Physical and Engineering Sciences in Medicine最新文献

筛选
英文 中文
How much data do you need? An analysis of pelvic multi-organ segmentation in a limited data context. 您需要多少数据?对有限数据背景下骨盆多器官分割的分析。
IF 2.4 4区 医学
Physical and Engineering Sciences in Medicine Pub Date : 2025-03-01 Epub Date: 2025-03-11 DOI: 10.1007/s13246-024-01514-w
Febrio Lunardo, Laura Baker, Alex Tan, John Baines, Timothy Squire, Jason A Dowling, Mostafa Rahimi Azghadi, Ashley G Gillman
{"title":"How much data do you need? An analysis of pelvic multi-organ segmentation in a limited data context.","authors":"Febrio Lunardo, Laura Baker, Alex Tan, John Baines, Timothy Squire, Jason A Dowling, Mostafa Rahimi Azghadi, Ashley G Gillman","doi":"10.1007/s13246-024-01514-w","DOIUrl":"10.1007/s13246-024-01514-w","url":null,"abstract":"<p><p>Training deep learning models generally requires large, costly datasets which can limit their application towards in-house segmentation tasks. This study investigates the trade-off in dataset size within the context of pelvic multi-organ MR segmentation where we evaluate the performance of nnU-Net, a well-known segmentation model, under conditions of limited domain and data availability. 12 participants undergoing treatment on an Elekta Unity were recruited, acquiring 58 MR images, with 4 participants (12 images) withheld for testing. Prostate, seminal vesicles (SV), bladder and rectum were contoured in each image by a radiation oncologist. Seven models were trained on progressively smaller subsets of the training dataset, simulating a limited dataset setting. To investigate the efficacy of data augmentation, another set of identical models were trained without augmentation. The performance of the networks was evaluated via the Dice Similarity Coefficient, mean surface distance, and 95% Hausdorff distance metrics. When trained with entire training dataset (46 images), the model achieved a mean Dice coefficient of 0.903 (Prostate), 0.851 (SV), 0.884 (Rectum) and 0.967 (Bladder). Segmentation performance remained stable when the number of training sets was > 12 images from 4 participants, but rapidly dropped in smaller data subsets. Data augmentation was found to be influential across all dataset sizes, but especially in very small datasets. This study demonstrated nnU-Net's proficiency in performing male pelvic multi-organ segmentation under a limited domain, a single scanner, and under limited data constraints. We found that the performance degradation was often modest until a threshold is reached (12 images), below which it dropped significantly. Data augmentation improved performance across all data sizes, but especially for very small datasets. We conclude that nnU-Net's low data requirement can be advantageous for in-house cases with consistent protocol and scarce data availability.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"409-419"},"PeriodicalIF":2.4,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11996946/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143606662","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
SchizoLMNet: a modified lightweight MobileNetV2- architecture for automated schizophrenia detection using EEG-derived spectrograms. SchizoLMNet:一种改进的轻量级MobileNetV2架构,用于使用脑电图衍生谱图自动检测精神分裂症。
IF 2.4 4区 医学
Physical and Engineering Sciences in Medicine Pub Date : 2025-03-01 Epub Date: 2025-01-06 DOI: 10.1007/s13246-024-01512-y
A Prabhakara Rao, Rakesh Ranjan, Bikash Chandra Sahana, G Prasanna Kumar
{"title":"SchizoLMNet: a modified lightweight MobileNetV2- architecture for automated schizophrenia detection using EEG-derived spectrograms.","authors":"A Prabhakara Rao, Rakesh Ranjan, Bikash Chandra Sahana, G Prasanna Kumar","doi":"10.1007/s13246-024-01512-y","DOIUrl":"10.1007/s13246-024-01512-y","url":null,"abstract":"<p><p>Schizophrenia (SZ) is a chronic neuropsychiatric disorder characterized by disturbances in cognitive, perceptual, social, emotional, and behavioral functions. The conventional SZ diagnosis relies on subjective assessments of individuals by psychiatrists, which can result in bias, prolonged procedures, and potentially false diagnoses. This emphasizes the crucial need for early detection and treatment of SZ to provide timely support and minimize long-term impacts. Utilizing the ability of electroencephalogram (EEG) signals to capture brain activity dynamics, this article introduces a novel lightweight modified MobileNetV2- architecture (SchizoLMNet) for efficiently diagnosing SZ using spectrogram images derived from selected EEG channel data. The proposed methodology involves preprocessing of raw EEG data of 81 subjects collected from Kaggle data repository. Short-time Fourier transform (STFT) is applied to transform pre-processed EEG signals into spectrogram images followed by data augmentation. Further, the generated images are subjected to deep learning (DL) models to perform the binary classification task. Utilizing the proposed model, it achieved accuracies of 98.17%, 97.03%, and 95.55% for SZ versus healthy classification in hold-out, subject independent testing, and subject-dependent testing respectively. The SchizoLMNet model demonstrates superior performance compared to various pretrained DL models and state-of-the-art techniques. The proposed framework will be further translated into real-time clinical settings through a mobile edge computing device. This innovative approach will serve as a bridge between medical staff and patients, facilitating intelligent communication and assisting in effective SZ management.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"285-299"},"PeriodicalIF":2.4,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142933191","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
Application of dielectric properties for identification of normal and malignant gastrointestinal tumors and lymph nodes ex vivo. 应用介电特性识别体内正常和恶性胃肠道肿瘤及淋巴结。
IF 2.4 4区 医学
Physical and Engineering Sciences in Medicine Pub Date : 2025-03-01 Epub Date: 2024-11-26 DOI: 10.1007/s13246-024-01490-1
Xi Rao, Qianyun Chen, Lishan Ding, Noman Shahid, Sidra Wafa, Qiang Huang, Enming Qiu, Xi Zhang, Songsheng Wang, Xueer Xia, Shuai Han, Haijin Chen, Zhou Li
{"title":"Application of dielectric properties for identification of normal and malignant gastrointestinal tumors and lymph nodes ex vivo.","authors":"Xi Rao, Qianyun Chen, Lishan Ding, Noman Shahid, Sidra Wafa, Qiang Huang, Enming Qiu, Xi Zhang, Songsheng Wang, Xueer Xia, Shuai Han, Haijin Chen, Zhou Li","doi":"10.1007/s13246-024-01490-1","DOIUrl":"10.1007/s13246-024-01490-1","url":null,"abstract":"<p><p>A need exists for a quick, simple method to accurately assess resection margins and lymph node metastases in gastrointestinal cancer surgeries. We aimed to develop a real-time, non-destructive technique to differentiate between normal and cancerous tissues using dielectric properties. Dielectric properties of tissues from 50 gastric and 120 colorectal cancer patients were measured during surgery using an open-ended coaxial probe, spanning frequencies from 10 MHz to 4 GHz. Lymph nodes were classified based on pathology into metastatic and non-metastatic, and tissues were divided into cancerous and normal, the latter being 3 cm from the cancer edge. Statistically significant differences in dielectric properties were found between metastatic and non-metastatic lymph nodes (P < 0.05), and between normal and malignant tissues. Metastatic lymph nodes showed higher dielectric permittivity and conductivity across the frequency range, with no significant difference between gastric and colorectal cancers. The coaxial probe method distinguishes between metastatic and non-metastatic lymph nodes by their dielectric properties within 10-4000 MHz, offering a potential tool for real-time identification of malignant tissues during surgery, despite not identifying the cancer type.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"75-85"},"PeriodicalIF":2.4,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142717472","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
Memory enhancement by transcranial radiofrequency wave treatment occurs without appreciably increasing brain temperature. 经颅射频波治疗的记忆增强没有明显增加脑温度。
IF 2.4 4区 医学
Physical and Engineering Sciences in Medicine Pub Date : 2025-03-01 Epub Date: 2025-01-06 DOI: 10.1007/s13246-024-01508-8
Rob Baranowski, John Amschler, Dave Wittwer, Gary W Arendash
{"title":"Memory enhancement by transcranial radiofrequency wave treatment occurs without appreciably increasing brain temperature.","authors":"Rob Baranowski, John Amschler, Dave Wittwer, Gary W Arendash","doi":"10.1007/s13246-024-01508-8","DOIUrl":"10.1007/s13246-024-01508-8","url":null,"abstract":"<p><p>We have previously shown in small studies that full brain Transcranial Radiofrequency Wave Treatment (TRFT) to subjects with Alzheimer's Disease could stop and reverse their cognitive decline. An 8-emitter head device, the \"MemorEM\", was used in these studies to provide TRFT at 915 MHz frequency and power level of 1.6 W/kg Specific Absorption Rate (SAR) during daily 1-hour treatments. Although no deleterious side effects during up to 2.5 years of treatment were reported, it is important to rule out the possibility that brain heating will occur during TRFT in humans at a higher power level of 4.0 W/kg SAR, which is anticipated for future clinical testing in order to increase treatment intensity/efficacy to deep sub-cortical areas. To examine if brain heating occurs during a single 1-hour treatment at 4 W/kg SAR, a hollow human head phantom filled with brain-analogous gel and with an attached MemorEM head device was utilized. Brain temperatures were taken at 64 specific coordinates within the brain gel before and immediately following one-hour of TRFT. Results revealed none of the 64 sites having a temperature increase after TRFT of 1 °C or more. Indeed, 45 of the 64 sites exhibited a temperature rise of less than 0.5 °C, with just three sites exhibiting an increase between 0.75 and 0.9 °C. These results demonstrate that TRFT in a human head phantom that mimics the electromagnetic properties of the human head, does not appreciably increase brain temperature (i.e., is non-thermal) at 915 MHz frequency and 4 W/kg SAR power level. Thus, TRFT would appear to be safe at 4 W/kg for long-term daily treatments.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"239-250"},"PeriodicalIF":2.4,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142933189","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
Use of a virtual phantom to assess the capability of a treatment planning system to perform magnetic resonance image distortion correction. 使用虚拟幻影来评估治疗计划系统执行磁共振图像失真校正的能力。
IF 2.4 4区 医学
Physical and Engineering Sciences in Medicine Pub Date : 2025-03-01 Epub Date: 2025-01-06 DOI: 10.1007/s13246-024-01515-9
Rogelio Manuel Diaz Moreno, Gonzalo Nuñez, C Daniel Venencia, Roberto A Isoardi, María José Almada
{"title":"Use of a virtual phantom to assess the capability of a treatment planning system to perform magnetic resonance image distortion correction.","authors":"Rogelio Manuel Diaz Moreno, Gonzalo Nuñez, C Daniel Venencia, Roberto A Isoardi, María José Almada","doi":"10.1007/s13246-024-01515-9","DOIUrl":"10.1007/s13246-024-01515-9","url":null,"abstract":"<p><p>Treatment Planning Systems (TPS) offer algorithms for distortion correction (DC) of Magnetic Resonance (MR) images, whose performances demand proper evaluation. This work develops a procedure using a virtual phantom to quantitatively assess a TPS DC algorithm. Variations of the digital Brainweb MR study were created by introducing known distortions and Control Points (CPs). A synthetic Computed Tomography (sCT) study was created based upon the MR study. Elements TPS (Brainlab, Munich, Germany) was used to apply DC to the MR images, choosing the sCT as the gold standard. Deviations in the CP locations between the original images, the distorted images and the corrected images were calculated. Structural Similarity Metric (SSIM) tests were applied for further assessment of image corrections. The introduced distortion deviated the CP locations by a median (range) value of 1.8 (0.2-4.4) mm. After DC was applied, these values were reduced to 0.6 (0.1-1.9) mm. Correction of the original image deviated the CP locations by 0.2 (0-1.1) mm. The SSIM comparisons between the original and the distorted images yielded values of 0.23 and 0.67 before and after DC, respectively. The SSIM comparison of the original study, before and after DC, yielded a value of 0.97. The proposed methodology using a virtual phantom with CPs can be used to assess a TPS DC algorithm. Elements TPS effectively reduced MR distorsions below radiosurgery tolerances.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"317-327"},"PeriodicalIF":2.4,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142932242","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
Measurement and spectral analysis of medical shock wave parameters based on flexible PVDF sensors. 基于柔性PVDF传感器的医疗冲击波参数测量与光谱分析。
IF 2.4 4区 医学
Physical and Engineering Sciences in Medicine Pub Date : 2025-03-01 Epub Date: 2025-01-28 DOI: 10.1007/s13246-025-01519-z
Liansheng Xu, Fei Shen, Fan Fan, Qiong Wu, Li Wang, Fengji Li, Yubo Fan, Haijun Niu
{"title":"Measurement and spectral analysis of medical shock wave parameters based on flexible PVDF sensors.","authors":"Liansheng Xu, Fei Shen, Fan Fan, Qiong Wu, Li Wang, Fengji Li, Yubo Fan, Haijun Niu","doi":"10.1007/s13246-025-01519-z","DOIUrl":"10.1007/s13246-025-01519-z","url":null,"abstract":"<p><p>Extracorporeal shock wave therapy (ESWT) achieves its therapeutic purpose mainly through the biological effects produced by the interaction of shock waves with tissues, and the accurate measurement and calculation of the mechanical parameters of shock waves in tissues are of great significance in formulating the therapeutic strategy and evaluating the therapeutic effect. This study utilizes the approach of implanting flexible polyvinylidene fluoride (PVDF) vibration sensors inside the tissue-mimicking phantom of various thicknesses to capture waveforms at different depths during the impact process in real time. Parameters including positive and negative pressure changes (P<sub>+</sub>, P<sub>-</sub>), pulse wave rise time ([Formula: see text]), and energy flux density (EFD) are calculated, and frequency spectrum analysis of the waveforms is conducted. The dynamic response, propagation process, and attenuation law of the shock wave in the phantom under different impact intensities were analyzed. Results showed that flexible PVDF sensors could precisely acquire the characteristics of pulse waveform propagating within the phantom. At the same depth, as the driving pressure increases, P<sub>+</sub> and P<sub>-</sub> increase linearly, and [Formula: see text] remains constant. At the same driving pressure, P<sub>+</sub>, P<sub>-</sub>, and EFD decay exponentially with increasing propagation depth. At the same depth, the spectra of pulse waveforms are similar, and the increasing driving pressure does not cause significant changes in carrier frequency and modulation frequency. The research findings could provide a reference for developing ESWT devices, improving treatment strategies, and enhancing the safety of clinical applications.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"369-378"},"PeriodicalIF":2.4,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143053861","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
Noninvasive machine-learning models for the detection of lesion-specific ischemia in patients with stable angina with intermediate stenosis severity on coronary CT angiography. 无创机器学习模型在冠状动脉CT造影中检测中度狭窄程度的稳定型心绞痛患者的病变特异性缺血。
IF 2.4 4区 医学
Physical and Engineering Sciences in Medicine Pub Date : 2025-03-01 Epub Date: 2024-12-30 DOI: 10.1007/s13246-024-01503-z
Hiroshi Hamasaki, Hidetaka Arimura, Yuzo Yamasaki, Takayuki Yamamoto, Mitsuhiro Fukata, Tetsuya Matoba, Toyoyuki Kato, Kousei Ishigami
{"title":"Noninvasive machine-learning models for the detection of lesion-specific ischemia in patients with stable angina with intermediate stenosis severity on coronary CT angiography.","authors":"Hiroshi Hamasaki, Hidetaka Arimura, Yuzo Yamasaki, Takayuki Yamamoto, Mitsuhiro Fukata, Tetsuya Matoba, Toyoyuki Kato, Kousei Ishigami","doi":"10.1007/s13246-024-01503-z","DOIUrl":"10.1007/s13246-024-01503-z","url":null,"abstract":"<p><p>This study proposed noninvasive machine-learning models for the detection of lesion-specific ischemia (LSI) in patients with stable angina with intermediate stenosis severity based on coronary computed tomography (CT) angiography. This single-center retrospective study analyzed 76 patients (99 vessels) with stable angina who underwent coronary CT angiography (CCTA) and had intermediate stenosis severity (40-69%) on invasive coronary angiography. LSI, defined as a resting full-cycle ratio < 0.86 or fractional flow reserve ≤ 0.80, was determined in 40 patients (46 vessels) using a hybrid resting full-cycle ratio-fractional flow reserve strategy. The resting full-cycle ratio and/or fractional flow reserve were measured using invasive coronary angiography as references for functional severity indices of coronary stenosis in the machine-learning models. LSI detection models were constructed using noninvasive machine-learning models that predicted the resting full-cycle ratio and fractional flow reserve by feeding machine-learning models with image features extracted from CCTA. The diagnostic performance of the proposed LSI detection models was assessed using a nested 10-fold cross-validation test. The LSI detection models with the highest diagnostic performance achieved an accuracy of 0.88 (95% CI: 0.81, 0.94), sensitivity of 0.78 (95% CI: 0.70, 0.86) and specificity of 0.96 (95% CI: 0.92, 1.00) on a vessel basis and 0.88 (95% CI: 0.81, 0.95), 0.80 (95% CI: 0.70, 0.86) and 0.97 (95% CI: 0.92, 1.00), respectively, on a patient basis. These findings suggest that LSI detection models with features extracted from CCTA can noninvasively detect LSI in patients with stable angina with intermediate stenosis severity.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"167-180"},"PeriodicalIF":2.4,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142911021","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
In-silico evaluation of the effect of set-up errors on dose delivery during mouse irradiations with a Cs-137 cell irradiator-based collimator system. 基于Cs-137细胞辐照器的准直系统对小鼠辐照过程中设置误差对剂量传递影响的计算机评价。
IF 2.4 4区 医学
Physical and Engineering Sciences in Medicine Pub Date : 2025-03-01 Epub Date: 2025-01-08 DOI: 10.1007/s13246-024-01486-x
Amir Entezam, Andrew Fielding, Gishan Ratnayake, Davide Fontanarosa
{"title":"In-silico evaluation of the effect of set-up errors on dose delivery during mouse irradiations with a Cs-137 cell irradiator-based collimator system.","authors":"Amir Entezam, Andrew Fielding, Gishan Ratnayake, Davide Fontanarosa","doi":"10.1007/s13246-024-01486-x","DOIUrl":"10.1007/s13246-024-01486-x","url":null,"abstract":"<p><p>Set-up errors are a problem for pre-clinical irradiators that lack imaging capabilities. The aim of this study was to investigate the impact of the potential set-up errors on the dose distribution for a mouse with a xenographic tumour irradiated with a standard Cs-137 cell irradiator equipped with an in-house lead collimator with 10 mm diameter apertures. The EGSnrc Monte-Carlo (MC) code was used to simulate the potential errors caused by displacements of the mouse in the irradiation setup. The impact of the simulated set-up displacements on the dose delivered to the xenographic tumour and surrounding organs was assessed. MC dose calculations were performed in a Computed Tomography (CT) derived model of the mouse for the reference position of the tumour in the irradiation setup. The errors were added into the CT data and then the mouse doses for the corresponding shifts were recalculated and dose volume histograms (DVHs) were generated. The investigation was performed for 1 cm and 0.5 cm diameter tumours. The DVH resulting from introducing the maximum setup errors for 1 cm diameter tumours showed up to 35% reduced dose to a significant fraction of the tumour volume. The setup errors demonstrated an insignificant effect on doses for 0.5 cm diameter tumour irradiations. Setup errors were observed to have negligible impact on out of field doses to organs at risk. The dosimetric results presented herein verify the robustness of our collimator system for irradiations of xenograft tumours up to 0.5 cm diameter in the presence of the maximum setup errors.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"21-33"},"PeriodicalIF":2.4,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142956847","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
Improving deep learning U-Net++ by discrete wavelet and attention gate mechanisms for effective pathological lung segmentation in chest X-ray imaging. 利用离散小波和注意门机制改进深度学习 U-Net++,从而在胸部 X 射线成像中有效进行病理肺分割。
IF 2.4 4区 医学
Physical and Engineering Sciences in Medicine Pub Date : 2025-03-01 Epub Date: 2024-11-04 DOI: 10.1007/s13246-024-01489-8
Faiçal Alaoui Abdalaoui Slimani, M'hamed Bentourkia
{"title":"Improving deep learning U-Net++ by discrete wavelet and attention gate mechanisms for effective pathological lung segmentation in chest X-ray imaging.","authors":"Faiçal Alaoui Abdalaoui Slimani, M'hamed Bentourkia","doi":"10.1007/s13246-024-01489-8","DOIUrl":"10.1007/s13246-024-01489-8","url":null,"abstract":"<p><p>Since its introduction in 2015, the U-Net architecture used in Deep Learning has played a crucial role in medical imaging. Recognized for its ability to accurately discriminate small structures, the U-Net has received more than 2600 citations in academic literature, which motivated continuous enhancements to its architecture. In hospitals, chest radiography is the primary diagnostic method for pulmonary disorders, however, accurate lung segmentation in chest X-ray images remains a challenging task, primarily due to the significant variations in lung shapes and the presence of intense opacities caused by various diseases. This article introduces a new approach for the segmentation of lung X-ray images. Traditional max-pooling operations, commonly employed in conventional U-Net++ models, were replaced with the discrete wavelet transform (DWT), offering a more accurate down-sampling technique that potentially captures detailed features of lung structures. Additionally, we used attention gate (AG) mechanisms that enable the model to focus on specific regions in the input image, which improves the accuracy of the segmentation process. When compared with current techniques like Atrous Convolutions, Improved FCN, Improved SegNet, U-Net, and U-Net++, our method (U-Net++-DWT) showed remarkable efficacy, particularly on the Japanese Society of Radiological Technology dataset, achieving an accuracy of 99.1%, specificity of 98.9%, sensitivity of 97.8%, Dice Coefficient of 97.2%, and Jaccard Index of 96.3%. Its performance on the Montgomery County dataset further demonstrated its consistent effectiveness. Moreover, when applied to additional datasets of Chest X-ray Masks and Labels and COVID-19, our method maintained high performance levels, achieving up to 99.3% accuracy, thereby underscoring its adaptability and potential for broad applications in medical imaging diagnostics.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"59-73"},"PeriodicalIF":2.4,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142569956","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 method for early prediction of sudden cardiac death through nonlinear feature extraction from ECG signals. 一种基于心电信号非线性特征提取的心源性猝死早期预测方法。
IF 2.4 4区 医学
Physical and Engineering Sciences in Medicine Pub Date : 2025-03-01 Epub Date: 2025-02-10 DOI: 10.1007/s13246-025-01517-1
Fatemeh Danesh Jablo, Hamed Danandeh Hesar
{"title":"A novel method for early prediction of sudden cardiac death through nonlinear feature extraction from ECG signals.","authors":"Fatemeh Danesh Jablo, Hamed Danandeh Hesar","doi":"10.1007/s13246-025-01517-1","DOIUrl":"10.1007/s13246-025-01517-1","url":null,"abstract":"<p><p>Sudden cardiac death (SCD) is a critical cardiovascular issue affecting approximately 3 million individuals globally each year, often occurring without prior noticeable symptoms. While the precise etiology of SCD remains elusive, ventricular fibrillation is believed to play a pivotal role in its pathophysiology. Given that symptoms typically manifest only an hour before the event, timely prediction is crucial for effective cardiac resuscitation. This study aims to predict SCD using time-frequency analysis of ECG signals. We utilized two online datasets: the Sudden Cardiac Death Holter dataset and the MIT-BIH Normal Sinus Rhythm dataset. Our proposed method involves segmenting the 60-min interval preceding ventricular fibrillation into one-minute segments, which are then decomposed into time-frequency sub-bands using empirical mode decomposition (EMD). Nonlinear features are extracted from these decomposed signals, followed by classification using support vector machines (SVM) and K-nearest neighbors (KNN) algorithms. To enhance classification accuracy, we employed two statistical feature selection techniques: T-test and ANOVA. Results indicate that using the ANOVA feature selection method in conjunction with SVM and KNN algorithms achieves high accuracy in predicting SCD. Specifically, the average accuracy rates for the 60 min preceding SCD were 93.51% for ANOVA-SVM and 93% for ANOVA-KNN. With T-test feature selection, the average accuracy rates were 93.29% for SVM and 93.41% for KNN. These findings demonstrate the promising performance of our proposed approach in predicting SCD, potentially contributing to improved early intervention strategies and patient outcomes.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":"343-358"},"PeriodicalIF":2.4,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143383558","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
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信