Physical and Engineering Sciences in Medicine最新文献

{"title":"Design and validation of a multi-angle planar surface electrode system for electrical impedance tomography.","authors":"Busra Oguzhan, Mustafa Istanbullu","doi":"10.1007/s13246-025-01597-z","DOIUrl":"10.1007/s13246-025-01597-z","url":null,"abstract":"<p><p>Electrical impedance-based imaging techniques offer a noninvasive and radiation-free alternative for assessing internal tissue structures. In this study, a novel bioimpedance measurement (BIM) system featuring a planar concentric ring electrode configuration was proposed to improve the spatial resolution and practicality of traditional electrical impedance tomography (EIT) approaches. Inspired by the 360° scanning principle of computed tomography (CT), the system enables multiangle current injection and voltage measurement through a structured stimulation protocol. A total of 32 electrodes, arranged in four concentric rings, were used to capture impedance variations across different angular perspectives, enhancing the detection of localized anomalies. The system was validated through both simulation and experimental studies. Simulations conducted using the EIDORS environment demonstrated successful localization of inhomogeneities within a modeled medium, whereas experimental tests using a saline-filled tank and embedded objects confirmed the system's practical effectiveness. Data acquired from the system were reconstructed into impedance images via the Gauss-Newton algorithm with total variation regularization, followed by image processing steps for improved visualization and boundary identification. The proposed system combines a cost-effective hardware design with a robust measurement and image reconstruction framework, offering a portable and accurate solution for biomedical diagnostics and laboratory research. The results highlight its potential for clinical and nonclinical applications requiring noninvasive monitoring.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"1439-1451"},"PeriodicalIF":2.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144643902","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}

{"title":"A novel UNet-SegNet and vision transformer architectures for efficient segmentation and classification in medical imaging.","authors":"Simon Tongbram, Benjamin A Shimray, Loitongbam Surajkumar Singh","doi":"10.1007/s13246-025-01564-8","DOIUrl":"10.1007/s13246-025-01564-8","url":null,"abstract":"<p><p>Medical imaging has become an essential tool in the diagnosis and treatment of various diseases, and provides critical insights through ultrasound, MRI, and X-ray modalities. Despite its importance, challenges remain in the accurate segmentation and classification of complex structures owing to factors such as low contrast, noise, and irregular anatomical shapes. This study addresses these challenges by proposing a novel hybrid deep learning model that integrates the strengths of Convolutional Autoencoders (CAE), UNet, and SegNet architectures. In the preprocessing phase, a Convolutional Autoencoder is used to effectively reduce noise while preserving essential image details, ensuring that the images used for segmentation and classification are of high quality. The ability of CAE to denoise images while retaining critical features enhances the accuracy of the subsequent analysis. The developed model employs UNet for multiscale feature extraction and SegNet for precise boundary reconstruction, with Dynamic Feature Fusion integrated at each skip connection to dynamically weight and combine the feature maps from the encoder and decoder. This ensures that both global and local features are effectively captured, while emphasizing the critical regions for segmentation. To further enhance the model's performance, the Hybrid Emperor Penguin Optimizer (HEPO) was employed for feature selection, while the Hybrid Vision Transformer with Convolutional Embedding (HyViT-CE) was used for the classification task. This hybrid approach allows the model to maintain high accuracy across different medical imaging tasks. The model was evaluated using three major datasets: brain tumor MRI, breast ultrasound, and chest X-rays. The results demonstrate exceptional performance, achieving an accuracy of 99.92% for brain tumor segmentation, 99.67% for breast cancer detection, and 99.93% for chest X-ray classification. These outcomes highlight the ability of the model to deliver reliable and accurate diagnostics across various medical contexts, underscoring its potential as a valuable tool in clinical settings. The findings of this study will contribute to advancing deep learning applications in medical imaging, addressing existing research gaps, and offering a robust solution for improved patient care.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"1023-1055"},"PeriodicalIF":2.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144585330","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}

{"title":"Action potential as a contributing factor in axonal transport: a numerical study.","authors":"AmirAli Saboorian, Bahman Vahidi","doi":"10.1007/s13246-025-01591-5","DOIUrl":"10.1007/s13246-025-01591-5","url":null,"abstract":"<p><p>Despite various studies on axonal mechanics in recent years, the mechanisms and factors contributing to axonal transport are still not fully understood. In this study, the possible role of action potential (AP) propagation through neurites in axonal transport was explored by utilizing underlying physical principles through numerical simulation. A fluid-structure interaction model was used to simulate the physical behavior of the axon as action potential waves propagate. The axon and its membrane were modeled as a fluid-filled cylinder with elastic walls, where the action potential acts as a moving radial load on the axon. Utilizing computational fluid dynamics simulation and accounting for forces induced by the action potential led to the emergence of an intercellular fluid flow inside the axon, which was subsequently incorporated into current models of axonal transport in the literature. The convective intercellular fluid flow induced by the action potential acts as a mechanism for axonal transport, with velocities ranging from 2 to 17 mm per day, which is consistent with previously reported ranges for the slow axonal transport component. Additionally, by incorporating the effect of convective flow, it was shown that unidirectional transport, coupled with convective transport, can successfully describe the movement of larger cargos against their concentration gradients. The results demonstrated that for the squid giant axon and hippocampal neurites, the displacement pulse propagates almost simultaneously with the AP. Analyzing the interaction between action potential and axonal transport can lead to a better understanding of these phenomena.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"1375-1388"},"PeriodicalIF":2.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144676207","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}

{"title":"Efficient feature extraction using light-weight CNN attention-based deep learning architectures for ultrasound fetal plane classification.","authors":"Arrun Sivasubramanian, Divya Sasidharan, V Sowmya, Vinayakumar Ravi","doi":"10.1007/s13246-025-01566-6","DOIUrl":"10.1007/s13246-025-01566-6","url":null,"abstract":"<p><p>Ultrasound fetal imaging is beneficial to support prenatal development because it is affordable and non-intrusive. Nevertheless, fetal plane classification (FPC) remains challenging and time-consuming for obstetricians since it depends on nuanced clinical aspects, which increases the difficulty in identifying relevant features of the fetal anatomy. Thus, to assist with its accurate feature extraction, a lightweight artificial intelligence architecture leveraging convolutional neural networks and attention mechanisms is proposed to classify the largest benchmark ultrasound dataset. The approach fine-tunes from lightweight EfficientNet feature extraction backbones pre-trained on the ImageNet1k. to classify key fetal planes such as the brain, femur, thorax, cervix, and abdomen. Our methodology incorporates the attention mechanism to refine features and 3-layer perceptrons for classification, achieving superior performance with the highest Top-1 accuracy of 96.25%, Top-2 accuracy of 99.80% and F1-Score of 0.9576. Importantly, the model has 40x fewer trainable parameters than existing benchmark ensemble or transformer pipelines, facilitating easy deployment on edge devices to help clinical practitioners with real-time FPC. The findings are also interpreted using GradCAM to carry out clinical correlation to aid doctors with diagnostics and improve treatment plans for expectant mothers.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"1079-1093"},"PeriodicalIF":2.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144175707","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}

{"title":"In response to the topical debate: in Australia professional registration for qualified medical physicists should be mandated through the Australian Health Practitioner Regulation Agency (AHPRA), and the associated letter to the editor in response.","authors":"Sivananthan Sarasanandarajah","doi":"10.1007/s13246-025-01572-8","DOIUrl":"10.1007/s13246-025-01572-8","url":null,"abstract":"","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"1487-1488"},"PeriodicalIF":2.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144129000","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}

{"title":"Thoracic staging of lung cancers by ¹⁸FDG-PET/CT: impact of artificial intelligence on the detection of associated pulmonary nodules.","authors":"Mariem Trabelsi, Hamida Romdhane, Dorra Ben-Sellem","doi":"10.1007/s13246-025-01567-5","DOIUrl":"10.1007/s13246-025-01567-5","url":null,"abstract":"<p><p>This study focuses on automating the classification of certain thoracic lung cancer stages in 3D ¹⁸FDG-PET/CT images according to the 9th Edition of the TNM Classification for Lung Cancer (2024). By leveraging advanced segmentation and classification techniques, we aim to enhance the accuracy of distinguishing between T4 (pulmonary nodules) Thoracic M0 and M1a (pulmonary nodules) stages. Precise segmentation of pulmonary lobes using the Pulmonary Toolkit enables the identification of tumor locations and additional malignant nodules, ensuring reliable differentiation between ipsilateral and contralateral spread. A modified ResNet-50 model is employed to classify the segmented regions. The performance evaluation shows that the model achieves high accuracy. The unchanged class has the best recall 93% and an excellent F1 score 91%. The M1a (pulmonary nodules) class performs well with an F1 score of 94%, though recall is slightly lower 91%. For T4 (pulmonary nodules) Thoracic M0, the model shows balanced performance with an F1 score of 87%. The overall accuracy is 87%, indicating a robust classification model.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"1095-1105"},"PeriodicalIF":2.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144530455","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}

{"title":"Establishing facility reference levels and comparing to international diagnostic reference levels in paediatric general X-ray.","authors":"Samuel M Lilli, Amanda A Perdomo","doi":"10.1007/s13246-025-01563-9","DOIUrl":"10.1007/s13246-025-01563-9","url":null,"abstract":"<p><p>Diagnostic Reference Levels (DRLs) can be used to assess the radiation exposure for specific protocols and identify areas of potential optimisation. Despite paediatric general X-ray (GXR) being a relatively low dose modality, due to the high radiosensitivity of children, it is imperative that doses remain as low as reasonably achievable (ALARA). This study aims to compare our institute's Dose-Area-Product (DAP) to currently available local, national, and regional DRLs, as there are currently no Australian DRL values established for paediatric GXR. The DAPs for GXR protocols are recorded in a commercially available DMS software, MyXrayDose, which generates a report of the Facility Reference Levels (FRLs) for all GXR protocols. As MyXrayDose uses age categories, our FRLs were converted to weight-based FRLs using the 50th percentile values derived from the World Health Organisation and Centres for Disease Control Weight-for-age charts. These were compared to published DRLs from eleven different countries and regions of the world. Pelvis Anterior-Posterior (AP)/Posterior-Anterior (PA), Abdomen AP/PA, Thorax AP/PA and Thorax lateral protocols were compared to available national and regional DRLs. For example, from 1st July 2023-30th June 2024, 1008 Abdomen AP/PA X-rays were conducted in Room 1 with a fixed GXR unit. The FRL for 31.2-56.5 kg (10-15 years) patients in Room 1 (1093 mGy.cm²) was more than 2.3 times greater than the European DRL (475 mGy.cm²). The FRLs for patients with a mean weight of 6 kg and 14 kg were below the European DRL whilst 25 kg, 44 kg and 60 kg patients exceeded the European Abdomen AP/PA DRL. The establishment of DRLs helps institutes identify potential areas of optimisation. As some of our GXR protocols exceed the European DRLs, the next step at our institute is to complete a multi-disciplinary image quality assessment to identify if it is possible to optimise these protocols.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"1015-1022"},"PeriodicalIF":2.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144188257","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}

{"title":"Evaluating the impact of view position in X-ray imaging for the classification of lung diseases.","authors":"Aya Hage Chehade, Nassib Abdallah, Jean-Marie Marion, Mohamad Oueidat, Pierre Chauvet","doi":"10.1007/s13246-025-01579-1","DOIUrl":"10.1007/s13246-025-01579-1","url":null,"abstract":"<p><p>Clinical information associated with chest X-ray images, such as view position, patient age and gender, plays a crucial role in image interpretation, as it influences the visibility of anatomical structures and pathologies. However, most classification models using the ChestX-ray14 dataset relied solely on image data, disregarding the impact of these clinical variables. This study aims to investigate which clinical variable affects image characteristics and assess its impact on classification performance. To explore the relationships between clinical variables and image characteristics, unsupervised clustering was applied to group images based on their similarities. Afterwards, a statistical analysis was then conducted on each cluster to examine their clinical composition, by analyzing the distribution of age, gender, and view position. An attention-based CNN model was developed separately for each value of the clinical variable with the greatest influence on image characteristics to assess its impact on lung disease classification. The analysis identified view position as the most influential variable affecting image characteristics. Accounting for this, the proposed approach achieved a weighted area under the curve (AUC) of 0.8176 for pneumonia classification, surpassing the base model (without considering view position) by 1.65% and outperforming previous studies by 6.76%. Furthermore, it demonstrated improved performance across all 14 diseases in the ChestX-ray14 dataset. The findings highlight the importance of considering view position when developing classification models for chest X-ray analysis. Accounting for this characteristic allows for more precise disease identification, demonstrating potential for broader clinical application in lung disease evaluation.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"1225-1236"},"PeriodicalIF":2.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144734068","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}

{"title":"¹⁸F-FDG PET-based liver segmentation using deep-learning.","authors":"Yuta Kaneko, Kenta Miwa, Tensho Yamao, Noriaki Miyaji, Ryuichi Nishii, Kana Yamazaki, Noriko Nishikawa, Masanori Yusa, Tatsuya Higashi","doi":"10.1007/s13246-025-01595-1","DOIUrl":"10.1007/s13246-025-01595-1","url":null,"abstract":"<p><p>Organ segmentation using ¹⁸F-FDG PET images alone has not been extensively explored. Segmentation based methods based on deep learning (DL) have traditionally relied on CT or MRI images, which are vulnerable to alignment issues and artifacts. This study aimed to develop a DL approach for segmenting the entire liver based solely on ¹⁸F-FDG PET images. We analyzed data from 120 patients who were assessed using ¹⁸F-FDG PET. A three-dimensional (3D) U-Net model from nnUNet and preprocessed PET images served as DL and input images, respectively, for the model. The model was trained with 5-fold cross-validation on data from 100 patients, and segmentation accuracy was evaluated on an independent test set of 20 patients. Accuracy was assessed using Intersection over Union (IoU), Dice coefficient, and liver volume. Image quality was evaluated using mean (SUVmean) and maximum (SUVmax) standardized uptake value and signal-to-noise ratio (SNR). The model achieved an average IoU of 0.89 and an average Dice coefficient of 0.94 based on test data from 20 patients, indicating high segmentation accuracy. No significant discrepancies in image quality metrics were identified compared with ground truth. Liver regions were accurately extracted from ¹⁸F-FDG PET images which allowed rapid and stable evaluation of liver uptake in individual patients without the need for CT or MRI assessments.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"1415-1424"},"PeriodicalIF":2.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144643901","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}

{"title":"Comparison of the air kerma standards of ARPANSA, Australia, and the IAEA in RQR, RQA, and RQT diagnostic X-ray beams.","authors":"Kam L Lee, Zakithi Msimang, Duncan Butler, Peter Thomas, Joao Cardoso","doi":"10.1007/s13246-025-01570-w","DOIUrl":"10.1007/s13246-025-01570-w","url":null,"abstract":"<p><p>A comparison of air kerma standards between the Australian Radiation Protection and Nuclear Safety Agency (ARPANSA) and the International Atomic Energy Agency (IAEA) was carried out for the RQR, RQA and RQT radiation qualities (as prescribed by IEC 61267 or IAEA TRS 457) using two ionisation chambers as transfer standards. The ratios between the IAEA and ARPANSA calibration coefficients ranged between 0.993 and 0.997 for RQR beams, 0.990 and 0.999 for RQA beams, and 0.993 to 0.994 for RQT beams. The relative expanded uncertainty for IAEA and ARPANSA was 1.2 and 1.4% respectively, and the comparison results agree at around the level of, or better than, the combined standard uncertainty of 0.74% for all the beams.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"1137-1144"},"PeriodicalIF":2.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144162986","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}