Physical and Engineering Sciences in Medicine最新文献

{"title":"A hybrid Wavelet-EfficientNetV2-Vision transformer framework for multiclass brain tumor MRI classification.","authors":"Oussama Abda, Hilal Naimi, Mohammed Bourennane, Shoffan Saifullah","doi":"10.1007/s13246-026-01787-3","DOIUrl":"10.1007/s13246-026-01787-3","url":null,"abstract":"<p><p>Accurate classification of brain tumors from MRI scans requires models capable of capturing both fine-grained structural details and broader contextual patterns. This study proposes a hybrid Wavelet-EfficientNetV2-Vision Transformer (ViT) framework that integrates multi-resolution frequency enhancement, hierarchical spatial encoding, and global dependency modeling into a unified representation. The Discrete Wavelet Transform (DWT) enriches directional and boundary-aware features, EfficientNetV2 extracts robust localized patterns, and the ViT captures long-range contextual relationships essential for differentiating tumor categories with overlapping visual characteristics. The method was evaluated on the Kaggle-MRI dataset consisting of four classes: glioma, meningioma, pituitary tumor, and no tumor. Experimental results show that the proposed model achieves 98.25% accuracy, with consistent gains in precision, recall, and F1-score compared to standalone CNNs, transformer models, and recent state-of-the-art approaches. Additional analyses, including confusion matrices, ROC-AUC evaluation, and stratified five-fold cross-validation, demonstrate strong class-level stability and generalization. These findings indicate that combining frequency, spatial, and contextual information provides a more discriminative feature space for MRI-based tumor classification. The proposed framework offers a promising direction for developing reliable and high-performance computer-aided diagnosis systems, with future work aimed at multi-center validation and extension to volumetric (3D) modeling.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"1867-1891"},"PeriodicalIF":2.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148763629","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 dual-discriminator conditional generative adversarial network (DDcGAN) approach to glioma grade classification with structural MRI images fusion.","authors":"Amir Khorasani","doi":"10.1007/s13246-026-01788-2","DOIUrl":"10.1007/s13246-026-01788-2","url":null,"abstract":"<p><p>Glioma grade is a critical parameter of clinical management. Recent advances in artificial intelligence (AI)-based image fusion have enabled effective integration of structural MRI (sMRI) sequences for glioma grading. This study investigates the application of AI-driven sMRI fusion techniques to improve glioma grade classification with Relative Signal Contrast (RSC) image-biomarker. The sMRI image-weights were collected from BraTS 2023 data-set. AI-based medical image fusion was performed using a Dual-Discriminator Conditional Generative Adversarial Network (DDcGAN). Entropy, standard deviation, peak signal-to-noise ratio, and the structural similarity index measure were determined for comparing fused image quality. In order to compute the RSC, signal intensity data were extracted from active tumor regions, necrotic core, and normal white matter, as volume of interest, in the sMRI images and the fused image pairs for each participant and compared statistically. The evaluation of the fused image quality demonstrated highly satisfactory results. In this study, RSC change between the High-Grade glioma and Low-Grade glioma groups were statistically significant across all sMRI and fused images, with the exception of T₁-weighted images and the T₁+T₂ fused image. ROC analysis in this study demonstrated that the T₁Gd+FLAIR fused image exhibited the highest performance for glioma grading, with an AUC of 0.91, a sensitivity of 0.90, and a specificity of 0.72. DDcGAN-based image fusion demonstrates strong potential for improving glioma grade determination. Among structural MRI sequences, fusion of T₁Gd+ FLAIR provides the most discriminative information, supporting the use of RSC calculated from fused images as an imaging-biomarker for glioma grade classification.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"1893-1908"},"PeriodicalIF":2.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148820081","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":"Exploration of overlap volumes-based IMRT Rapidplan for cervical cancer patients with the aim of OARs sparing.","authors":"Minfeng Huang, Changfei Gong, Biaoshui Liu, Yili Wang, Jinghua Zhong, Min Wang, Jun Chi, Li Xinyuan, Ruilian Xie, Chunbo Tang","doi":"10.1007/s13246-026-01732-4","DOIUrl":"10.1007/s13246-026-01732-4","url":null,"abstract":"","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"1191-1205"},"PeriodicalIF":2.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147786008","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":"Dosimetric impact of knowledge-based automated planning using HyperArc for angiosarcoma of the scalp.","authors":"Shoki Inui, Natsuo Tomita, Taiki Takaoka, Yoshihiro Ueda, Shingo Ohira, Yuya Nitta, Sayaka Kihara, Takahiro Tsuchiya, Yutaka Takahashi, Teiji Nishio, Masahiko Koizumi, Koji Konishi","doi":"10.1007/s13246-026-01780-w","DOIUrl":"10.1007/s13246-026-01780-w","url":null,"abstract":"<p><p>This study aimed to automate and standardize treatment planning by comparing the dosimetric performance of conventional volumetric modulated arc therapy (C-VMAT) with that of HyperArc optimized using the knowledge-based RapidPlan model trained with the HyperArc plan (RP-HA) for total scalp irradiation (TSI) in the treatment of angiosarcoma of the scalp (AS). Additionally, this study compared the dosimetric performance of RP-HA with that of non-coplanar VMAT optimized using the same model (RP-NC-VMAT). From 40 patients with AS who had undergone TSI, 20 patients were selected for HyperArc planning and RapidPlan model training. The remaining 20 patients had treatment plans generated using three different methods (C-VMAT, RP-NC-VMAT, and RP-HA). The prescription doses were 70 and 56 Gy in 35 fractions of the target volumes, including gross tumor and whole scalp, respectively, using the simultaneous integrated boost technique. The dose distribution, dosimetric parameters, and dosimetric accuracy of each treatment plan were evaluated and compared between methods. None of the three methods exceeded the acceptable limits for all constraint parameters of the target and organs at risk. The RP-HA plan provided a significantly lower mean brain dose (10.96 ± 1.54 Gy) than the C-VMAT and RP-NC-VMAT plans (18.06 ± 2.17 Gy and 12.36 ± 2.12 Gy). The dose received by 0.1 cm³ of the hippocampus was significantly lower in the RP-NC-VMAT and RP-HA plans than in the C-VMAT plan. The RapidPlan model trained with the HyperArc plan can be helpful in automating and standardizing treatment planning in TSI for AS.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"1767-1776"},"PeriodicalIF":2.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148537253","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":"Kullback-Leibler divergence in feature selection: a methodology for improved detection of heart valve disorders.","authors":"V H Preetha, C V Raghu","doi":"10.1007/s13246-026-01737-z","DOIUrl":"10.1007/s13246-026-01737-z","url":null,"abstract":"<p><p>Dimensionality reduction is crucial for the effective management of high-dimensional datasets, particularly in the healthcare industry. Feature selection identifies the most relevant attributes, reducing computational overhead and ensuring robust performance, especially in resource-constrained environments. This study introduces a Kullback-Leibler Divergence (KLD)-based feature selection method for heart sound analysis to diagnose valvular heart diseases. Mel-frequency cepstral coefficients and mel spectrograms were extracted from the dataset as input features. The KLD was applied to identify the most informative features, which were subsequently validated using various classifiers. This approach resulted in an accuracy of 99% in diagnosing five distinct heart sounds, outperforming classifiers using the full feature set. The method prioritizes critical features, leading to improved performance across all evaluated classifiers. This endeavor also aims to classify heart sounds on an embedded platform, enabling the efficient analysis and accurate diagnosis of cardiovascular conditions. These findings highlight the potential of KLD-based feature selection for the real-time detection of heart valve disorders. By reducing the processing overhead while preserving classification accuracy, this approach supports the development of efficient, cost-effective edge-based tools, ultimately improving diagnostic precision and healthcare resource efficiency.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"1251-1265"},"PeriodicalIF":2.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147960368","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":"SPECT hybrid approach combining conventional and deep features for early detection of Parkinson's disease.","authors":"Jihad Boucherouite, Atman Jbari, Abdelilah Jilbab","doi":"10.1007/s13246-026-01739-x","DOIUrl":"10.1007/s13246-026-01739-x","url":null,"abstract":"<p><p>The early diagnosis of Parkinson's disease (PD) using SPECT imaging continues to be challenging due to the subtle dopaminergic deficits present in the early stages of the disease. This study proposes a novel hybrid approach combining conventional and deep learning features to improve PD classification, and applies it to reclassify scans without evidence of dopaminergic deficit (SWEDD) cases. We used SPECT images from early PD patients and healthy controls (HC) and extracted SBR metrics, morphometric, and deep learning features. Our multi-stage feature selection pipeline employed near-zero variance filtering, ANOVA F-test analysis, correlation-based feature elimination, and Random Forest importance scoring. We evaluated multiple machine learning algorithms and selected Linear Discriminant Analysis as the optimal classifier, then applied this model to reclassify 79 SWEDD cases. Feature selection reduced 79 significant features to 15 optimal features: 1 SBR metric (6.7%), 7 morphometric (46.7%), and 7 deep features (46.7%). The hybrid Linear Discriminant model achieved the best performance, outperforming individual feature approaches with 97.40% test accuracy, 96.25% sensitivity, 98.65% specificity, and 99.59% AUC. Statistical analysis revealed morphometric features had the highest mean importance (0.0699 ± 0.0539), followed by deep (0.0400 ± 0.0570) and SBR features (0.0206 ± 0.019). SWEDD reclassification identified 5 cases (6.3%) with imaging patterns consistent with early PD, while 74 cases (93.7%) maintained HC characteristics. This study presents a proof-of-concept demonstration of the effectiveness of integrating conventional measures with deep learning techniques for improving the early diagnosis of PD, while offering new insights into SWEDD case reclassification.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"1267-1283"},"PeriodicalIF":2.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147876073","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 an anthropomorphic ultrasound face phantom for training in cosmetic and aesthetic procedures.","authors":"Olga Vlasova, Denis Leonov, Anastasia Nasibullina, Yulia Bulgakova, Veronika Grebennikova, Marina Sayfutdinova, Maria Kodenko, Anna Borde, Ekaterina Privalova, Zhuhuang Zhou, José Francisco Silva Costa-Júnior, Olga Omelianskaya, Yuriy Vasilev","doi":"10.1007/s13246-026-01763-x","DOIUrl":"10.1007/s13246-026-01763-x","url":null,"abstract":"<p><p>Ultrasound face phantoms are essential tools for cosmetic procedures, providing a realistic and anatomically accurate representation of the human face for training and practice. This research aims to create an ultrasound face phantom to simulate the skin, muscles, arteries and other structures of the face, allowing medical professionals to accurately assess and measure the impact of various treatments and aesthetic procedures using ultrasound imaging. The phantom was made using polyvinyl chloride mixed with additives. The ingredients were chosen to accurately replicate the physical and ultrasound properties of human tissues. To ensure alignment with the biomechanical and ultrasound characteristics of human facial tissues, compressive, tensile, and acoustic measurements were conducted. The ultrasound evaluation of the designed phantom was performed using a carrier frequency of up to 20 MHz. The phantom was 155 × 117 × 120 mm³ in size, weighed 1.1 kg and consisted of the models of a skull, muscle and soft tissues, salivary gland, lymph nodules, and blood vessels. The ultrasound images of the phantom closely mimicked those of the human face, allowing for accurate and realistic simulations. The tissue-mimicking materials showed a Young's modulus ranging from 31 to 35 kPa through compression, a Young's modulus of 80 to 170 kPa through tension, an ultrasound speed of 1440 to 1481 m/s, and an attenuation coefficient of 0.21 to 0.58 dB/cm/MHz, which were consistent with the properties of subcutaneous tissues. The designed face phantom allows for more accurate and realistic training in ultrasound-guided cosmetology. This study successfully developed a highly realistic ultrasound facial phantom with precise mechanical and acoustic properties. These phantoms can serve as a practical tool for training specialists in both diagnostic and surgical procedures, enabling simulations of injections, biopsies, and other minimally invasive interventions with accuracy close to clinical conditions.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"1535-1550"},"PeriodicalIF":2.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148580788","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":"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/s13246-026-01773-9","DOIUrl":"10.1007/s13246-026-01773-9","url":null,"abstract":"<p><p>Radiochromic films are widely used in radiotherapy dosimetry for their high spatial resolution and near-water-equivalence. Nonetheless, these films are frequently purchased in bulk, leading clinical departments to accumulate stock beyond the manufacturer's expiration date. Assessing the dosimetric performance of expired films may confer economic and environmental advantages. This work evaluated whether expired EBT-XD radiochromic films remain suitable for specific radiotherapy dosimetry applications. Two expired batches were compared with a non-expired batch. Dose-response curves were generated using a 6 MV photon beam from a clinical linear accelerator. The films were tested for small-field output factor measurements and patient-specific quality assurance (PSQA) in volumetric-modulated arc therapy (VMAT) and stereotactic radiosurgery (SRS), employing gamma-index analysis. Results indicated that expired films exhibit reduced sensitivity relative to unexpired films, particularly at lower dose levels. However, acceptable dosimetric agreement with unexpired films was observed for small-field output factors and high-dose SRS PSQA cases, provided appropriate recalibration was applied. More pronounced discrepancies emerged in low-dose VMAT PSQA measurements, where diminished film sensitivity may have influenced the film's response. These findings suggest that expired EBT-XD radiochromic films may still provide useful dosimetric information as relative dosimeters for selected radiotherapy measurements, especially when measurements fall within the film's recommended dose range, and films are properly stored and recalibrated.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"1665-1677"},"PeriodicalIF":2.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148563415","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":"Improving the classification of cardiovascular diseases using statistical features obtained from empirical mode decomposition.","authors":"S Daphin Lilda, R Jayaparvathy, S Pravin Kumar, N Vedachalam","doi":"10.1007/s13246-026-01760-0","DOIUrl":"10.1007/s13246-026-01760-0","url":null,"abstract":"<p><p>Globally, cardiovascular diseases (CVDs) constitute a leading cause of death. Significant reductions in mortality are possible with early detection and treatment of CVDs. The electrocardiogram (ECG) is an easy-to-understand, non-invasive technique for assessing the state of the heart. A specific CVD can be determined by a slight deviation in the ECG, which is difficult and time-consuming to diagnose manually. This work suggests an empirical mode decomposition (EMD)-based approach together with time and frequency series feature extraction for the automated identification of CVDs. Five CVDs are taken into consideration in this work: myocardial infarction (MI), hypertrophic cardiomyopathy (HCM), dilated cardiomyopathy (DCM), bundle branch block (BBB) and coronary artery disease (CAD). The decomposition of signals using EMD yields amplitude- and frequency-modulated waves called intrinsic mode functions (IMFs). Temporal and spectral features are extracted from the obtained IMFs. These features are ranked using the one-way anova test, and the ranked features are fed as inputs to the classification model. When combined with eleven features, the extreme gradient boosting classifier allows the suggested approach to attain a maximum classification accuracy of 99.56%. On the proposed database and 92.4% on MIT-BIH database, demonstrating strong generalizability. Clinical validation on 6,55,659 beats from RELA Hospital yielded 81.3% accuracy, highlighting the challenges of real-world deployment.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"1495-1509"},"PeriodicalIF":2.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148438247","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":"Deep learning for developmental dysplasia of the hip: comparative classification strategies for ultrasound imaging with heterogeneous image quality.","authors":"Shota Ichikawa, Yohan Kondo","doi":"10.1007/s13246-026-01770-y","DOIUrl":"10.1007/s13246-026-01770-y","url":null,"abstract":"<p><p>Computer-assisted diagnostic tools may help improve the consistency and reliability of ultrasonographic screening for developmental dysplasia of the hip (DDH). This study aimed to compare preprocessing strategies for convolutional neural network (CNN)-based classification of infant hip ultrasound images under heterogeneous image quality conditions. We evaluated six approaches for classifying infant hip ultrasound images as normal or abnormal: original-image CNN classification, CycleGAN-based domain translation in two directions, DeepLabV3-Plus-based segmentation preprocessing, and two combined approaches using CycleGAN followed by DeepLabV3-Plus. Each approach was independently trained and evaluated ten times using ninefold cross-validation, and performance was assessed using the area under the receiver operating characteristic curve (AUC). The baseline approach using original images achieved a mean AUC of 0.724 (95% confidence interval [CI]: 0.711-0.737). CycleGAN-based domain translation did not improve performance, with mean AUCs of 0.719 (95% CI: 0.703-0.736) for Dataset A-to-B translation and 0.679 (95% CI: 0.658-0.700) for Dataset B-to-A translation. DeepLabV3-Plus-based segmentation preprocessing showed the numerically highest mean AUC of 0.791 (95% CI: 0.773-0.809), while the combined approaches achieved mean AUCs of 0.780 and 0.783. Pairwise comparisons with Bonferroni correction showed no statistically significant differences between approaches (all adjusted p-values > 0.05). These exploratory findings suggest that segmentation-based preprocessing may be a promising strategy for CNN-based classification of infant hip ultrasound images under heterogeneous imaging conditions, whereas CycleGAN-based domain translation did not provide a measurable benefit in this setting. Further validation using larger multicenter datasets is required before clinical applicability can be established.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"1611-1620"},"PeriodicalIF":2.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148438220","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}