Physical and Engineering Sciences in Medicine最新文献

{"title":"Deep learning based depth of anaesthesia monitoring using EEG: a 4-layer CNN model with PSD and BSR correlation features.","authors":"M S Thasneem, K R Remesh Babu","doi":"10.1007/s13246-026-01753-z","DOIUrl":"10.1007/s13246-026-01753-z","url":null,"abstract":"<p><p>Monitoring the depth of anaesthesia (DoA) through electroencephalogram (EEG) analysis plays a major role in maintaining patient safety and guiding optimal anaesthetic delivery during surgery. In this study, a convolutional neural network (CNN) framework was designed to classify DoA into three clinically relevant states: Deep Anaesthesia, adequate anaesthesia, and awake. EEG recordings were transformed into spectrograms, enabling the CNN to capture temporal-spectral representations. Key features such as power spectral density (PSD) and the correlation between PSD and burst suppression ratio (BSR) were incorporated to enhance discriminability across states. The model was evaluated on three representative patient cases, achieving accuracies of 93%, 84%, and 73%, respectively. Detailed performance analysis using confusion matrices and metrics such as Precision, Recall, and F1-score demonstrated strong generalization in detecting stable states (Deep Anaesthesia and awake) but limited sensitivity in transitional states (adequate/light anaesthesia) due to overlapping spectral signatures. These findings highlight both the promise and limitations of CNN-based DoA monitoring.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"1413-1432"},"PeriodicalIF":2.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148200745","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":"Complementary roles of GPU-accelerated Monte Carlo and ArcCHECK in TomoTherapy quality assurance.","authors":"Panxia Wu, Wenheng Zheng, Longfei Xu, XingXing Yuan, Changfei Gong, Changwei Luo, Junming Jian, Shenggou Ding, Yun Zhang","doi":"10.1007/s13246-026-01750-2","DOIUrl":"10.1007/s13246-026-01750-2","url":null,"abstract":"<p><p>The complex dose delivery mechanisms of TomoTherapy (TOMO) demand rigorous patient-specific quality assurance (PSQA). This study systematically evaluates the relationship between ArcCHECK measurements and GPU-accelerated Monte Carlo (GPU-MC) calculations for nasopharyngeal carcinoma (NPC) TOMO plans across multiple gamma criteria, aiming to delineate their respective strengths and inform an optimized verification strategy. A retrospective analysis was conducted on 317 TOMO plans for NPC, each optimized using the Accuray Precision Treatment Planning System. Patient-specific dose verification was performed using ArcCHECK measurements and independent MC calculations implemented through PlanQA. Gamma passing rates (GPRs) were evaluated under nine different conditions, including both same-criterion and cross-criterion comparisons. To assess differences, agreement, and correlations between methods, statistical analyses were conducted using the Wilcoxon signed-rank test, Bland-Altman analysis, and Spearman correlation. Under identical Gamma criteria, there was no statistically significant difference in GPR between ArcCHECK and MC. However, cross-criterion comparisons revealed marked discrepancies, highlighting the criterion-dependent nature of GPR outcomes. Lenient standards typically exhibit good consistency and relatively minor deviations. Furthermore, the correlations among all combinations of these standards can be considered negligible. The comparable performance of GPU-MC and ArcCHECK under conventional criteria (3%/3 mm, 3%/2 mm) validates ArcCHECK's established role in verifying delivery fidelity. Crucially, under the stringent 2%/2 mm criterion where ArcCHECK passing rates decline, MC provides critical diagnostic power to differentiate between discrepancies originating from the dose calculation algorithm and those arising from the physical delivery process. For TOMO PSQA, GPU-MC and ArcCHECK are complementary. An integrated approach leveraging both methods is therefore recommended.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"1383-1391"},"PeriodicalIF":2.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148200522","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":"MRI-based brain tumor detection through an explainable EfficientNetV2 and MLP-mixer attention architecture.","authors":"Mustafa Yurdakul, Şakir Taşdemir","doi":"10.1007/s13246-026-01728-0","DOIUrl":"10.1007/s13246-026-01728-0","url":null,"abstract":"","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"1125-1143"},"PeriodicalIF":2.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147628819","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":"CNN models in time-frequency domain for identification of motor imagery tasks from EEG signals.","authors":"V Srimadumathi, M Ramasubba Reddy","doi":"10.1007/s13246-026-01758-8","DOIUrl":"10.1007/s13246-026-01758-8","url":null,"abstract":"<p><p>The Motor imagery (MI) based brain computer interface (BCI) system provides a way for the people suffering from motor impairments to communicate to the external world. This work proposes compact convolutional neural network (CNN) models with single convolutional layer, for effectively classifying the left and right hand MI tasks using the EEG data from only two channels. The Complex Morlet Wavelets (CMW) are used here to extract high-resolution time and frequency domain features from MI EEG signal. These time-frequency representations (TFR) serve as inputs to three proposed CNN models namely the time domain CNN (TD-CNN), the frequency domain CNN (FD-CNN) and the time-frequency domain CNN (TF-CNN) models, which perform a convolution along the time, frequency and time-frequency domain features of the data respectively. The developed models have been evaluated on the BCI Competition 4 dataset 2a using the subject-dependent and subject-independent validation strategies. The TF-CNN model has outperformed the TD-CNN and FD-CNN models, by giving a classification accuracy of 85.83% and 77.6% for the subject dependent and independent validations respectively. The results show that the proposed models have given a better performance than the state-of-the art methods and the existing CNN models with complex network architectures.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"1469-1482"},"PeriodicalIF":2.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148406485","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":"Employing machine learning techniques for non-invasive blood pressure classification using photoplethysmography signals.","authors":"Hanieh Mohammadi, Bahram Tarvirdizadeh, Khalil Alipour, Mohammad Ghamari","doi":"10.1007/s13246-026-01782-8","DOIUrl":"10.1007/s13246-026-01782-8","url":null,"abstract":"<p><p>Regulating blood pressure (BP) effectively is vital for maintaining health and ensuring survival, yet elevation and fluctuation in BP can lead to significant health threats. Traditional methods for measuring BP, such as cuff-based and invasive procedures, can be cumbersome and do not allow for continuous measurements. In response to these challenges, our research focuses on enhancing non-invasive BP monitoring by leveraging photoplethysmography (PPG) signals in conjunction with sophisticated machine learning (ML) techniques. Our research analyzed PPG data from a diverse cohort of subjects, ranging in age from 21 to 86, including both individuals in good health and those with underlying health conditions. The analysis involved rigorous preprocessing and feature extraction processes. To enhance computational efficiency and mitigate the risk of overfitting, we applied four distinct feature selection strategies. The features identified by each method were then utilized in five ML classification models using k-fold cross validation to differentiate BP across four categories. Our findings indicate that the ensemble-based extra trees classifier (ETC) model, combined with the SelectFromModel feature selection approach, achieved remarkable accuracy of 91.13% on the test dataset. The F1 scores for the four BP categories were 93.94%, 89.31%, 88.25%, and 88.33%, respectively. Given the imbalance in dataset, we adopted two strategies for train data balancing in the second phase of our study, which boosted the test accuracy to 93.25%. The improved F1 scores for the four BP categories reached 95.34%, 90.80%, 94%, and 91.11%, respectively, underscoring the efficacy of our method in BP classification and its potential for broader application.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"1793-1815"},"PeriodicalIF":2.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148680531","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 the current research landscape academic and scholarly journals have outlived their usefulness.","authors":"Daniel Manrique-Castano, Jamie Trapp, Clive Baldock","doi":"10.1007/s13246-026-01806-3","DOIUrl":"10.1007/s13246-026-01806-3","url":null,"abstract":"","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"1119-1124"},"PeriodicalIF":2.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149082333","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":"Optimization of a Q.Clear PET image reconstruction based on bayesian optimization in oncology and neurology applications.","authors":"Qariemah Azahar, Hazlin Hashim, Khadijah Abdul Hamid, Lyu Xin, Syahir Mansor","doi":"10.1007/s13246-026-01776-6","DOIUrl":"10.1007/s13246-026-01776-6","url":null,"abstract":"<p><p>Bayesian Penalized Likelihood (BPL) reconstruction can improve image quality and quantitative accuracy in PET/CT imaging. This study aimed to determine the optimal Beta (β)-factor in Q.Clear reconstruction using Bayesian Optimization (BO) through phantoms and clinical evaluation. NEMA IQ and Hoffman Brain phantoms, along with clinical PET/CT images, were analyzed. Phantom images were reconstructed using β-factors (50-1000) across different acquisition times. Recovery coefficient (RC%) and contrast-to-noise ratio (CNR) were calculated. Clinical evaluation included one neurology and one oncology case as verification data, reconstructed using OSEM and Q.Clear at β-factors (100-1000), with full and reduced reconstruction times (neurology: 8 and 2 min; oncology: 15 and 7 min), respectively. Visual assessment was independently performed by two nuclear medicine physicians, and inter-rater agreement was analyzed using Krippendorff's alpha. In the NEMA IQ phantom, increasing β-factor resulted in decreased RC% but increased CNR. In the Hoffman Brain phantom, cortical regions showed stable RC% from mid to high β-factors, whereas subcortical regions were more sensitive, showing reduced RC%. CNR improved with higher β-factors and longer acquisition times. BO analysis indicates that smaller spheres achieved optimal performance at lower β-factors and longer acquisition times, while larger spheres tolerated higher β-factors (600-800). Optimal β-factors for cortical and subcortical brain regions were (400-600) and (100-300), respectively. Clinically, the highest scores were observed for β-factors (300-1000) in oncology, and (500-900) in neurology. Higher β-factors improved RC% and CNR stability in phantom studies. BO identified (500-900) as the optimal β-factors, consistent with clinical findings demonstrating high visual scores and strong inter-rater agreement, supporting its reliability of BO-optimized β-factors for PET/CT reconstruction.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"1719-1731"},"PeriodicalIF":2.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148438207","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 surface-guided radiotherapy-based deep inspiration breath hold and continuous positive airway pressure techniques in left-sided breast cancer: dosimetric and workflow analysis.","authors":"Su Chul Han, Jason Joon Bock Lee, Jin Dong Cho, Il Sun Jeong, Heerim Nam, Hyebin Lee","doi":"10.1007/s13246-026-01733-3","DOIUrl":"10.1007/s13246-026-01733-3","url":null,"abstract":"","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"1207-1216"},"PeriodicalIF":2.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147786050","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":"Development of a scientific version TPS workflow for BNCT dosimetry based on DICOM and Monte Carlo engine.","authors":"Yinan Zhu, Zuokang Lin, Guanchao Wu, Zhiyuan Lin, Zijian Zhang, Ye Dai, Haiyan Yu, Xiaohan Yu","doi":"10.1007/s13246-026-01743-1","DOIUrl":"10.1007/s13246-026-01743-1","url":null,"abstract":"<p><p>Boron Neutron Capture Therapy (BNCT) is a binary targeted radiotherapy modality that requires accurate dose calculation and treatment plan optimization. In this work, we proposed a scientific version Treatment Planning System (TPS) for BNCT. The proposed TPS is a workflow for research purposes, aiming at dosimetric analysis and plan formulation and not certified for clinical use. The workflow integrates DICOM based voxel phantom reconstruction, automated generation of Monte Carlo program input files, and post-processing of BNCT dose components to enable comparative evaluation of candidate epithermal neutron spectra. Boron pharmacokinetics were incorporated using published concentration to time curves following intravenous bolus administration of Borono-Phenyl-Alanine (BPA). Compound Biological Effectiveness (CBE) factors of BPA were further applied to compute biologically equivalent doses for the tumor, normal brain tissue, and scalp. Two representative intracranial targets were selected to investigate dosimetric differences among four therapeutic beam spectra shaped by different moderator materials and thicknesses. The results indicate that the harder spectrum produced by 45 cm FLUENTAL moderation improves treatment efficiency for deep-seated tumors, whereas the softer spectrum produced by 45 cm MgF₂ moderation provides improved dose selectivity for shallow tumors. Overall, these findings demonstrate the feasibility of the proposed scientific version TPS workflow as a research tool for BNCT dosimetry studies.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"1321-1331"},"PeriodicalIF":2.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147870064","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 generative adversarial network-based postprocessing super-resolution for lumbar spine magnetic resonance imaging.","authors":"Yasuo Takatsu, Kazuki Takano, Shohei Harada, Hayato Takeda, Masafumi Nakamura, Akiyoshi Iwase, Atsushi Ikemoto, Tosiaki Miyati, Soma Kumasaka","doi":"10.1007/s13246-026-01768-6","DOIUrl":"10.1007/s13246-026-01768-6","url":null,"abstract":"<p><p>This study evaluated the feasibility of generative adversarial network (GAN)-based postprocessing super-resolution for T2-weighted lumbar spine magnetic resonance imaging (MRI) using both objective resolution metrics and perceptual assessment. Sagittal lumbar spine MRI datasets from healthy volunteers were analyzed. An enhanced super-resolution GAN (ESRGAN) was trained on downsampled images, while zero-filling, bicubic, and bilinear interpolation, as well as enhanced deep residual networks for single image super-resolution (EDSR), were used as comparators. Image quality was assessed by comparing upscaled images from 256 × 256 acquisitions with corresponding 512 × 512 reference images, using full width at half maximum (FWHM) and normalized integrated power spectrum (NIPS), along with similarity metrics including structural similarity index, peak signal-to-noise ratio, and root mean square error. Subjective image quality was evaluated using a ranking method. An additional analysis using 320 × 320 and 640 × 640 image pairs was conducted to assess consistency across resolution settings. Statistical comparisons were performed using the Friedman test with Bonferroni correction. ESRGAN showed no significant differences from the original high-resolution images in FWHM and NIPS, whereas interpolation methods and EDSR demonstrated inferior performance (P < 0.05). Although interpolation methods achieved higher scores in pixel-wise metrics, ESRGAN obtained the highest subjective ratings and interrater agreement. These findings indicate that ESRGAN better restores high-frequency structural information not captured by conventional similarity metrics. GAN-based postprocessing super-resolution may improve image quality in lumbar spine MRI and warrants further investigation of its clinical impact.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"1579-1594"},"PeriodicalIF":2.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148622191","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}