Physical and Engineering Sciences in Medicine最新文献

{"title":"Correction to: A novel hierarchical transfer learning to enhance breast cancer detection on screening mammography using deep learning.","authors":"Arman Monajemi Mamaghani, Fatemeh Baharvand Ahmadi, Zeinab Naseri, Davood Sotoude, Amin Amiri Tehranizadeh","doi":"10.1007/s13246-026-01786-4","DOIUrl":"10.1007/s13246-026-01786-4","url":null,"abstract":"","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"1791"},"PeriodicalIF":2.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148708099","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":"Correction to: Clinical applications with expired EBT-XD radiochromic film in radiotherapy.","authors":"O A García-Garduño, Y Ávila-Muñoz, I Gamboa-deBuen, J M Lárraga-Gutiérrez","doi":"10.1007/s13246-026-01785-5","DOIUrl":"10.1007/s13246-026-01785-5","url":null,"abstract":"","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"1679"},"PeriodicalIF":2.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148670922","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":"Multimodal attention-enhanced network of segmenting acute ischemic stroke from perfusion images.","authors":"Xuanhe Zhao, Shannan Chen, Patrice Monkam, Ronghui Ju, Peizhuo Zang, Chao Li, Shouliang Qi","doi":"10.1007/s13246-026-01730-6","DOIUrl":"10.1007/s13246-026-01730-6","url":null,"abstract":"<p><p>Acute ischemic stroke (AIS) is a major cause of long-term disability and mortality worldwide. Accurate segmentation of stroke lesions, particularly the infarct core and penumbra, is critical for effective treatment planning. In this study, we propose a deep learning-based multimodal segmentation network to improve the accuracy of AIS lesion delineation. The proposed framework consists of independent encoders, Multimodal Spatial and Channel Fusion (MSCF) modules, and Decoder Spatial and Channel Attention (DSCA) modules. Independent encoders are used to extract modality-specific features, while the MSCF module integrates complementary information across modalities. The DSCA module is introduced in the decoder to refine feature fusion between encoder representations and decoder features. The model was trained and evaluated on the ISLES SPES 2015, ISLES 2017, and ISLES 2018 datasets using Dice Similarity Coefficient (DSC), Hausdorff Distance (HD95), Recall, and Precision. On the ISLES SPES 2015 dataset, the proposed method achieved a DSC of 83.91%, HD95 of 4.16 mm, Recall of 78.23%, and Precision of 88.63%. On the ISLES 2017 and ISLES 2018 datasets, the model achieved DSC values of 41.32% and 54.90%, with HD95 values of 25.10 mm and 23.06 mm, respectively. These results demonstrate that the proposed multimodal fusion strategy effectively improves segmentation accuracy and robustness for AIS lesion segmentation.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"1157-1177"},"PeriodicalIF":2.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147595578","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":"Design and implementation of an automated quality assurance tool for Hounsfield unit-to-relative electron density calibration in cone beam computed tomography imaging.","authors":"Oussama El Mouden, Hamza Sekkat, Ahmed Bannan, Redouane El Baydaoui, Mustapha Bougteb, Mounir Mkimel, Abdellah Khallouqi, Maroine Tahiri, Yasmina Berrada, Fahd Chaara, Omar El Rhazouani","doi":"10.1007/s13246-026-01749-9","DOIUrl":"10.1007/s13246-026-01749-9","url":null,"abstract":"<p><p>Accurate calibration of Hounsfield Units (HU) to relative electron density (RED) is critical for reliable absorbed dose calculation in radiotherapy, particularly for cone-beam CT (CBCT)-based adaptive workflows. We developed and evaluated a fully automated HU-RED calibration and quality assurance (QA) workflow for Elekta CBCT systems, integrating PyLinac with QATrack + to enable reproducible, user-independent analysis. Using the CIRS 062 M phantom, protocol-specific HU-RED calibration curves were generated for head, thorax, abdomen and pelvis CBCT acquisitions. Systematic protocol-dependent HU offsets were observed relative to fan-beam CT, with air-equivalent inserts shifting from approximately - 1000 HU on CT to + 500-600 HU for body CBCT protocols and up to + 1000 HU for head CBCT acquisitions. Water-equivalent inserts exhibited offsets of + 580-720 HU, while dense bone showed increases of + 200-500 HU depending on protocol. Despite these offsets, short-term reproducibility was high, with standard deviations ≤ 3 HU for water, ≤ 5 HU for bone and ≤ 12 HU for air across repeated scans. Over six months of monitoring, no significant HU drift was observed, demonstrating the ability of the automated workflow to reproducibly measure and track HU constancy over time. Automated tolerance checking using ± 30 HU (water/soft tissue) and ± 50 HU (lung/bone) thresholds showed 100% compliance across all measurements. The complete analysis and QA reporting required less than one minute per scan. This automated approach provides quantitative, protocol-specific HU-RED calibration and stable long-term monitoring, supporting routine CBCT QA and adaptive radiotherapy in accordance with international guidelines.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"1369-1381"},"PeriodicalIF":2.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148200772","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":"Pancreas SBRT requires online adaptive treatment to adequately manage motion.","authors":"Tony Young, Mark Lee, Meredith Johnston, David Thwaites, Lois Holloway, Theresa Nguyen, Rebecca Ko, Sankar Arumugam","doi":"10.1007/s13246-026-01762-y","DOIUrl":"10.1007/s13246-026-01762-y","url":null,"abstract":"<p><p>Hypofractionated stereotactic body radiotherapy (SBRT) for pancreatic cancer has shown improved local control but is challenging due to the proximity of several organs at risk (OARs). This study investigated possible dosimetric variations over a simulated SBRT course for pancreatic cancer using daily MR images considering breath hold (BH) and internal target volume (ITV) motion management techniques for three treatment regimes. Ten healthy volunteers were scanned on a Siemens Skyra 3T MRI. Each volunteer had 2 sets of scans acquired per day, 3 h apart, over five days, to represent a daily simulation planning scan and a pre-treatment scan. A hypothetical GTV was generated, with a BH GTV and ITV expanded to generate two different planning target volumes (PTV). Treatment plans for each were generated using the Raystation TPS on each bulk density corrected scan. Plans were propagated and accumulated to simulate conventional, daily adaptive and online adaptive treatment regimes, with DVH comparison of PTV and OAR doses. The BH PTV D95% varied on average - 2.9% ± 3% and - 5.1% ± 5.3% for conventional and daily adaptive regimes, while the ITV PTV D95% varied on average - 8.1% ± 7.2% and - 8.5% ± 5.4% respectively. For the online adaptive approach, the BH PTV D95% varied on average 1.5% ± 2.4% while the ITV PTV D95% varied on average 3% ± 4.9%, achieving improved agreement of target dose. In conclusion, pancreas SBRT shows significant dosimetric variations from positional variations of target and OARs, but accuracy may be improved with online adaptive treatment planning.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"1525-1534"},"PeriodicalIF":2.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148670981","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":"Increasing demands on commissioning and quality assurance for cone-based multiple brain metastases robotic radiosurgery: evaluation in a custom phantom.","authors":"Godfrey Mukwada, Pejman Rowshanfarzad, Martin A Ebert","doi":"10.1007/s13246-026-01765-9","DOIUrl":"10.1007/s13246-026-01765-9","url":null,"abstract":"<p><p>CyberKnife stereotactic radiosurgery (SRS) treatment of multiple brain metastases (MBM) using fixed cone collimation is well established. This study aims to rigorously evaluate the commissioning of MBM SRS using feasible complex clinical scenarios. Sixteen gross tumour volumes (GTVs) were contoured on the CT of an in-house developed phantom. Six treatment plans, testing different levels of complexity, were generated using the Ray Tracing (RT) dose calculation algorithm and recalculated with the Monte Carlo (MC) algorithm. Respective quality assurance (QA) plans were generated on the same phantom and delivered on a CyberKnife M6 system. QA was performed with EBT4 film inserted in the GTVs under investigation. The films were scanned and analysed using in-house developed software for comparison with RT and MC calculated dose distributions in the film planes. For simple cases, RT and MC performed equally well. As the number and proximity of GTVs increased, with complex GTV geometrical distribution and multiple prescription dose levels (MPDLs), the plan gamma pass rate at 3%/1 mm was 36.2% for RT compared to 96.4% for MC. Corresponding RT and MC calculated dose planes were also compared for the failing cases, and similar differences were observed. In conclusion, commissioning of the algorithm with simple and few brain metastases should not be assumed to hold for MBM SRS. The RT algorithm was found to be unsuitable for complex MBM SRS. When commissioning SRS techniques for treating multiple GTVs, the increased demands of proximity and geometrical distribution of GTVs, and the use of MPDLs, should be carefully considered.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"1561-1569"},"PeriodicalIF":2.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13638703/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148537293","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}

{"title":"A novel IoT-aware wearable sensor device for healthcare data management framework using hybrid optimization algorithm.","authors":"Gopalakrishnan B, Purusothaman P","doi":"10.1007/s13246-026-01772-w","DOIUrl":"10.1007/s13246-026-01772-w","url":null,"abstract":"<p><p>The Internet of Things (IoT) has provided a lot of support for patient care by connecting technologies and clinicians through a high-speed network. Data management in IoT healthcare requires a lot of support, since most of the networks are designed for continuous monitoring through the sensor devices, and this leads to challenges in managing sensor data. As the resources in IoT are limited, it is necessary to explore data management strategies so as to achieve an energy-efficient IoT healthcare setup. The classical transmission networks implemented for human-aided applications have various problems, such as limited battery life and resources. Therefore, an effective healthcare data management system using IoT-aided wearable sensor devices is implemented in this work to address the challenges encountered in traditional models. To facilitate robust communication for an IoT-assisted healthcare device, a cloud layer is established, which is used for health data collection and transmission and health monitoring. Here, optimal resource allocation is done using the proposed Hybrid Tasmanian Devil Archery Algorithm (HTDAA), and it is developed from the existing concepts of Tasmanian Devil Optimization (TDO) and Archery Algorithm (AA) to achieve high multi-objective constraint balance and convergence power. This optimal resource allocation process helps in reducing energy consumption in the usual data transmission. For an effective resource allocation process, an objective function is formulated based on the normalized energy ratio value, the buffer memory ratio, and the packet arrival data rate. The proposed HTDAA is established in the IoT setup and used for allocating the optimal channel resources to be involved in the health data transmission, and minimizes the energy requirement. The performance of the suggested HTDAA is estimated by comparing its numerical outcomes with recent optimization techniques. According to the analysis, the packet arrival ratio of HTDAA is 5.6%, 31.7%, 3.3%, and 18.1% enhanced than the recent ESO, SLO, TDO, and AA techniques. Simulations under different cases confirm that the designed HTDAA-based healthcare data management system achieves more robust and energy-efficient solutions than the traditional models.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"1637-1663"},"PeriodicalIF":2.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148563421","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":"Brain stroke detection and classification using deep learning-based transCBAMSegNet and hybrid transformer models.","authors":"Abdullah Şener","doi":"10.1007/s13246-026-01744-0","DOIUrl":"10.1007/s13246-026-01744-0","url":null,"abstract":"<p><p>Stroke is a life-threatening neurological condition that requires rapid assessment to reduce mortality and long-term disability. Accurate lesion segmentation and reliable stroke type classification from brain computed tomography (CT) images are essential to support timely clinical decision-making. In this study, a deep learning-based framework is proposed for automatic stroke lesion segmentation and CT-based stroke type classification. In the segmentation stage, the developed TransCBAMSegNet model achieved an accuracy of 99.60%, a mean intersection over union (mIoU) of 75.98%, and a Dice Similarity Score (DSS) of 75.50%. In the classification stage, a hybrid MaxxViT-ViT-SwinV2 feature fusion strategy achieved an accuracy of 97%, enabling reliable differentiation between acute/hyperacute ischaemic stroke, haemorrhagic stroke, and normal cases. Experimental results show that the proposed multi-transformer fusion approach provides improved performance compared to single-backbone configurations under identical evaluation settings. The framework is designed as a computer-aided CT-based stroke assessment tool and may support early-stage imaging-based decision processes. Overall, the proposed methodology offers a robust and reproducible approach for automated stroke analysis using CT imaging data.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"1333-1354"},"PeriodicalIF":2.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147870066","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":"Evaluation of the time‑of‑flight-enhanced deep learning image reconstruction method in ¹⁸F‑FDG PET/CT for breast cancer imaging.","authors":"Shohei Fukai, Hiromitsu Daisaki, Ryogo Onda, Manami Shiga, Honoka Yoshida, Kazuki Motegi, Naoki Shimada, Kazuaki Takatsu, Masataka Nakagawa, Takashi Terauchi","doi":"10.1007/s13246-026-01742-2","DOIUrl":"10.1007/s13246-026-01742-2","url":null,"abstract":"<p><strong>Background: </strong>Breast cancer is the most frequently diagnosed cancer among women. Accurate diagnosis and effective management rely heavily on high-quality positron emission tomography (PET) imaging. A novel time-of-flight (TOF)-enhanced deep learning reconstruction (DLR) technique has recently been introduced for the Omni Legend (GE Healthcare) PET/CT system. However, its clinical utility in breast cancer imaging has not yet been fully established. This study aims to assess the impact of the DLR method on ¹⁸F-FDG PET/CT imaging in patients with breast cancer.</p><p><strong>Methods: </strong>This retrospective study included 30 female breast cancer patients who underwent ¹⁸F-FDG PET/CT using the Omni Legend system. PET images were reconstructed using the Bayesian penalized likelihood (BPL) method and a DLR method with three TOF enhancement levels: low (L-DLR), medium (M-DLR), and high (H-DLR). Image quality was evaluated using liver noise level (Noise) and lesion signal-to-background ratios (SBR). Percentage changes in these metrics between BPL and each DLR setting were calculated. The four reconstruction methods were compared using the Friedman test with Bonferroni correction. P-values < 0.05 were used to denote statistical significance.</p><p><strong>Results: </strong>Noise values for BPL, L-DLR, M-DLR, and H-DLR were 0.08, 0.06, 0.06, and 0.08, respectively (P < 0.001), whereas SBR values were 3.75, 3.85, 4.09, and 4.39, respectively (P < 0.001). Compared with BPL, L-DLR and M-DLR significantly reduced Noise by 33.20% (P < 0.001) and 22.21% (P < 0.001), respectively, whereas M-DLR and H-DLR significantly improved SBR by 8.96% (P < 0.001) and 16.79% (P < 0.001), respectively.</p><p><strong>Conclusions: </strong>The TOF-enhanced DLR method improves PET image quality metrics compared with the BPL method and has the potential to enhance image quality in ¹⁸F-FDG PET/CT for patients with breast cancer.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"1313-1320"},"PeriodicalIF":2.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147870046","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":"Impact of automatic exposure control on radiation dose and detectability in dual-source and fast kV switching dual-energy CT.","authors":"Kosuke Matsubara, Yoshinori Ogawa, Ryo Yoshikawa, Ayaka Hirosawa, Shoma Chiba, Chatnapa Nuntue, Khajonsak Tantiwetchayanon","doi":"10.1007/s13246-026-01735-1","DOIUrl":"10.1007/s13246-026-01735-1","url":null,"abstract":"<p><p>We evaluated radiation dose and detectability changes with automatic exposure control (AEC) according to object size in dual-source (DS) and fast kV switching (FS) dual-energy computed tomography (DECT). A phantom with five section diameters (16-36 cm) was scanned using different AEC settings (DS: Quality Reference mAs [QRmAs] 300-700; FS: Noise Index [NI] 8-12). Volume CT dose index (CTDI_vol) and detectability index (d') for iodine were measured. Clinical CTDI_vol data from 40 to 80 kg patients undergoing liver dynamic DECT were retrospectively analyzed. In DS-DECT, CTDI_vol increased slightly with section diameter but plateaued at QRmAs 600-700 for 31-36 cm (31 cm: 24.1 mGy; 36 cm: 22.5-22.7 mGy), and d' decreased for larger sections. Clinical CTDI_vol did not differ significantly among weight groups (40-<50 kg: 21.5 mGy; 50-<60 kg: 22.2 mGy; 60-<70 kg: 22.8 mGy; mean; p = 0.13). In FS-DECT, CTDI_vol and d' varied with NI and section diameter: for the 26-cm section, CTDI_vol ranged from 15.0 to 30.8 mGy and d' from 37.5 to 59.0; for 36-cm section, CTDI_vol was 39.9 mGy and d' 24.0-27.8, with smaller variations than single-energy CT (SECT). Clinical CTDI_vol increased with patient weight up to 70 kg (40-<50 kg: 20.3 mGy, 50-<60 kg: 25.8 mGy, 60-<70 kg: 29.2 mGy; mean; p < 0.05). AEC behavior in DECT differs from SECT, causing variations in dose and detectability. Appropriate AEC settings in DECT can achieve image quality comparable to SECT.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"1231-1239"},"PeriodicalIF":2.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147844836","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}