Physical and Engineering Sciences in Medicine最新文献

筛选
英文 中文
Machine learning prediction of electronic-portal-imaging-device-based in vivo dosimetry results using plan complexity metrics, machine output and gamma passing rate: a feasibility study. 使用计划复杂性度量、机器输出和伽马通过率的基于电子门户成像设备的体内剂量测定结果的机器学习预测:可行性研究。
IF 2.4 4区 医学
Physical and Engineering Sciences in Medicine Pub Date : 2026-11-10 DOI: 10.1007/s13246-026-01834-z
Nipon Saiyo, Hironori Kojima, Kimiya Noto, Naoki Isomura, Haruna Yokoyama, Kosuke Tsukamoto, Yuto Segawa, Shotaro Yamaguchi, Shota Ishihara, Akihiro Takemura
{"title":"Machine learning prediction of electronic-portal-imaging-device-based in vivo dosimetry results using plan complexity metrics, machine output and gamma passing rate: a feasibility study.","authors":"Nipon Saiyo, Hironori Kojima, Kimiya Noto, Naoki Isomura, Haruna Yokoyama, Kosuke Tsukamoto, Yuto Segawa, Shotaro Yamaguchi, Shota Ishihara, Akihiro Takemura","doi":"10.1007/s13246-026-01834-z","DOIUrl":"https://doi.org/10.1007/s13246-026-01834-z","url":null,"abstract":"<p><p>In vivo dosimetry (IVD) is essential for verifying treatment accuracy and current methods only identify discrepancies after delivery. Predicting IVD results beforehand offers proactive risk anticipation. This study aimed to develop a machine learning (ML) model for predicting electronic-portal-imaging-device (EPID)-based IVD results. Input predictors included volumetric modulated arc therapy (VMAT) plan complexity metrics, gamma passing rate (GPRs) from EPID-based patient-specific quality assurance (PSQA), and daily machine output quality assurance (QA) data for each treatment fraction. Seventeen VMAT plan complexity metrics were calculated from DICOM-RT files, and GPRs were obtained from forty head and neck cancer patients. The IVD results, a set of point-dose deviations between reconstructed and planned dose distributions, served as the input response. An ensemble-bagged-tree regression model was used to develop the prediction model. Model performance was evaluated using root mean square error (RMSE), mean absolute error (MAE), and R-squared. Spearman's rank correlation assessed relationships between predictors and responses. In the test set, the model achieved RMSE of 2.9%, MAE of 2.1%, and R-squared of 0.80. Correlations between EPID-based IVD results and plan complexity, GPRs of PSQA, and machine output QA metrics were weak, while the ML model showed strong predictive accuracy, closely matching predicted and measured IVD results. This study demonstrates the feasibility of combining ML with EPID-based IVD point-dose data. If further developed, this approach could provide fraction-by-fraction IVD estimates in clinics without dedicated IVD software and enable early detection of potential errors, enhancing IVD process.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2026-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149388321","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Hybrid metaheuristic optimization technique for cardiac disease prediction using cardiac multimodal affecting parameters. 基于心脏多模态影响参数的心脏病预测混合元启发式优化技术。
IF 2.4 4区 医学
Physical and Engineering Sciences in Medicine Pub Date : 2026-11-10 DOI: 10.1007/s13246-026-01830-3
Kunvar Kant Patel, Basant Kumar
{"title":"Hybrid metaheuristic optimization technique for cardiac disease prediction using cardiac multimodal affecting parameters.","authors":"Kunvar Kant Patel, Basant Kumar","doi":"10.1007/s13246-026-01830-3","DOIUrl":"https://doi.org/10.1007/s13246-026-01830-3","url":null,"abstract":"<p><p>This paper presents a new technique for improving the machine learning (ML)-based cardiac disease classification model by optimizing the weights of cardiac-affecting parameters (CAPs), such as systolic and diastolic blood pressure, cholesterol, BMI, SpO<sub>2</sub>, and other clinical and physiological parameters. Now, it is well established that accurate and robust prediction of cardiac diseases requires analysis of electrocardiograms along with other cardiac-affecting parameters. A systematic study is still required to determine the weightage of these parameters in the onset of cardiac disease. This paper introduces a scientific technique to determine and optimize CAPs weight; the results help develop a robust, accurate algorithm for early detection of cardiovascular disease. CAPs weight optimization is achieved using a hybrid metaheuristic (LSTM + PSO) technique. This technique significantly contributes to the development of an improved method for early detection of cardiac diseases. The improvement is achieved by determining the weights of CAPs and applying these weights for fine-tuning the ML-based CatBoost, XGBoost, TapNet, and SVM classification models. The study integrates the perspectives of 200 cardiologists on 13 CAPs. The variability in doctors' opinions creates a challenge in determining the best weights for each CAP, and it is resolved with the optimized CAPs technique. It is found that the optimized CatBoost classifier algorithm achieves the highest accuracy of 99.8% with a 0.02% FNR on the Kudem dataset. On the CardioHTDC dataset, the SVM classifier obtained a maximum accuracy of 96.3%. The suggested approach is efficient, adaptable, and may help cardiologists, as shown by the findings from two databases.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2026-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149388320","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Impact of extended field-of-view on image quality and stopping power ratio in proton therapy dose calculation. 扩大视场对质子治疗剂量计算中图像质量和停止功率比的影响。
IF 2.4 4区 医学
Physical and Engineering Sciences in Medicine Pub Date : 2026-11-02 DOI: 10.1007/s13246-026-01828-x
Mananchaya Vimolnoch, Sornjarod Oonsiri, Puntiwa Oonsiri, Nichakan Chatchumnan, Sakda Kingkaew
{"title":"Impact of extended field-of-view on image quality and stopping power ratio in proton therapy dose calculation.","authors":"Mananchaya Vimolnoch, Sornjarod Oonsiri, Puntiwa Oonsiri, Nichakan Chatchumnan, Sakda Kingkaew","doi":"10.1007/s13246-026-01828-x","DOIUrl":"https://doi.org/10.1007/s13246-026-01828-x","url":null,"abstract":"<p><p>CT simulators offer an extended field-of-view (eFOV) to include immobilization devices and anatomy beyond the scan FOV (sFOV). This study evaluated its impact on image quality, stopping power ratio (SPR), and proton dose calculations. CT images were reconstructed into the sFOV and three eFOVs. Image quality was assessed using the CATPHAN phantom. Hounsfield unit (HU)-to-SPR curves were generated using the stoichiometric method. HU and SPR variations were evaluated using homogeneous and heterogeneous phantoms extending beyond the sFOV. Proton dose calculations using 50-cm sFOV and 80-cm eFOV images were compared in breast and lung cases using dose differences and three-dimensional gamma analysis. Geometric distortion remained below 0.5 mm at the center but increased to 1.7 mm near the FOV edge. Spatial resolution, uniformity, and contrast were comparable across FOVs. HU-to-SPR calibration curves differed by ≤0.6%. Homogeneous phantom SPR differences were 1.4%, 0.1%, and 0.2% for lung-, bone-, and water-equivalent materials, respectively. Heterogeneous phantom SPR differences were within 1% for most materials and reached 2.4% for lung-equivalent material. Mean clinical target volume dose differences were 0.6% for breast and 0.8% for lung cases; organ-at-risk dose differences were within 2.0% and 3.2%, respectively. Gamma pass rates exceeded 99%, 98%, and 92% for 3%/2 mm, 2%/2 mm, and 1%/1 mm criteria, respectively.Extended FOV images were reliable for proton dose planning when the treatment area was centered in the scanning field.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2026-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149326219","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Clinical impact of enhanced leaf modelling on multi-metastatic intracranial SRT delivered on Halcyon: a modest but consistent dosimetric effect. 增强叶片模拟对多转移性颅内SRT的临床影响:适度但一致的剂量学效应。
IF 2.4 4区 医学
Physical and Engineering Sciences in Medicine Pub Date : 2026-10-30 DOI: 10.1007/s13246-026-01826-z
Mark Ashburner, Arun Gandhi, Omer Ali, Ben Scarlet
{"title":"Clinical impact of enhanced leaf modelling on multi-metastatic intracranial SRT delivered on Halcyon: a modest but consistent dosimetric effect.","authors":"Mark Ashburner, Arun Gandhi, Omer Ali, Ben Scarlet","doi":"10.1007/s13246-026-01826-z","DOIUrl":"https://doi.org/10.1007/s13246-026-01826-z","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Introduction: &lt;/strong&gt;Enhanced Leaf Modelling (ELM), introduced in Varian Eclipse v18, provides a refined representation of MLC transmission by explicitly modelling physical leaf geometry, interleaf leakage, and leaf-tip effects for Halcyon, replacing the traditional dosimetric leaf gap approximation. Unlike C-arm systems, Halcyon employs no collimator jaws, making out-of-field dose more exclusively dependent on MLC transmission characteristics and increasing the relative importance of accurate MLC modelling. Local commissioning supported the implementation of ELM on Halcyon and demonstrated improved agreement between calculated and measured dose distributions in the commissioning tests. These commissioning findings were separate form the present analysis, which characterises the dosimetric impact of ELM in clinically representative multi-metastatic stereotactic radiotherapy (MMSRT) plans rather than independently validating their physical accuracy.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;Ten MMSRT patients (2-6 lesions) were replanned using two calculation models: the standard Acuros XBv16 and v18 (with ELM). For each, two optimisation strategies were compared, manual and automatic normal tissue optimisation (NTO), to assess robustness across planning methods. The low-dose valley, defined as [Brain-PTVs], represented normal brain between targets. Dose-volume metrics were extracted across V50% to V2% of prescription dose to evaluate low-dose spread. Dose fall-off was quantified using concentric 1 mm rings extending 1-7 mm from the PTV surface, recording mean, median, and maximum doses within each ring. Clinically relevant spread was further evaluated using V12 Gy, V20 Gy, and V24 Gy metrics. Statistical analysis was done using appropriate parametric or non-parametric testing (p&lt;0.05).&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;Enhanced Leaf Modeling (ELM) primarily affected low- and intermediate-dose regions surrounding intracranial targets in MMSRT plans delivered on Halcyon. Statistically significant differences in normal brain volume were observed between ELM and the conventional MLC model (XB16), particularly beyond 3 mm from the PTV and at lower dose levels (V12-V24 Gy). ELM consistently reported higher low-dose volumes, with the largest effects observed for V20 Gy and V24 Gy within proximal rings, especially for manually optimised plans. Differences in extreme dose metrics were observed, with ELM associated with increased minimum dose and reduced maximum dose in the peri-PTV region, while mean dose remained largely unchanged. Despite statistical significance, all observed differences were small in magnitude and did not affect clinical acceptability.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusion: &lt;/strong&gt;Enhanced Leaf Modelling (ELM) introduces measurable but clinically small changes in dose distribution for MMSRT delivered on Halcyon treatment units, with effects confined predominantly to low-dose regions and steep dose gradients. These changes did not alter clinical","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2026-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149301264","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A swin transformer with cross-task attention and gating for cardiac murmur detection and grading. 一个具有交叉任务注意和门控的心脏杂音检测和分级的swin变压器。
IF 2.4 4区 医学
Physical and Engineering Sciences in Medicine Pub Date : 2026-10-29 DOI: 10.1007/s13246-026-01818-z
Aihui Han, Hong Tang, Miao Wang, Jinlong Long, Qianhui Zhao, Xiaoling Liang, Yan Chen
{"title":"A swin transformer with cross-task attention and gating for cardiac murmur detection and grading.","authors":"Aihui Han, Hong Tang, Miao Wang, Jinlong Long, Qianhui Zhao, Xiaoling Liang, Yan Chen","doi":"10.1007/s13246-026-01818-z","DOIUrl":"https://doi.org/10.1007/s13246-026-01818-z","url":null,"abstract":"<p><p>Cardiac murmur detection and severity grading are critical for early cardiovascular screening; however, existing studies often address these tasks separately and lack sufficient post-hoc explainability. This study aimed to develop a deep learning framework with post-hoc explainability for joint murmur detection and severity grading from phonocardiogram recordings. Heart sound recordings from the CirCor DigiScope dataset were preprocessed using Butterworth band-pass filtering, normalization, and sliding-window segmentation, and transformed into CWT-based time-frequency representations. An improved Swin Transformer, termed ST-CAG (Swin Transformer with Cross-Task Attention and Gating), was proposed for simultaneous murmur detection and three-class severity grading. The framework integrates a spatial attention module for enhancing murmur-related features, a Cross-Task Attention module for information exchange between tasks, and a Grade Gate mechanism for improving severity prediction consistency. Post-hoc explainability was investigated using spatial attention heatmap visualization. ST-CAG achieved accuracies of 98.99% and 95.00% with macro-averaged F1-scores of 94.28% and 94.07% for murmur detection and severity grading, respectively, on the independent test set. Ablation studies demonstrated the contribution of the proposed modules, and attention visualization highlighted discriminative time-frequency regions associated with murmur classification. ST-CAG provides an accurate framework with post-hoc explainability for joint cardiac murmur detection and severity grading. The proposed multitask design and visualization strategy enhance model explainability and demonstrate potential for intelligent auscultation and computer-aided cardiovascular screening.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2026-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149326204","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Optimising radiotherapy and immunotherapy timing: a mechanistic model of the tumour microenvironment. 优化放疗和免疫治疗时间:肿瘤微环境的机制模型。
IF 2.4 4区 医学
Physical and Engineering Sciences in Medicine Pub Date : 2026-10-27 DOI: 10.1007/s13246-026-01822-3
Allison M Ng, Rebecca A D'Alonzo, Synat Keam, Pejman Rowshanfarzad, Anna K Nowak, Suki Gill, Alistair M Cook, Martin A Ebert
{"title":"Optimising radiotherapy and immunotherapy timing: a mechanistic model of the tumour microenvironment.","authors":"Allison M Ng, Rebecca A D'Alonzo, Synat Keam, Pejman Rowshanfarzad, Anna K Nowak, Suki Gill, Alistair M Cook, Martin A Ebert","doi":"10.1007/s13246-026-01822-3","DOIUrl":"https://doi.org/10.1007/s13246-026-01822-3","url":null,"abstract":"<p><p>This study aimed to determine the optimal scheduling of radiotherapy (RT) and anti-PD-1/CTLA-4 immune checkpoint inhibitors (ICIs) in a murine model of mesothelioma. BALB/c mice inoculated with a syngeneic mesothelioma tumour on the flank were treated with combination RT and ICI, and tumour growth was measured. An extension of an existing mechanistic model of the tumour microenvironment was fitted to the data, estimating growth, clearing of RT-damaged tumour cells, release of antigens, and activation of T-cells. This model was further extended to investigate the effects of tumour hypoxia on treatment efficacy. Each treatment schedule was analysed to calculate the highest tumour control probability (TCP). Combining ICIs with RT increases the TCP, consistent with other pre- clinical studies. Anti-PD-1 was more effective than anti-CTLA-4 at enhancing tumour control in our model. However, administering anti-PD-1 alone was less effective compared to combined anti-CTLA-4 and anti-PD-1. The TCP was robust to changes in the interval between ICI treatment days and delaying anti-CTLA-4 treatment. However, TCP was sensitive to delays in RT treatment and increases in the interval between RT treatment days. This study supports the synergistic effect between RT and ICIs. Further validation of the model on an external dataset is required before the model can be used to inform optimal treatment scheduling for future human clinical trials.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2026-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149289267","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Fidelity-oriented pelvic CBCT-to-CT synthesis using an anatomical information-attention diffusion model. 基于解剖学信息-注意力扩散模型的骨盆ct - ct合成。
IF 2.4 4区 医学
Physical and Engineering Sciences in Medicine Pub Date : 2026-10-27 DOI: 10.1007/s13246-026-01823-2
Chaoyu Ma, Jingyang Ni, Huiping Cui, Juntian Shi, Kunyuan Xu
{"title":"Fidelity-oriented pelvic CBCT-to-CT synthesis using an anatomical information-attention diffusion model.","authors":"Chaoyu Ma, Jingyang Ni, Huiping Cui, Juntian Shi, Kunyuan Xu","doi":"10.1007/s13246-026-01823-2","DOIUrl":"https://doi.org/10.1007/s13246-026-01823-2","url":null,"abstract":"<p><p>Cone-beam computed tomography (CBCT) is widely used in image-guided radiotherapy and adaptive radiotherapy, but its direct quantitative use is limited by scatter artifacts, low soft-tissue contrast, and inaccurate Hounsfield unit (HU) values. Diffusion models provide stable image generation capabilities for CBCT-to-CT synthesis. However, in medical image synthesis tasks where patient-specific anatomical fidelity is more important than generation diversity, the stochastic sampling capability of diffusion models may conflict with task requirements. We propose a fidelity-oriented Anatomical Information-Attention Diffusion Model (AIADM) for pelvic CBCT-to-CT synthesis to generate synthetic CT (sCT) images. Unlike conventional diffusion models that primarily predict noise during reverse denoising, AIADM directly predicts the image state at the preceding diffusion time step, aiming to reduce unnecessary generation variation. A Fourier-based anatomical information fusion module integrates frequency-domain features of the current diffusion state with CBCT structural features, while a Vision Transformer attention module captures global pelvic structural dependencies. The diffusion process loss and anatomical information consistency loss constrain the intensity residuals of stepwise prediction and the target edge responses, respectively. Experiments on an internal pelvic dataset comprising 86 patients show that AIADM outperforms the GAN-based, VAE-based, and diffusion-based methods compared in this study across the four evaluated metrics. Using the registered reference pCT as the evaluation reference, AIADM achieves an MAE of 14.25 ± 1.05 HU, an RMSE of 26.42 ± 5.70 HU, a PSNR of 43.87 ± 1.89 dB, and an SSIM of 0.96 ± 0.01. Visual comparisons and HU profiles show that the generated results are closer to the reference pCT, with fewer visible streak artifacts in multiplanar and three-dimensional reconstruction views. AIADM introduces image-domain supervision and anatomical feature fusion into a conditional diffusion framework for pelvic CBCT-to-CT synthesis. The proposed framework reduces intensity errors relative to the registered pCT, increases image similarity, and improves the visual continuity of reconstruction views, providing a basis for subsequent image synthesis and dosimetric evaluation.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2026-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149289296","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Closed-form elasticity and elementary-effect sensitivity analysis of the universal survival curve model for stereotactic radiotherapy fractionation. 立体定向放疗分割通用生存曲线模型的闭合弹性及基本效应敏感性分析。
IF 2.4 4区 医学
Physical and Engineering Sciences in Medicine Pub Date : 2026-10-27 DOI: 10.1007/s13246-026-01827-y
Aryaveer Singh, Rajiv Kumar Singh
{"title":"Closed-form elasticity and elementary-effect sensitivity analysis of the universal survival curve model for stereotactic radiotherapy fractionation.","authors":"Aryaveer Singh, Rajiv Kumar Singh","doi":"10.1007/s13246-026-01827-y","DOIUrl":"https://doi.org/10.1007/s13246-026-01827-y","url":null,"abstract":"<p><strong>Purpose: </strong>The universal survival curve (USC) joins the linear-quadratic (LQ) description of the shoulder region to the log-linear multi-target asymptote at a transition dose, and is increasingly invoked to justify ablative fractionation. Which input actually controls predicted survival has not been established analytically. We derive closed-form elasticities, rank the inputs by two independent methods, and quantify the consequences for stereotactic schedules.</p><p><strong>Methods: </strong>Continuity of value and gradient at the transition dose fixes the quadratic coefficient and the transition dose in terms of the three cell-line parameters. Elasticities were derived in closed form, verified against central differences, and ranked independently by Morris elementary-effect screening over a fifteen per cent envelope. Biologically effective doses were compared for six clinical schedules and nine non-small-cell lung cancer cell lines.</p><p><strong>Results: </strong>Dose dominated, with mean absolute elasticity 7.89, followed by the mean inactivation dose 6.64, the quasi-threshold dose 1.15 and the radiosensitivity coefficient 0.104. Morris screening reproduced this ordering. The two agreed for conventional fractionation but diverged sharply above the transition dose, the LQ formulation overstating biologically effective dose by 42 per cent for 54 Gy in three fractions and by 97 per cent for a single 30 Gy fraction.</p><p><strong>Conclusion: </strong>Within the USC model and the in vitro data examined, predicted survival is governed by delivered dose and the characteristic dose rather than by the radiosensitivity coefficient, so parameter-estimation effort should target the terminal slope of the survival curve; the analysis ranks the inputs of each model but does not adjudicate between the models.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2026-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149289231","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A stacking-based ensemble learning approach for lung segmentation in multi-center chest X-ray images. 一种基于堆叠的集成学习方法用于多中心胸部x线图像的肺分割。
IF 2.4 4区 医学
Physical and Engineering Sciences in Medicine Pub Date : 2026-10-27 DOI: 10.1007/s13246-026-01817-0
Maedeh Sadat Khorasani, Farshid Babapour Mofrad
{"title":"A stacking-based ensemble learning approach for lung segmentation in multi-center chest X-ray images.","authors":"Maedeh Sadat Khorasani, Farshid Babapour Mofrad","doi":"10.1007/s13246-026-01817-0","DOIUrl":"https://doi.org/10.1007/s13246-026-01817-0","url":null,"abstract":"<p><p>Automatic segmentation of lung fields in chest X-ray (CXR) images is an essential part of the diagnostic process. However, the lungs' diverse shapes and irregular appearance caused by disease make this task challenging. Most previous studies have relied on individual networks, each with its own strengths and weaknesses. In this study, a stacking-based ensemble learning approach incorporating multiple individual networks was developed to leverage their complementary strengths and improve these challenges. To evaluate the generalizability and reproducibility of the results, three public datasets, namely Montgomery, Shenzhen, and JSRT, were utilized. The outputs of the three models, FAT-Net, UNet3+, and DeepLabv3+, on the validation data were used as inputs to a convolutional neural network acting as a meta-learner. Finally, the performance of the proposed method was evaluated on the test data. The proposed method achieved improved performance across the evaluated metrics, with the two key segmentation metrics, IoU and Dice score, reaching 94.49% and 97.13%, respectively. These results indicate greater overlap between the predicted and ground-truth masks and more accurate segmentation. The robustness of these results was further confirmed through five-fold cross-validation, in which the proposed method consistently outperformed the individual models. Based on the results obtained and comparisons with recent studies, stacking-based ensemble learning, by integrating the strengths of individual models, can achieve more reliable results in lung field segmentation.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2026-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149289215","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Construction and benchmarking of the AFISMI water-filled CT phantom against the ACR, AAPM and Catphan 600 phantoms using automated image quality analysis with IndoQCT. 使用IndoQCT的自动图像质量分析,对AFISMI充水CT模体与ACR、AAPM和Catphan 600模体进行构建和基准测试。
IF 2.4 4区 医学
Physical and Engineering Sciences in Medicine Pub Date : 2026-10-23 DOI: 10.1007/s13246-026-01812-5
Lukmanda Evan Lubis, Choirul Anam, Ariij Naufal, Ani Sulistyani, Syaukha Ahmad Risyad, Ungguh Prawoto, Nur Afifah, Hanendya Disha Randy Raharja, Freddy Haryanto, Supriyanto Ardjo Pawiro
{"title":"Construction and benchmarking of the AFISMI water-filled CT phantom against the ACR, AAPM and Catphan 600 phantoms using automated image quality analysis with IndoQCT.","authors":"Lukmanda Evan Lubis, Choirul Anam, Ariij Naufal, Ani Sulistyani, Syaukha Ahmad Risyad, Ungguh Prawoto, Nur Afifah, Hanendya Disha Randy Raharja, Freddy Haryanto, Supriyanto Ardjo Pawiro","doi":"10.1007/s13246-026-01812-5","DOIUrl":"https://doi.org/10.1007/s13246-026-01812-5","url":null,"abstract":"<p><p>Routine computed tomography (CT) quality control (QC) is used to verify adequate image quality, support radiation-dose optimisation, and identify changes in scanner performance. Commonly used test objects include the ACR CT Phantom, the AAPM CT Performance Phantom, and the Catphan 600. The AFISMI CT Phantom is a locally manufacturable, water-filled prototype developed for routine constancy testing. This study provides preliminary single-scanner benchmarking of the AFISMI phantom using the IndoQCT automated analysis platform. The AFISMI phantom comprises a hollow polymethyl methacrylate (PMMA) shell (16 cm diameter and 10 cm length), a nominal 1.0-mm aluminium sheet fixed at 45° for slice-thickness measurement, and acrylic and Teflon inserts. Each phantom was scanned in three separate acquisitions on a Philips Ingenuity 128 CT scanner using 120 kVp, 300 mAs, a 5.0-mm slice thickness, and a 200-mm field of view; each acquisition was analysed independently. IndoQCT assessed uniformity in homogeneous water-filled or water-equivalent regions, Hounsfield unit (HU) accuracy, noise power spectrum (NPS), modulation transfer function (MTF), slice thickness, and signal-difference-to-noise ratio (SDNR). Raw-noise magnitude was not analysed separately because it is not included in the Indonesian national CT Compliance Test protocol used to define the QC scope. Under the tested scan and reconstruction conditions, the AFISMI phantom produced broadly comparable results for uniformity, water CT-number accuracy, MTF, and slice-thickness measurement relative to the commercial reference phantoms. NPS magnitude and shape differed among the phantoms. The AFISMI phantom had a higher mean SDNR than the AAPM phantom under the tested conditions, but this result cannot be used to claim better low-contrast performance because phantom geometry, target contrast, and background materials differed. Scalar outcomes are reported as mean ± standard deviation from three acquisitions and compared descriptively; no inferential statistical tests were performed. The AFISMI phantom and IndoQCT showed feasibility for automated CT constancy measurements under the tested single-scanner conditions. The findings represent preliminary benchmarking rather than independent validation or evidence of comparative advantage. Longitudinal baseline testing, multi-scanner evaluation, production-unit reproducibility assessment, and formal cost analysis are required before broad QA applicability or economic advantage can be established.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2026-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149246892","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信
小红书