Medical physics最新文献

{"title":"FLASH radiotherapy: Paradigm shift or a passing fad?","authors":"Joao Seco, Joseph O. Deasy, Indra J. Das","doi":"10.1002/mp.17807","DOIUrl":"10.1002/mp.17807","url":null,"abstract":"","PeriodicalId":18384,"journal":{"name":"Medical physics","volume":"52 6","pages":"3504-3508"},"PeriodicalIF":3.2,"publicationDate":"2025-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143782263","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":"Electron beam reference dosimetry measurements obtained at multiple institutions using the Addendum to AAPM's TG-51 protocol","authors":"Bryan R. Muir, Thomas H. Davis, Sandeep Dhanesar, Yair Hillman, Viktor Iakovenko, Yu Lei, Tina Pike, Daniel W. Pinkham, Eric Vandervoort, Grace Gwe-Ya Kim","doi":"10.1002/mp.17802","DOIUrl":"10.1002/mp.17802","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>The TG-51 protocol describes methods for obtaining reference dosimetry measurements for external photon and electron beams. Since the publication of TG-51 in 1999, research on reference dosimetry has allowed revisiting the procedures and data recommended in the protocol. An Addendum to TG-51 for electron beam reference dosimetry was published in 2024, which revises the formalism and procedures and provides updated <span></span><math>\u0000 <semantics>\u0000 <msub>\u0000 <mi>k</mi>\u0000 <mi>Q</mi>\u0000 </msub>\u0000 <annotation>$k_{Q}$</annotation>\u0000 </semantics></math> data.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Purpose</h3>\u0000 \u0000 <p>To compare clinical reference dosimetry measurements in electron beams obtained using the original American Association of Physicists in Medicine's (AAPM) TG-51 protocol and its associated Addendum (AAPM WGTG51 report 385).</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>Measurements were performed in electron beams using the data and methods prescribed by TG-51 and its Addendum. Nine participants (eight clinics and one primary standards laboratory) provided data and measurements. Results were obtained with 18 linacs using 87 total beam energies (4–6 energies per linac) between 4–22 MeV, representing the range of electron beam energies used clinically. Various cylindrical (6 types) and parallel-plate (4 types) ionization chamber types were employed, representing most of the chambers commonly used in modern radiation therapy clinics. An analysis was performed to determine if differences arise from the new data recommended for beam quality conversion factors or from changes to the procedure.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>Results for dose to water per monitor unit obtained using the Addendum are up to 2.3% higher in low-energy beams and 1.3% higher in high-energy beams compared to results obtained using the original TG-51 protocol. These differences are consistent with what was predicted by the Addendum. Differences arise from both the changes to procedure (up to 0.7% from not requiring the <span></span><math>\u0000 <semantics>\u0000 <msubsup>\u0000 <mi>P</mi>\u0000 <mi>gr</mi>\u0000 <mi>Q</mi>\u0000 </msubsup>\u0000 <annotation>$P^Q_{rm gr}$</annotation>\u0000 </semantics></math> correction for cylindrical c","PeriodicalId":18384,"journal":{"name":"Medical physics","volume":"52 6","pages":"4971-4983"},"PeriodicalIF":3.2,"publicationDate":"2025-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/mp.17802","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143775121","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":"Megavoltage intrafraction monitoring and position uncertainty in gimbaled markerless dynamic tumor tracking treatment of lung tumors","authors":"Marco Serpa, Tobias Brandt, Simon K. B. Spohn, Andreas Rimner, Christoph Bert","doi":"10.1002/mp.17740","DOIUrl":"10.1002/mp.17740","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>The clinical realization of markerless dynamic tumor tracking (MLDTT) has prompted a new paradigm shift to intrafraction imaging-based quality assurance (QA). During MLDTT treatment using a gimbaled accelerator, the megavoltage (MV) imager serves as an independent system to leverage real-time intrafraction monitoring. Soft-tissue feature tracking has shown promise for tumor localization in confined MV projections, but studies demonstrating its application in clinical MLDTT treatments are scarse.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Purpose</h3>\u0000 \u0000 <p>To validate MV image-based dense soft-tissue feature tracking for intrafraction position monitoring of lung tumors during MLDTT stereotactic body radiotherapy (SBRT), and report on the resolved geometric uncertainty.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>Ten non-small cell lung cancer (NSCLC) patients underwent MLDTT-SBRT using a commercial gimbal-based system. During treatment, beam's-eye-view (BEV) projection images were captured at ∼3 frames s<sup>−1</sup> (fps) using the electronic portal imaging device (EPID). MV sequences were streamed to a research workstation and processed off-line using a purpose-built algorithm, the soft-tissue feature tracker (SoFT). Both the tumor and dynamic field aperture position were automatically extracted in the pan and tilt directions of the gimbaled x-ray head, corresponding to the in-plane lateral and longitudinal direction of the imager, and compared to ground truth manual tracking. The success, percentage of fields producing an output, and performance of MV tracking under the presence/absence of anatomy-related obstruction and multi-leaf collimator (MLC) occlusion were quantified, including three-dimensional conformal (3DCRT) and step-and-shoot intensity modulated radiotherapy (IMRT) deliveries. In addition, the geometric uncertainty of MLDTT treatment was estimated as the difference between field aperture and target center position in the BEV. The standard deviation of systematic (<i>Σ</i>) and random (<i>σ</i>) errors were determined.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>MV tracking was successful for 89.7% of (unmodulated) 3DCRT fields, as well as 82.4% of (modulated) control points (CPs) and subfields (SFs) for IMRT and field-in-field 3DCRT deliveries. The MV tracking accuracy was dependent on the traversed anatomy, tumor visibility, and occlusion by the MLC. The mean MV tracking accuracy was 1.2 mm (pan) and 1.4 mm (tilt), and a resultant 2D accuracy of 1.8 mm. The MV tracking performance within 2 mm was observe","PeriodicalId":18384,"journal":{"name":"Medical physics","volume":"52 6","pages":"4657-4674"},"PeriodicalIF":3.2,"publicationDate":"2025-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/mp.17740","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143775137","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":"Small elongated MLC fields: Novel equivalent square field formula and output factors","authors":"Antonella Fogliata, Antonella Stravato, Marco Pelizzoli, Francesco La Fauci, Pasqualina Gallo, Andrea Bresolin, Luca Cozzi, Giacomo Reggiori","doi":"10.1002/mp.17806","DOIUrl":"10.1002/mp.17806","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Purpose</h3>\u0000 \u0000 <p>This study evaluates different approaches for estimating the equivalent square field size (ESF) to derive the Output Correction Factors (OCF) according to the IAEA TRS-483 protocol, for small fields, focusing on rectangular fields generated by MLCs. A novel formula is proposed for estimating the ESF to be used alongside the TRS-483 formalism for Field Output Factor (FOF) determination.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Method</h3>\u0000 \u0000 <p>FOF for fields from 0.5 to 4 cm side shaped with MLC (jaws fixed to 4.4 × 4.4 cm<sup>2</sup>) were measured using two Varian TrueBeam (with Millennium and HD-MLC), at isocenter, 10 cm depth, with 6 and 10 MV beam energies, both with and without flattening filter, with microDiamond, DiodeE, and PinPoint3D detectors.</p>\u0000 \u0000 <p>Measured ratios were corrected using the OCF from the TRS-483 Tables to determine the FOF. The field size for each setting was determined as the FWHM of the scanning profiles acquired with the microDiamond detector. The ESF was determined using three methods: the Equivalent Area method (according to TRS-483), the Sterling Formula, and a new method according to the following formula:</p>\u0000 \u0000 <p><span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mi>E</mi>\u0000 <mi>q</mi>\u0000 <mi>S</mi>\u0000 <mi>q</mi>\u0000 <mi>F</mi>\u0000 <mi>S</mi>\u0000 <mo>=</mo>\u0000 <mrow>\u0000 <mo>[</mo>\u0000 <mrow>\u0000 <mn>2</mn>\u0000 <mo>·</mo>\u0000 <mi>m</mi>\u0000 <mi>i</mi>\u0000 <mi>n</mi>\u0000 <msup>\u0000 <mrow>\u0000 <mo>(</mo>\u0000 <mrow>\u0000 <mi>X</mi>\u0000 <mo>,</mo>\u0000 <mi>Y</mi>\u0000 </mrow>\u0000 <mo>)</mo>\u0000 </mrow>\u0000 <mi>a</mi>\u0000 </msup>\u0000 <mo>·</mo>\u0000 <mi>m</mi>\u0000 <mi>a</mi>\u0000 <mi>x</mi>\u0000 <msup>\u0000 <mrow>\u0000 <","PeriodicalId":18384,"journal":{"name":"Medical physics","volume":"52 6","pages":"5032-5038"},"PeriodicalIF":3.2,"publicationDate":"2025-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/mp.17806","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143782221","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":"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":"10.1002/mp.17780","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>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>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Purpose</h3>\u0000 \u0000 <p>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>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>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 (<i>n</i> = 78) and the validation group (<i>n</i> = 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>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>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, <i>p</i>> 0.05, in both the training and validation groups).</p>\u0000 ","PeriodicalId":18384,"journal":{"name":"Medical physics","volume":"52 6","pages":"3697-3710"},"PeriodicalIF":3.2,"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":2,"RegionCategory":"医学","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":"10.1002/mp.17796","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>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.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Purpose</h3>\u0000 \u0000 <p>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.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>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.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>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","PeriodicalId":18384,"journal":{"name":"Medical physics","volume":"52 6","pages":"4910-4923"},"PeriodicalIF":3.2,"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":2,"RegionCategory":"医学","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":"10.1002/mp.17782","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>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.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Purpose</h3>\u0000 \u0000 <p>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.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>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.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>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 t","PeriodicalId":18384,"journal":{"name":"Medical physics","volume":"52 6","pages":"3541-3556"},"PeriodicalIF":3.2,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/mp.17782","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143766254","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":"A CNN–transformer fusion network for predicting high-grade patterns in stage IA invasive lung adenocarcinoma","authors":"Yali Tao,&nbsp;Rong Sun,&nbsp;Jian Li,&nbsp;Wenhui Wu,&nbsp;Yuanzhong Xie,&nbsp;Xiaodan Ye,&nbsp;Xiujuan Li,&nbsp;Shengdong Nie","doi":"10.1002/mp.17781","DOIUrl":"10.1002/mp.17781","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>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>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Purpose</h3>\u0000 \u0000 <p>To develop a CNN–transformer fusion network based on radiomics and clinical information for predicting the HGPs of LUAD.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>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>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>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>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusions</h3>\u0000 \u0000 <p>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>\u0000 </section>\u0000 </div>","PeriodicalId":18384,"journal":{"name":"Medical physics","volume":"52 6","pages":"4557-4566"},"PeriodicalIF":3.2,"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":2,"RegionCategory":"医学","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,&nbsp;Marc-André Renaud,&nbsp;Monica Serban,&nbsp;Jan Seuntjens","doi":"10.1002/mp.17771","DOIUrl":"10.1002/mp.17771","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>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>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Purpose</h3>\u0000 \u0000 <p>This study provides the first assessment of the impact of range uncertainties on MBRT plans.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>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>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>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>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusion</h3>\u0000 \u0000 <p>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>\u0000 </section>\u0000 </div>","PeriodicalId":18384,"journal":{"name":"Medical physics","volume":"52 6","pages":"4785-4792"},"PeriodicalIF":3.2,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/mp.17771","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143756857","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":"A novel skeletal muscle quantitative method and deep learning-based sarcopenia diagnosis for cervical cancer patients treated with radiotherapy","authors":"Zhe Wu,&nbsp;Lihua Deng,&nbsp;Wanyang Wu,&nbsp;Bin Zeng,&nbsp;Cheng Xu,&nbsp;Li Liu,&nbsp;Mujun Liu,&nbsp;Yi Wu","doi":"10.1002/mp.17791","DOIUrl":"10.1002/mp.17791","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>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>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Purpose</h3>\u0000 \u0000 <p>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>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>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>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>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 <i>R</i>² 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>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusion</h3>\u0000 \u0000 <p>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>\u0000 </section>\u0000 </div>","PeriodicalId":18384,"journal":{"name":"Medical physics","volume":"52 5","pages":"2887-2897"},"PeriodicalIF":3.2,"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":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}