Biomedizinische Technik. Biomedical engineering最新文献

{"title":"Combination of edge enhancement and cold diffusion model for low dose CT image denoising.","authors":"Yinglin Du, Yi Liu, Han Wu, Jiaqi Kang, Zhiguo Gui, Pengcheng Zhang, Yali Ren","doi":"10.1515/bmt-2024-0362","DOIUrl":"10.1515/bmt-2024-0362","url":null,"abstract":"<p><strong>Objectives: </strong>Since the quality of low dose CT (LDCT) images is often severely affected by noise and artifacts, it is very important to maintain high quality CT images while effectively reducing the radiation dose.</p><p><strong>Methods: </strong>In recent years, the representation of diffusion models to produce high quality images and stable trainability has attracted wide attention. With the extension of the cold diffusion model to the classical diffusion model, its application has greater flexibility. Inspired by the cold diffusion model, we proposes a low dose CT image denoising method, called CECDM, based on the combination of edge enhancement and cold diffusion model. The LDCT image is taken as the end point (forward) of the diffusion process and the starting point (reverse) of the sampling process. Improved sobel operator and Convolution Block Attention Module are added to the network, and compound loss function is adopted.</p><p><strong>Results: </strong>The experimental results show that CECDM can effectively remove noise and artifacts from LDCT images while the inference time of a single image is reduced to 0.41 s.</p><p><strong>Conclusions: </strong>Compared with the existing LDCT image post-processing methods, CECDM has a significant improvement in all indexes.</p>","PeriodicalId":93905,"journal":{"name":"Biomedizinische Technik. Biomedical engineering","volume":" ","pages":"157-169"},"PeriodicalIF":0.0,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142585202","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A multimodal deep learning-based algorithm for specific fetal heart rate events detection.","authors":"Zhuya Huang, Junsheng Yu, Ying Shan","doi":"10.1515/bmt-2024-0334","DOIUrl":"10.1515/bmt-2024-0334","url":null,"abstract":"<p><strong>Objectives: </strong>This study aims to develop a multimodal deep learning-based algorithm for detecting specific fetal heart rate (FHR) events, to enhance automatic monitoring and intelligent assessment of fetal well-being.</p><p><strong>Methods: </strong>We analyzed FHR and uterine contraction signals by combining various feature extraction techniques, including morphological features, heart rate variability features, and nonlinear domain features, with deep learning algorithms. This approach enabled us to classify four specific FHR events (bradycardia, tachycardia, acceleration, and deceleration) as well as four distinct deceleration patterns (early, late, variable, and prolonged deceleration). We proposed a multi-model deep neural network and a pre-fusion deep learning model to accurately classify the multimodal parameters derived from Cardiotocography signals.</p><p><strong>Results: </strong>These accuracy metrics were calculated based on expert-labeled data. The algorithm achieved a classification accuracy of 96.2 % for acceleration, 94.4 % for deceleration, 90.9 % for tachycardia, and 85.8 % for bradycardia. Additionally, it achieved 67.0 % accuracy in classifying the four distinct deceleration patterns, with 80.9 % accuracy for late deceleration and 98.9 % for prolonged deceleration.</p><p><strong>Conclusions: </strong>The proposed multimodal deep learning algorithm serves as a reliable decision support tool for clinicians, significantly improving the detection and assessment of specific FHR events, which are crucial for fetal health monitoring.</p>","PeriodicalId":93905,"journal":{"name":"Biomedizinische Technik. Biomedical engineering","volume":" ","pages":"183-194"},"PeriodicalIF":0.0,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142559729","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A software tool for fabricating phantoms mimicking human tissues with designated dielectric properties and frequency.","authors":"Xinyue Zhang, Guofang Xu, Qiaotian Zhang, Henghui Liu, Xiang Nan, Jijun Han","doi":"10.1515/bmt-2024-0043","DOIUrl":"10.1515/bmt-2024-0043","url":null,"abstract":"<p><strong>Objectives: </strong>Dielectric materials play a crucial role in assessing and refining the measurement performance of dielectric properties for specific tasks. The availability of viable and standardized dielectric materials could greatly enhance medical applications related to dielectric properties. However, obtaining reliable phantoms with designated dielectric properties across a specified frequency range remains challenging. In this study, we propose software to easily determine the components of dielectric materials in the frequency range of 16 MHz to 3 GHz.</p><p><strong>Methods: </strong>A total of 184 phantoms were fabricated and measured using open-ended coaxial probe method. The relationship among dielectric properties, frequency, and the components of dielectric materials was fitted through feedforward neural networks. Software was developed to quickly calculate the composition of dielectric materials.</p><p><strong>Results: </strong>We performed validation experiments including blood, muscle, skin, and lung tissue phantoms at 128 MHz, 298 MHz, 915 MHz, and 2.45 GHz. Compared with literature values, the relative errors of dielectric properties are less than 15 %.</p><p><strong>Conclusions: </strong>This study establishes a reliable method for fabricating dielectric materials with designated dielectric properties and frequency through the development of the software. This research holds significant importance in enhancing medical research and applications that rely on tissue simulation using dielectric phantoms.</p>","PeriodicalId":93905,"journal":{"name":"Biomedizinische Technik. Biomedical engineering","volume":" ","pages":"61-70"},"PeriodicalIF":0.0,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142514610","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Concept and development of a telemedical supervision system for anesthesiology in operating rooms using the interoperable communication standard ISO/IEEE 11073 SDC.","authors":"Jonas Roth, Verena Voigt, Okan Yilmaz, Michael Schauwinhold, Michael Czaplik, Andreas Follmann, Carina B Pereira","doi":"10.1515/bmt-2024-0378","DOIUrl":"10.1515/bmt-2024-0378","url":null,"abstract":"<p><strong>Objectives: </strong>Discussion of a telemedical supervision system for anesthesiology in the operating room using the interoperable communication protocol SDC. Validation of a first conceptual demonstrator and highlight of strengths and weaknesses.</p><p><strong>Methods: </strong>The system includes relevant medical devices, a central anesthesia workstation (AN-WS), and a remote supervision workstation (SV-WS) and the concept uses the interoperability standard ISO/IEEE 11073 SDC. The validation method involves a human patient simulator, and the system is tested in an intervention study with 16 resident anesthetists supervised by a senior anesthetist.</p><p><strong>Results: </strong>This study presents a novel tele-supervision system that enables remote patient monitoring and communication between anesthesia providers and supervisors. It is composed of connected medical devices via SDC, a central AN-WS and a mobile remote SV-WS. The system is designed to handle multiple ORs and route the data to a single SV-WS. It enables audio/video connections and text chatting between the workstations and offers the supervisor to switch between cameras in the OR. Through a validation study the feasibility and usefulness of the system was assessed.</p><p><strong>Conclusions: </strong>Validation results highlighted, that such system might not replace physically present supervisors but is able to provide supervision for scenarios where supervision is currently not available or only under adverse circumstances.</p>","PeriodicalId":93905,"journal":{"name":"Biomedizinische Technik. Biomedical engineering","volume":" ","pages":"91-101"},"PeriodicalIF":0.0,"publicationDate":"2024-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142514611","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"DeepCOVIDNet-CXR: deep learning strategies for identifying COVID-19 on enhanced chest X-rays.","authors":"Gokhan Altan, Süleyman Serhan Narli","doi":"10.1515/bmt-2021-0272","DOIUrl":"10.1515/bmt-2021-0272","url":null,"abstract":"<p><strong>Objectives: </strong>COVID-19 is one of the recent major epidemics, which accelerates its mortality and prevalence worldwide. Most literature on chest X-ray-based COVID-19 analysis has focused on multi-case classification (COVID-19, pneumonia, and normal) by the advantages of Deep Learning. However, the limited number of chest X-rays with COVID-19 is a prominent deficiency for clinical relevance. This study aims at evaluating COVID-19 identification performances using adaptive histogram equalization (AHE) to feed the ConvNet architectures with reliable lung anatomy of airways.</p><p><strong>Methods: </strong>We experimented with balanced small- and large-scale COVID-19 databases using left lung, right lung, and complete chest X-rays with various AHE parameters. On multiple strategies, we applied transfer learning on four ConvNet architectures (MobileNet, DarkNet19, VGG16, and AlexNet).</p><p><strong>Results: </strong>Whereas DarkNet19 reached the highest multi-case identification performance with an accuracy rate of 98.26 % on the small-scale dataset, VGG16 achieved the best generalization performance with an accuracy rate of 95.04 % on the large-scale dataset.</p><p><strong>Conclusions: </strong>Our study is one of the pioneering approaches that analyses 3615 COVID-19 cases and specifies the most responsible AHE parameters for ConvNet architectures in the multi-case classification.</p>","PeriodicalId":93905,"journal":{"name":"Biomedizinische Technik. Biomedical engineering","volume":" ","pages":"21-35"},"PeriodicalIF":0.0,"publicationDate":"2024-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142382753","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mechano-responses of quadriceps muscles evoked by transcranial magnetic stimulation.","authors":"Zafirah Zakaria, Mazlina Mazlan, Tze Yang Chung, Victor S Selvanayagam, John Temesi, Vhinoth Magenthran, Nur Azah Hamzaid","doi":"10.1515/bmt-2023-0501","DOIUrl":"10.1515/bmt-2023-0501","url":null,"abstract":"<p><p>Mechanomyography (MMG) may be used to quantify very small motor responses resulting from muscle activation, voluntary or involuntary. The purpose of this study was to investigate the MMG mean peak amplitude (MPA) and area under the curve (AUC) and the corresponding mechanical responses following delivery of transcranial magnetic stimulation (TMS) to the knee extensors. Fourteen adults (23 ± 1 years) received single TMS pulses at intensities from 30-80 % maximum stimulator output to elicit muscle responses in the relaxed knee extensors while seated. An accelerometer-based sensor was placed on the rectus femoris (RF) and vastus lateralis (VL) muscle bellies to measure the MMG signal. Pearson correlation revealed a positive linear relationship between MMG MPA and TMS intensity for RF (r=0.569; p<0.001) and VL (r=0.618; p<0.001). TMS intensity of ≥60 % maximum stimulator output produced significantly higher MPA than at 30 % TMS intensity and evoked measurable movement at the knee joint. MMG MPA was positively correlated to AUC (r=0.957 for RF and r=0.603 for VL; both p<0.001) and knee extension angle (r=0.596 for RF and r=0.675 for VL; both p<0.001). In conclusion, MMG captured knee extensor mechanical responses at all TMS intensities with the response increasing with increasing TMS intensity. These findings suggest that MMG can be an additional tool for assessing muscle activation.</p>","PeriodicalId":93905,"journal":{"name":"Biomedizinische Technik. Biomedical engineering","volume":" ","pages":"3-10"},"PeriodicalIF":0.0,"publicationDate":"2024-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142334324","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Vein segmentation and visualization of upper and lower extremities using convolution neural network.","authors":"Amit Laddi, Shivalika Goyal, Himani, A. Savlania","doi":"10.1515/bmt-2023-0331","DOIUrl":"https://doi.org/10.1515/bmt-2023-0331","url":null,"abstract":"OBJECTIVES\u0000The study focused on developing a reliable real-time venous localization, identification, and visualization framework based upon deep learning (DL) self-parametrized Convolution Neural Network (CNN) algorithm for segmentation of the venous map for both lower and upper limb dataset acquired under unconstrained conditions using near-infrared (NIR) imaging setup, specifically to assist vascular surgeons during venipuncture, vascular surgeries, or Chronic Venous Disease (CVD) treatments.\u0000\u0000\u0000METHODS\u0000A portable image acquisition setup has been designed to collect venous data (upper and lower extremities) from 72 subjects. A manually annotated image dataset was used to train and compare the performance of existing well-known CNN-based architectures such as ResNet and VGGNet with self-parameterized U-Net, improving automated vein segmentation and visualization.\u0000\u0000\u0000RESULTS\u0000Experimental results indicated that self-parameterized U-Net performs better at segmenting the unconstrained dataset in comparison with conventional CNN feature-based learning models, with a Dice score of 0.58 and displaying 96.7 % accuracy for real-time vein visualization, making it appropriate to locate veins in real-time under unconstrained conditions.\u0000\u0000\u0000CONCLUSIONS\u0000Self-parameterized U-Net for vein segmentation and visualization has the potential to reduce risks associated with traditional venipuncture or CVD treatments by outperforming conventional CNN architectures, providing vascular assistance, and improving patient care and treatment outcomes.","PeriodicalId":93905,"journal":{"name":"Biomedizinische Technik. Biomedical engineering","volume":"43 20","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140661047","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hybrid optimization assisted channel selection of EEG for deep learning model-based classification of motor imagery task.","authors":"K Venu, P Natesan","doi":"10.1515/bmt-2023-0407","DOIUrl":"10.1515/bmt-2023-0407","url":null,"abstract":"<p><strong>Objectives: </strong>To design and develop an approach named HC + SMA-SSA scheme for classifying motor imagery task.</p><p><strong>Methods: </strong>The offered model employs a new method for classifying motor imagery task. Initially, down sampling is deployed to pre-process the incoming signal. Subsequently, \"Modified Stockwell Transform (ST) and common spatial pattern (CSP) based features are extracted\". Then, optimal channel selection is made by a novel hybrid optimization model named as Spider Monkey Assisted SSA (SMA-SSA). Here, \"Long Short Term Memory (LSTM) and Bidirectional Gated Recurrent Unit (BI-GRU)\" models are used for final classification, whose outcomes are averaged at the end. At last, the improvement of SMA-SSA based model is proven over different metrics.</p><p><strong>Results: </strong>A superior sensitivity of 0.939 is noted for HC + SMA-SSA that was higher over HC with no optimization and proposed with traditional ST.</p><p><strong>Conclusions: </strong>The proposed method achieved effective classification performance in terms of performance measures.</p>","PeriodicalId":93905,"journal":{"name":"Biomedizinische Technik. Biomedical engineering","volume":" ","pages":"125-140"},"PeriodicalIF":0.0,"publicationDate":"2023-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"71489999","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CT-based evaluation of tissue expansion in cryoablation of <i>ex vivo</i> kidney.","authors":"Frank Hübner, Moritz Klaus, Norbert Siedow, Christian Leithäuser, Thomas Josef Vogl","doi":"10.1515/bmt-2023-0174","DOIUrl":"10.1515/bmt-2023-0174","url":null,"abstract":"<p><strong>Objectives: </strong>To evaluate tissue expansion during cryoablation, the displacement of markers in <i>ex vivo</i> kidney tissue was determined using computed tomographic (CT) imaging.</p><p><strong>Methods: </strong>CT-guided cryoablation was performed in nine porcine kidneys over a 10 min period. Markers and fiber optic temperature probes were positioned perpendicular to the cryoprobe shaft in an axial orientation. The temperature measurement was performed simultaneously with the acquisitions of the CT images in 5 s intervals. The distance change of the markers to the cryoprobe was determined in each CT image and equated to the measured temperature at the marker.</p><p><strong>Results: </strong>The greatest increase in the distance between the markers and the cryoprobe was observed in the initial phase of cryoablation. The maximum displacement of the markers was determined to be 0.31±0.2 mm and 2.8±0.02 %, respectively.</p><p><strong>Conclusions: </strong>The mean expansion of <i>ex vivo</i> kidney tissue during cryoablation with a single cryoprobe is 0.31±0.2 mm. The results can be used for identification of basic parameters for optimization of therapy planning.</p>","PeriodicalId":93905,"journal":{"name":"Biomedizinische Technik. Biomedical engineering","volume":" ","pages":"211-217"},"PeriodicalIF":0.0,"publicationDate":"2023-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"71489998","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Epileptic EEG patterns recognition through machine learning techniques and relevant time-frequency features.","authors":"Sahbi Chaibi, Chahira Mahjoub, Wadhah Ayadi, Abdennaceur Kachouri","doi":"10.1515/bmt-2023-0332","DOIUrl":"10.1515/bmt-2023-0332","url":null,"abstract":"<p><strong>Objectives: </strong>The present study is designed to explore the process of epileptic patterns' automatic detection, specifically, epileptic spikes and high-frequency oscillations (HFOs), via a selection of machine learning (ML) techniques. The primary motivation for conducting such a research lies mainly in the need to investigate the long-term electroencephalography (EEG) recordings' visual examination process, often considered as a time-consuming and potentially error-prone procedure, requiring a great deal of mental focus and highly experimented neurologists. On attempting to resolve such a challenge, a number of state-of-the-art ML algorithms have been evaluated and compare in terms of performance, to pinpoint the most effective algorithm fit for accurately extracting epileptic EEG patterns.</p><p><strong>Content: </strong>Based on intracranial as well as simulated EEG data, the attained findings turn out to reveal that the randomforest (RF) method proved to be the most consistently effective approach, significantly outperforming the entirety of examined methods in terms of EEG recordings epileptic-pattern identification. Indeed, the RF classifier appeared to record an average balanced classification rate (BCR) of 92.38 % in regard to spikes recognition process, and 78.77 % in terms of HFOs detection.</p><p><strong>Summary: </strong>Compared to other approaches, our results provide valuable insights into the RF classifier's effectiveness as a powerful ML technique, fit for detecting EEG signals born epileptic bursts.</p><p><strong>Outlook: </strong>As a potential future work, we envisage to further validate and sustain our major reached findings through incorporating a larger EEG dataset. We also aim to explore the generative adversarial networks (GANs) application so as to generate synthetic EEG signals or combine signal generation techniques with deep learning approaches. Through this new vein of thought, we actually preconize to enhance and boost the automated detection methods' performance even more, thereby, noticeably enhancing the epileptic EEG pattern recognition area.</p>","PeriodicalId":93905,"journal":{"name":"Biomedizinische Technik. Biomedical engineering","volume":" ","pages":"111-123"},"PeriodicalIF":0.0,"publicationDate":"2023-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"71415998","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}