Physical and Engineering Sciences in Medicine最新文献_第9页

Development of a customized three-dimensional bolus using transparent gel wax and its application in electron beam therapy. 透明凝胶蜡定制三维微丸的研制及其在电子束治疗中的应用。

IF 2.4 4区医学

Physical and Engineering Sciences in Medicine Pub Date : 2026-08-27 DOI: 10.1007/s13246-026-01790-8

Young Jin Won, Jung Ju Jo, Su Ah Yu, Su Jung Shim, Kum Bae Kim, Jung Hoon Kim, Sang Hyoun Choi, Samju Cho

{"title":"Development of a customized three-dimensional bolus using transparent gel wax and its application in electron beam therapy.","authors":"Young Jin Won, Jung Ju Jo, Su Ah Yu, Su Jung Shim, Kum Bae Kim, Jung Hoon Kim, Sang Hyoun Choi, Samju Cho","doi":"10.1007/s13246-026-01790-8","DOIUrl":"10.1007/s13246-026-01790-8","url":null,"abstract":"This study aimed to develop a customized bolus using commercially available transparent gel wax (TGW) without requiring 3D printing technology and to evaluate its applicability in radiotherapy, including its physical and dosimetric characteristics. A dental alginate impression was taken from the curved surface of a mastectomy phantom to replicate the patient's skin contour. Based on this, a silicone mould was fabricated, into which TGW was poured to form the customized bolus. The fabricated bolus was evaluated for its physical properties (density, electron density, homogeneity) and bolus conformity index (BCI), treatment planning dosimetric analysis, and actual dose measurements using optically stimulated luminescent (OSL) dosimeters, in comparison with a conventional vinyl gel sheet bolus (SuperFlex). The TGW bolus demonstrated high transparency and excellent homogeneity (standard deviation of internal HU: ±5.1), and its BCI was 0.03, indicating a very high level of conformity to the virtual bolus. Under 6 MeV and 8 MeV electron beam conditions, the TGW bolus showed mean dose errors of - 0.2% ± 1.3% and 0.5% ± 1.2%, respectively, which were numerically comparable to those of the SuperFlex bolus (0.6% ± 1.8% and - 2.1% ± 1.4%, respectively), with both systems providing clinically acceptable dose accuracy. In particular, the TGW bolus showed superior conformity and reproducibility in regions with high surface curvature, effectively reducing dose loss caused by air gaps. TGW is a low-cost, transparent, and flexible material that enables rapid fabrication (within one day) of a customized bolus through a simple moulding process. Its superior physical stability and equivalent dosimetric performance compared to existing products suggest strong potential for clinical application in radiotherapy.","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2026-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148841372","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

An end-to-end quality assurance procedure for pelvic VMAT using optically stimulated luminescence dosimeters and an anthropomorphic phantom. 盆腔VMAT端到端的质量保证程序使用光刺激发光剂量计和拟人化幻影。

IF 2.4 4区医学

Physical and Engineering Sciences in Medicine Pub Date : 2026-08-24 DOI: 10.1007/s13246-026-01800-9

Ahlam Azalmad, Mohamed Abour, Mehdi El Ouartiti, Mohamed Hilal

{"title":"An end-to-end quality assurance procedure for pelvic VMAT using optically stimulated luminescence dosimeters and an anthropomorphic phantom.","authors":"Ahlam Azalmad, Mohamed Abour, Mehdi El Ouartiti, Mohamed Hilal","doi":"10.1007/s13246-026-01800-9","DOIUrl":"https://doi.org/10.1007/s13246-026-01800-9","url":null,"abstract":"Background: Volumetric modulated arc therapy (VMAT) enables highly conformal pelvic dose delivery, but its clinical benefit depends on agreement between the Treatment Planning System (TPS) calculation and the dose actually delivered in anatomically realistic conditions.Purpose: To experimentally validate VMAT dosimetric accuracy for cervical cancer using optically stimulated luminescence dosimeters (OSLDs) placed in an anthropomorphic female pelvic phantom.Materials and methods: A female pelvic phantom was CT-scanned. A dual-arc VMAT plan was created in Eclipse (v18) using the Acuros XB algorithm with heterogeneity correction. Fifty-three OSLDs were positioned across seven pelvic slices (28-34) spanning in-field, edge, peripheral, and out-of-field regions. Measured doses were compared to TPS values using a TG-119-style percent difference metric.Results: Overall agreement was clinically acceptable. The mean %Diff (OSL vs. TPS) was + 3.56% (range - 2.13% to + 6.93%). In-field doses showed the closest agreement (≤ 3%). Larger deviations occurred at the field edge (≈ 3.17%-6.93%), consistent with steep dose gradients. Peripheral and out-of-field locations generally remained within ~ 5%-7%, where scatter and low-dose modeling uncertainty dominate. Reproducibility was strong: SD_OSL values were < 5.2%, with mean SD of 2.63% (in-field), 4.34% (edge), 4.44% (peripheral), and 4.96% (out-of-field).Conclusion: OSLD measurements in an anatomically realistic female pelvic phantom confirm that cervical cancer VMAT delivery is accurate and reproducible. These results support the reliability of Eclipse (v18) using the Acuros XB algorithm across high-dose, gradient, and low-dose regions.","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2026-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148814201","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 novel approach for predicting heart failure survival using a rectangular coded network. 使用矩形编码网络预测心力衰竭生存的新方法。

IF 2.4 4区医学

Physical and Engineering Sciences in Medicine Pub Date : 2026-08-15 DOI: 10.1007/s13246-026-01791-7

Ahmet Alkan, Kubilay Muhammed Sunnetci, Faruk Enes Oguz

{"title":"A novel approach for predicting heart failure survival using a rectangular coded network.","authors":"Ahmet Alkan, Kubilay Muhammed Sunnetci, Faruk Enes Oguz","doi":"10.1007/s13246-026-01791-7","DOIUrl":"https://doi.org/10.1007/s13246-026-01791-7","url":null,"abstract":"This paper provides both effortless augmentation of data and efficient creation of images according to the image input size of deep learning models by converting almost all numerical data into 24-bit images of particular standards. As cardiovascular disease is a cause of mortality, artificial intelligence-based architectures may play an important role here, and predicting survival from heart failure is a great challenge. For this purpose, we adjust the image input size according to different deep learning architectures by using the automated feature engineering technique in the approach, which can be easily used in different numerical datasets. Afterward, we horizontally augment the transpose of the new features obtained, thus creating the 8-bit rectangular coded images. After converting these images to 24-bit, we rotate them into multiples of 15° using different coefficients to augment the dataset. We train the ResNet18 and ResNet50 architectures using these images in the new data. According to the findings, the performance metrics (Accuracy, Sensitivity, Specificity, and F1 Score) are quantified as 0.9331-0.9610-0.8742-0.9512 for ResNet18 and 0.9617-0.9743-0.9349-0.9718 for ResNet50. Evaluated alongside current literature, these findings confirm that the proposed methodology represents an innovative, competitive, and highly applicable solution for heart failure classification. The proposed novel method allows numerical data to be evaluated as image representations and, accordingly, to be easily utilized in image processing, data augmentation, and similar techniques.","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2026-08-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148763098","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

Diabetic foot ulcer classification using an enhanced coordinate attention integrated ConvNext model. 基于增强坐标注意集成ConvNext模型的糖尿病足溃疡分类。

IF 2.4 4区医学

Physical and Engineering Sciences in Medicine Pub Date : 2026-06-01 Epub Date: 2026-01-05 DOI: 10.1007/s13246-025-01692-1

L Jani Anbarasi, R Neeraja, S Geetha, R Vidhya, Vinayakumar Ravi, D Dhanya

{"title":"Diabetic foot ulcer classification using an enhanced coordinate attention integrated ConvNext model.","authors":"L Jani Anbarasi, R Neeraja, S Geetha, R Vidhya, Vinayakumar Ravi, D Dhanya","doi":"10.1007/s13246-025-01692-1","DOIUrl":"10.1007/s13246-025-01692-1","url":null,"abstract":"Diabetic foot ulcers (DFUs) pose a significant complication of diabetes with the potential to lead to amputation if not effectively managed. Current DFU treatments require rigorous monitoring by both healthcare professionals and patients, which is challenging due to the high costs associated with diagnosis, treatment and long-term care. A major limitation of these approaches is their limited capacity to identify highly relevant pattern connections and broad contextual correlations resulting inaccuracies in classifying regions of interest. This research introduces an attention enhanced deep learning-based automated approach for assessing DFUs using images to expedite the investigation process and offer optimal recommendations. Adaptive thresholding is employed to enhance the contrast and uniformity of DFU images and thereby improves the feature extraction. A hybrid model incorporating coordinate attention enhanced ConvNeXt is used for effective DFU image classification to enhance the representation of complex patterns through efficient parameter utilization. The ConvNeXt architecture is designed to scale efficiently across various sizes by utilizing depthwise separable convolutions and improved image normalization. This model is augmented with coordinate attention, which captures spatial information in both horizontal and vertical directions, aiding in the extraction of long-range dependency features for more accurate classification of DFU images. Experimental results demonstrate that the model achieves an accuracy of 97.16% and F1-score of 0.97.","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"617-630"},"PeriodicalIF":2.4,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145901346","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

CNN1D-LSTM with SMOTE for breast cancer classification: performance and statistical insights. CNN1D-LSTM与SMOTE用于乳腺癌分类：性能和统计见解。

IF 2.4 4区医学

Physical and Engineering Sciences in Medicine Pub Date : 2026-06-01 Epub Date: 2026-03-24 DOI: 10.1007/s13246-026-01724-4

Kamini G Panchbhai, Lalchand B Patle, Madhusudan G Lanjewar

{"title":"CNN1D-LSTM with SMOTE for breast cancer classification: performance and statistical insights.","authors":"Kamini G Panchbhai, Lalchand B Patle, Madhusudan G Lanjewar","doi":"10.1007/s13246-026-01724-4","DOIUrl":"10.1007/s13246-026-01724-4","url":null,"abstract":"Breast cancer is a significant global health issue, demanding early identification to provide appropriate therapy and satisfactory survival results. This work used two independent imbalanced datasets (EIS-BT and WBCD). CNN1D with Long Short-Term Memory (LSTM) was integrated to acquire features from these datasets to identify breast cancer. Three scenarios for breast cancer detection were investigated based on CNN1D-LSTM derived characteristics from Dataset-1, Dataset-2, and their combination. The Synthetic Minority Over-sampling Technique (SMOTE) was used to balance the collected features in all three scenarios. The suggested CNN1D-LSTM-SMOTE approach, in conjunction with Support Vector Classification (SVC), yields impressive results with a Matthews Correlation Coefficient (MCC) of 97.2 % on Dataset-1 and 100.0% on Dataset-2. Random Forest Classifiers (RFC) perform better, achieving an MCC of 98.4% on the combined features. The K-fold approach was used, yielding average MCCs of 91.7%, 74.1%, and 96.9% on Dataset-1, Dataset-2, and the combined features, respectively. Statistical analysis revealed a p-value of 0.01, signifying the significance of the findings, and a standard error of 0.006 for the combined features. Bootstrapping was employed to calculate confidence intervals, resulting in Lower Confidence Intervals (LCI) of 95.6% and Higher Confidence Intervals (HCI) of 97.9% for the combined features. These findings highlight the model's potential clinical application in supporting oncologists with early, real-time, reliable, and automated breast cancer diagnosis, leading to improved diagnostic procedures and patient outcomes.","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"747-758"},"PeriodicalIF":2.4,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147515945","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 study on using custom 3D-printed tongue bites for radiotherapy patients with oral tongue carcinoma. 定制3d打印舌咬用于放疗患者舌癌的研究。

IF 2.4 4区医学

Physical and Engineering Sciences in Medicine Pub Date : 2026-06-01 Epub Date: 2026-03-19 DOI: 10.1007/s13246-026-01725-3

Muhammad Furqan Zulqurnain, Haris Arif, Misbah Batool, Nouman Amjad, Robin Hill

{"title":"A study on using custom 3D-printed tongue bites for radiotherapy patients with oral tongue carcinoma.","authors":"Muhammad Furqan Zulqurnain, Haris Arif, Misbah Batool, Nouman Amjad, Robin Hill","doi":"10.1007/s13246-026-01725-3","DOIUrl":"10.1007/s13246-026-01725-3","url":null,"abstract":"Oral cavity cancers are a debilitating form of head and neck cancer with high rates of mortality. Radiotherapy is one of the main forms of treatment but relies on minimizing doses that are delivered to organs at risk and considering any motion in the mouth. One solution is to use a block within the mouth which acts to reduce motion and decreases tissue heterogeneity. In this work, we developed a process for designing a customized tissue-equivalent 3D-printed tongue bite and evaluated its impact on the radiation treatment. Six patients with stage III or IV oral cancer were involved. Computed tomography (CT) images for each patient were acquired with currently used Styrofoam tongue bites within the mouth. The designs of 3D tongue bites were prepared using those CT images and then printed on an SLA printer using F80 resin which is a tissue-equivalent and biocompatible material. Secondary CT images were then acquired for each patient with the 3D tongue bites to have a dosimetric comparison. Volumetric-modulated arc therapy (VMAT) planning was carried out for individual patients on both CT images. Plan parameters, fractionation scheme and optimization priorities were all kept the same. The radiotherapy plans utilizing 3D tongue bites showed better PTV coverage and reduced Dmax (p = 0.028). Doses to organs at risk (OARs) including brainstem, parotid glands and hard palate were also reduced (p < 0.028) except for the spinal cord (p > 0.05). The dose conformity and homogeneity were also improved (p = 0.028 and p = 0.044 respectively). All patients reported that the 3D tongue bites were soft, conformal to the oral cavity, comfortable and did not cause any gag reflex. We conclude that the 3D tongue bite is a useful utility that improves the treatment of patients with oral cancer.","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"881-888"},"PeriodicalIF":2.4,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13375762/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147487825","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Evaluation of ThinkQA (v2.0.1.11) as an online secondary dose check for MR guided radiation therapy with the Elekta Unity MR-Linac. 评估ThinkQA （v2.0.1.11）作为Elekta Unity MR- linac磁共振引导放射治疗的在线二次剂量检查。

IF 2.4 4区医学

Physical and Engineering Sciences in Medicine Pub Date : 2026-06-01 Epub Date: 2026-01-19 DOI: 10.1007/s13246-025-01693-0

Ariadne S Brodmann, John A Baines

{"title":"Evaluation of ThinkQA (v2.0.1.11) as an online secondary dose check for MR guided radiation therapy with the Elekta Unity MR-Linac.","authors":"Ariadne S Brodmann, John A Baines","doi":"10.1007/s13246-025-01693-0","DOIUrl":"10.1007/s13246-025-01693-0","url":null,"abstract":"To evaluate ThinkQA (TQA), a collapsed cone convolution-based secondary dose check, as an alternative to MU2net (Clarkson-based, point-dose) for online adaptive planning on the Elekta Unity 1.5 T MR-Linac at Townsville University Hospital. Commissioning followed MPPG 5.b tests. The reference-dose agreement, magnetic-field modelling, directional dependence, output factors, off-axis points, heterogeneous slab geometries and calculation properties were assessed. Nine step-and-shoot IMRT plans (courtesy of Elekta) and 226 retrospectively analysed adapted fractions (prostate and pelvic nodes; planning target volumes 1.9-170.0 cm3) were compared between TQA and Monaco by gamma analysis (global 10.0% threshold; 2.0%/2.0 mm, 3.0%/2.0 mm). At 10.0 cm depth under TQA reference conditions, the mean absolute point-dose difference versus Monaco was 0.4%. TQA reproduced models the magnetic-field-induced cross-plane asymmetry with close agreement to Monaco. Directional dependence differences were ≤ ± 1.2% except when traversing the couch (± 1.8%). Output factors agreed within ≤ 1.0% (SSD 133.5 cm) and ≤ 2.0% (SSD 138.5 cm). In 226 clinical fractions, 3.0%/2.0 mm (global) yielded 93.0% passes in the high-dose region and 100.0% in other regions; 2.0%/2.0 mm yielded 25% high-dose passes. TQA results were available within about 1 min post Monaco export. TQA provides accurate, rapid, volumetric secondary dose verification for Unity, improves agreement with Monaco, and reduces console time by eliminating dose point re-selection. A 3.0%/2.0 mm global gamma criterion is a clinical acceptance level, with tighter criteria reserved for targeted investigations.","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"639-654"},"PeriodicalIF":2.4,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13375681/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145999435","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Education note: cultivating assessment and feedback for learning in our training hospital. 教育说明：在我们的培训医院培养学习评估和反馈。

IF 2.4 4区医学

Physical and Engineering Sciences in Medicine Pub Date : 2026-06-01 Epub Date: 2026-03-23 DOI: 10.1007/s13246-026-01721-7

Rebecca Day, Louise Beckingsale

{"title":"Education note: cultivating assessment and feedback for learning in our training hospital.","authors":"Rebecca Day, Louise Beckingsale","doi":"10.1007/s13246-026-01721-7","DOIUrl":"10.1007/s13246-026-01721-7","url":null,"abstract":"High-value feedback is essential for the successful development of medical physics trainees (registrars) as they complete their clinical training. In this education note, we present an overview of a small education intervention we implemented in our hospital to encourage feedback conversations, one of the principles of high-value feedback. Our intervention was based on the concepts of 'assessment for learning' and 'programmatic assessment'. This intervention encourages registrars to take ownership of the feedback process associated with each learning outcome assessment. Registrars are encouraged to complete and document a self-assessment of their performance, before seeking feedback from their trainer. We modified an assessment template to support this process. This new approach appears to have resulted in higher quality feedback conversations between registrars and trainers. Additionally, trainers have benefited from the registrars completing the majority of the assessment template, thus reducing their workload. Whilst this approach has increased the workload for registrars, we believe this has benefits for their learning. We hope other centres can learn from our experience and may consider how they can adopt a similar process for their setting.","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"1105-1110"},"PeriodicalIF":2.4,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13375686/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147505236","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A new model based on multi-axis vision transformer for chondromalacia patella diagnosis in magnetic resonance scans. 基于多轴视觉变压器的髌骨软骨软化症磁共振诊断新模型。

IF 2.4 4区医学

Physical and Engineering Sciences in Medicine Pub Date : 2026-06-01 Epub Date: 2026-02-04 DOI: 10.1007/s13246-026-01707-5

Semih Demirel, Okan Demirtaş, Sümeyra Kuş Ordu, Ömer Kazcı, Habip Eser Akkaya, Oktay Yıldız

{"title":"A new model based on multi-axis vision transformer for chondromalacia patella diagnosis in magnetic resonance scans.","authors":"Semih Demirel, Okan Demirtaş, Sümeyra Kuş Ordu, Ömer Kazcı, Habip Eser Akkaya, Oktay Yıldız","doi":"10.1007/s13246-026-01707-5","DOIUrl":"10.1007/s13246-026-01707-5","url":null,"abstract":"A degenerative disease of the patellofemoral joint cartilage, chondromalacia patella (CMP) often results in anterior knee discomfort and functional disability. Determining the best course of therapy and stopping the progression of the disease depend on an accurate and timely diagnosis. In this work, we provide a deep learning architecture based on transformers for the classification of chondromalacia patella using magnetic resonance imaging (MRI) data. We assessed transformer-based designs including Multi-Axis Vision Transformer (MaxViT), Vision Transformer (ViT), and Swin Transformer in addition to convolutional neural network (CNN) based models like Google Network (GoogLeNet), Residual Network 18 (ResNet18), and Mobile Network v2 (MobileNetV2). We evaluated the models' ability to differentiate between cases of chondromalacia patella and normal cases. With an accuracy of 0.9817, precision of 0.9821, recall of 0.9817, and F1-score of 0.9818, Multi-Axis Vision Transformer outperformed all other models on the testing dataset.","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"863-879"},"PeriodicalIF":2.4,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13375817/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146120721","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Fundamental performance and clinical usefulness of a new AEC-equipped flat panel detector for dose optimization. 用于剂量优化的新型aec平板探测器的基本性能和临床用途。

IF 2.4 4区医学

Physical and Engineering Sciences in Medicine Pub Date : 2026-06-01 Epub Date: 2026-01-27 DOI: 10.1007/s13246-026-01705-7

Sho Maruyama, Hiroki Saitou, Nao Koyama

{"title":"Fundamental performance and clinical usefulness of a new AEC-equipped flat panel detector for dose optimization.","authors":"Sho Maruyama, Hiroki Saitou, Nao Koyama","doi":"10.1007/s13246-026-01705-7","DOIUrl":"10.1007/s13246-026-01705-7","url":null,"abstract":"The demand for bedside radiography is increasing due to critical clinical needs, including infection control and the limited mobility of severely ill patients. However, radiation dose adjustment in these settings remains heavily reliant on the expertise and experience of radiographers. To address this issue, a novel flat panel detector (FPD) integrated with an automatic exposure control (AEC) system has been developed. This study aims to experimentally evaluate the fundamental performance of this system and clarify its clinical utility, including its potential limitations. The dependency of the AEC performance on object thickness and tube voltage was investigated using acrylic phantoms. To simulate clinical scenarios, the AEC response was examined using a chest phantom. Additionally, the effects of source-to-image distance and oblique X-ray incidence on the AEC performance were also evaluated using a quality-control test device. Our results elucidated the behavior of the exposure index (EI) and image quality under varying tube voltage and object thickness. In clinical conditions, the introduction of the AEC system significantly reduced EI, confirming its potential for effective dose management. Multiple factors were identified that influence both the AEC response and image quality, such as sensor positioning, imaging distance, and beam angle. These findings demonstrate that the AEC-equipped FPD system maintains consistent image quality while effectively reducing the radiation dose under various simulated imaging conditions. Our results also underscore the importance of accounting for environmental factors that affect dose control and image characteristics, highlighting the need for practical adjustment in routine clinical operation.","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"837-847"},"PeriodicalIF":2.4,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146054610","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