":"Imaging system for real-time, full-field pulse-by-pulse surface dosimetry of UHDR electron beams.","authors":"Megan Clark, Noah Daniel, Petr Bruza, Rongxiao Zhang, Lesley Jarvis, P Jack Hoopes, David Gladstone","doi":"10.1002/mp.17784","DOIUrl":"https://doi.org/10.1002/mp.17784","url":null,"abstract":"<p><strong>Background: </strong>The interest in ultra-high dose rate (UHDR) radiation therapy (RT) has grown due to its potential to spare normal tissue. However, clinical application is hindered by dosimetry challenges, as current irradiators and dosimeters are not designed for UHDR's high fluence. To ensure safe treatment and accurate dose delivery, real-time dose and dose rate quantification methods are essential.</p><p><strong>Purpose: </strong>We propose a novel scintillation imaging system for in vivo, pulse-by-pulse surface dose monitoring during delivery with a UHDR-capable Mobetron (IntraOp LLC Sunnyvale, CA, USA) system. This setup aims to measure entrance beam dose with high 2D spatial and temporal resolution.</p><p><strong>Methods: </strong>A modified collimating cone was 3D printed to house the imaging lens. The system featured a 90° sinuscope endoscope attached to a CMOS camera, was gated by the Mobetron's magnetron output signal, and captured light from a scintillator placed on the treatment surface. Three scintillator types were tested for their emission intensity and decay time. Dose and dose rate linearity studies were performed using various pulse lengths and repetition frequencies, respectively, and the imaging data were compared to an EDGE diode detector (SunNuclear Melbourne, FL, USA) and the Mobetron beam-current transformer (BCT) measurements.</p><p><strong>Results: </strong>Dose (R²= 0.993) and dose rate (within 2%) were linear, and the temporal beam structure agreed with the diode and BCT data, as evident by the fact that it was successfully gated such that it captured each pulse during testing. Dose per pulse measurements agreed with diode and BCT data within 2.0 ± 1.2 cGy (0.6% ± 0.3%) and 2.5 ± 1.0 cGy (1.1% ± 0.4%), respectively.</p><p><strong>Conclusions: </strong>The developed imaging system met the criteria for measuring entrance beam dose with high spatial and temporal resolution, offering a promising in vivo dosimetry method for UHDR RT in preclinical and clinical trials.</p>","PeriodicalId":94136,"journal":{"name":"Medical physics","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143766252","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":"Verification of dose and dose rate for quality assurance of spread-out-Bragg-peak proton FLASH radiotherapy using machine log files.","authors":"Seyyedeh Azar Oliaei Motlagh, François Vander Stappen, Michele M Kim, Rudi Labarbe, Lucian Hotoiu, Arnaud Pin, Rasmus Nilsson, Erik Traneus, Keith A Cengel, Wei Zou, Boon-Keng Kevin Teo, Lei Dong, Eric S Diffenderfer","doi":"10.1002/mp.17792","DOIUrl":"https://doi.org/10.1002/mp.17792","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Ultra-high dose rate radiotherapy elicits a biological effect (FLASH), which has been shown to reduce toxicity while maintaining tumor control in preclinical radiobiology experiments. FLASH depends on the dose rate, with evidence that higher dose rates drive increased normal tissue sparing. The pattern of dose delivery also has significance for conformal proton FLASH delivered via pencil beam scanning (PBS) given its unique spatio-temporal distribution of dose deposition.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Purpose: &lt;/strong&gt;In PBS, the machine-generated log file contains information on the spatio-temporal pattern of PBS delivery measured by the segmented ionization chambers in the treatment nozzle. The spot position and monitor unit (MU) obtained from log files have previously been used to reconstruct the treatment dose by Monte Carlo (MC) simulations. The incorporation of spot timing allows reconstruction of the 3D temporal dose distribution. The log-based dose and dose rate can have a role in quality assurance (QA) and FLASH treatment verification if the reconstruction can be shown to be accurate in spatial and temporal domains of dose deposition. Thus, the objective of this study is to validate the accuracy of dose rate reconstruction using input data from machine log files of PBS delivery. By analyzing the delivered spot timing, position, and MU extracted from the logs, we aim to evaluate the reliability and precision of the log data for dose and dose rate reconstruction.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;FLASH PBS spread-out Bragg peak (SOBP) treatment fields were delivered using a cyclotron accelerated proton beam. This method involves a patient and field-specific conformal energy modulator (CEM) to achieve a SOBP at the tumor site. Log files record spot positions and the delivered MU with timing information at 250 µs resolution. To validate timing information, a 9.9 mm diameter parallel plate ionization chamber was positioned at various locations within the SOBP. An electrometer sampling at 20 kHz recorded the time-resolved ionization current collected by the ionization chamber. These measurements were used to determine spot dose, dose rate, duration, and transition times. Disparities between the measured and logged spot map MU and timing were determined. Dose average and PBS dose rates were compared between the measurement and log-based MC simulations.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;There was a good agreement between the measured dwell time and transition time and the logged information across various detector positions. The median disparities for inter-spot dwell time range from -0.041  to 0.024 ms. Differences between logged and planned spot positions are minimal, measuring less than 1.08 mm in the x direction and 1.15 mm in the y direction, consistent with prior studies and the spatial resolution of the PBS nozzle ionization chamber. Delivered MU were within 1.9% of the planned MU. Measured dose and dose rates are consistent ","PeriodicalId":94136,"journal":{"name":"Medical physics","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143766257","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":"Impact of harmonization on predicting complications in head and neck cancer after radiotherapy using MRI radiomics and machine learning techniques.","authors":"Benyamin Khajetash, Ghasem Hajianfar, Amin Talebi, Seid Rabi Mahdavi, Beth Ghavidel, Farshid Arbabi Kalati, Seyed Hadi Molana, Yang Lei, Meysam Tavakoli","doi":"10.1002/mp.17793","DOIUrl":"https://doi.org/10.1002/mp.17793","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Variations in medical images specific to individual scanners restrict the use of radiomics in both clinical practice and research. To create reproducible and generalizable radiomics-based models for outcome prediction and assessment, data harmonization is essential.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Purpose: &lt;/strong&gt;This study aims to investigate the impact of harmonization in performance of machine learning-based radiomics model toward the prediction of radiotherapy-induced toxicity (early and late sticky saliva and xerostomia) in head and neck cancer (HNC) patients after radiation therapy using &lt;math&gt; &lt;semantics&gt;&lt;msub&gt;&lt;mi&gt;T&lt;/mi&gt; &lt;mn&gt;1&lt;/mn&gt;&lt;/msub&gt; &lt;annotation&gt;$T_1$&lt;/annotation&gt;&lt;/semantics&gt; &lt;/math&gt; and &lt;math&gt; &lt;semantics&gt;&lt;msub&gt;&lt;mi&gt;T&lt;/mi&gt; &lt;mn&gt;2&lt;/mn&gt;&lt;/msub&gt; &lt;annotation&gt;$T_2$&lt;/annotation&gt;&lt;/semantics&gt; &lt;/math&gt; -weighted magnetic resonance (MR) images.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;A total of 85 HNC patients who underwent radiotherapy was studied. Radiomic features were extracted from &lt;math&gt; &lt;semantics&gt;&lt;msub&gt;&lt;mi&gt;T&lt;/mi&gt; &lt;mn&gt;1&lt;/mn&gt;&lt;/msub&gt; &lt;annotation&gt;$T_1$&lt;/annotation&gt;&lt;/semantics&gt; &lt;/math&gt; and &lt;math&gt; &lt;semantics&gt;&lt;msub&gt;&lt;mi&gt;T&lt;/mi&gt; &lt;mn&gt;2&lt;/mn&gt;&lt;/msub&gt; &lt;annotation&gt;$T_2$&lt;/annotation&gt;&lt;/semantics&gt; &lt;/math&gt; -weighted MR images with standardized protocols. Data harmonization was performed using ComBat algorithm to reduce inter-center variability. Besides imaging features, both dosimetric and demographic features were extracted and used in our model. Recursive feature elimination was employed as feature selection method to identify the most important variables. Ten classification algorithms, including eXtreme Gradient Boosting (XGBoost), multilayer perceptron (MLP), support vector machines (SVM), random forest (RF), k-nearest neighbor (KNN), Naive Bayes (NB), logistic regression (LR), and decision tree (DT), boosted generalized linear model (GLMB), and stack learning (SL) were utilized and compared to develop predictive models. This evaluation comparisons were performed before and after harmonization to demonstrate its significance.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;Our results indicate that harmonization consistently enhances predictive performance across various complications and imaging modalities. In early and late sticky saliva prediction using &lt;math&gt; &lt;semantics&gt;&lt;msub&gt;&lt;mi&gt;T&lt;/mi&gt; &lt;mn&gt;1&lt;/mn&gt;&lt;/msub&gt; &lt;annotation&gt;$T_1$&lt;/annotation&gt;&lt;/semantics&gt; &lt;/math&gt; -weighted images, the SVM and RF models achieved an impressive area under the curve (AUC) of 0.88 &lt;math&gt;&lt;semantics&gt;&lt;mo&gt;±&lt;/mo&gt; &lt;annotation&gt;$pm$&lt;/annotation&gt;&lt;/semantics&gt; &lt;/math&gt; 0.09 and 0.97 &lt;math&gt;&lt;semantics&gt;&lt;mo&gt;±&lt;/mo&gt; &lt;annotation&gt;$pm$&lt;/annotation&gt;&lt;/semantics&gt; &lt;/math&gt; 0.05 with harmonization versus 0.42 &lt;math&gt;&lt;semantics&gt;&lt;mo&gt;±&lt;/mo&gt; &lt;annotation&gt;$pm$&lt;/annotation&gt;&lt;/semantics&gt; &lt;/math&gt; 0.12 and 0.83 &lt;math&gt;&lt;semantics&gt;&lt;mo&gt;±&lt;/mo&gt; &lt;annotation&gt;$pm$&lt;/annotation&gt;&lt;/semantics&gt; &lt;/math&gt; 0.08 without harmonization, respectively. Similarly, in early and late xerostomia prediction, the model attained an AUC of 0.79 &lt;math&gt;&lt;semantic","PeriodicalId":94136,"journal":{"name":"Medical physics","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143756855","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}