Biomedizinische Technik. Biomedical engineering最新文献

{"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}

{"title":"Biomechanical comparison of three fixation strategies for radial head fractures: a biomechanical study.","authors":"Yao-Tung Tsai, Kun-Jhih Lin, Jui-Cheng Lin","doi":"10.1515/bmt-2023-0107","DOIUrl":"10.1515/bmt-2023-0107","url":null,"abstract":"<p><p>Second-generation headless compression screws (HCSs) are commonly used for the fixation of small bones and articular fractures. However, there is a lack of biomechanical data regarding the application of such screws to radial head fractures. This study evaluated the mechanical properties of the fixation of radial head fractures using a single oblique HCS compared with those obtained using a standard locking radial head plate (LRHP) construct and a double cortical screw (DCS) construct. Radial synbone models were used for biomechanical tests of HCS, LRHP, and DCS constructs. All specimens were first cyclically loaded and then loaded to failure. The stiffness for the LRHP group was significantly higher than that for the other two groups, and that for the HCS group was significantly higher than that for the DCS group. The LRHP group had the greatest strength, followed by the HCS group and then the DCS group. The HCS construct demonstrated greater fixation strength than that of the commonly used cortical screws, although the plate group was the most stable. The present study revealed the feasibility of using a single oblique HCS, which has the advantages of being buried, requiring limited wound exposure, and having relatively easy operation, for treating simple radial head fractures.</p>","PeriodicalId":93905,"journal":{"name":"Biomedizinische Technik. Biomedical engineering","volume":" ","pages":"193-198"},"PeriodicalIF":0.0,"publicationDate":"2023-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"50164161","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":"Probabilistic hierarchical clustering based identification and segmentation of brain tumors in magnetic resonance imaging.","authors":"Ankit Vidyarthi","doi":"10.1515/bmt-2021-0313","DOIUrl":"10.1515/bmt-2021-0313","url":null,"abstract":"<p><p>The automatic segmentation of the abnormality region from the head MRI is a challenging task in the medical science domain. The abnormality in the form of the tumor comprises the uncontrolled growth of the cells. The automatic identification of the affected cells using computerized software systems is demanding in the past several years to provide a second opinion to radiologists. In this paper, a new clustering approach is introduced based on the machine learning aspect that clusters the tumor region from the input MRI using disjoint tree generation followed by tree merging. Further, the proposed algorithm is improved by introducing the theory of joint probabilities and nearest neighbors. Later, the proposed algorithm is automated to find the number of clusters required with its nearest neighbors to do semantic segmentation of the tumor cells. The proposed algorithm provides good semantic segmentation results having the DB index-0.11 and Dunn index-13.18 on the SMS dataset. While the experimentation with BRATS 2015 dataset yields <i>Dice</i> _complete=80.5 %, <i>Dice</i> _core=73.2 %, and <i>Dice</i> _enhanced=62.8 %. The comparative analysis of the proposed approach with benchmark models and algorithms proves the model's significance and its applicability to do semantic segmentation of the tumor cells with the average increment in the accuracy of around ±2.5 % with machine learning algorithms.</p>","PeriodicalId":93905,"journal":{"name":"Biomedizinische Technik. Biomedical engineering","volume":" ","pages":"181-192"},"PeriodicalIF":0.0,"publicationDate":"2023-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49694963","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":"Development of audio-guided deep breathing and auditory Go/No-Go task on evaluating its impact on the wellness of young adults: a pilot study.","authors":"Eng Keat Kwa, Soon Keng Cheong, Lin Kooi Ong, Poh Foong Lee","doi":"10.1515/bmt-2023-0410","DOIUrl":"10.1515/bmt-2023-0410","url":null,"abstract":"<p><strong>Objectives: </strong>Numerous studies indicate that deep breathing (DB) enhances wellbeing. Multiple deep breathing methods exist, but few employ audio to reach similar results. This study developed audio-guided DB and evaluated its immediate impacts on healthy population via self-created auditory Go/No-Go task, tidal volume changes, and psychological measures.</p><p><strong>Methods: </strong>Audio-guided DB with natural sounds to guide the DB was developed. Meanwhile, audio-based Go/No-Go paradigm with Arduino was built to measure the attention level. Thirty-two healthy young adults (n=32) were recruited. Psychological questionnaires (Rosenberg's Self-Esteem Scale (RSES), Cognitive and Affective Mindfulness Scale-Revised (CAMS-R), Perceived Stress Scale (PSS)), objective measurements with tidal volume and attention level with auditory Go/No-Go task were conducted before and after 5 min of DB.</p><p><strong>Results: </strong>Results showed a significant increment in tidal volume and task reaction time from baseline (p=0.003 and p=0.033, respectively). Significant correlations were acquired between (1) task accuracy with commission error (r=-0.905), (2) CAMS-R with task accuracy (r=-0.425), commission error (r=0.53), omission error (r=0.395) and PSS (r=-0.477), and (3) RSES with task reaction time (r=-0.47), task accuracy (r=-0.362), PSS (r=-0.552) and CAMS-R (r=0.591).</p><p><strong>Conclusions: </strong>This pilot study suggests a link between it and young adults' wellbeing and proposes auditory Go/No-Go task for assessing attention across various groups while maintaining physical and mental wellness.</p>","PeriodicalId":93905,"journal":{"name":"Biomedizinische Technik. Biomedical engineering","volume":" ","pages":"141-150"},"PeriodicalIF":0.0,"publicationDate":"2023-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49686310","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":"Detection of driver drowsiness level using a hybrid learning model based on ECG signals.","authors":"Hui Xiong, Yan Yan, Lifei Sun, Jinzhen Liu, Yuqing Han, Yangyang Xu","doi":"10.1515/bmt-2023-0193","DOIUrl":"10.1515/bmt-2023-0193","url":null,"abstract":"<p><strong>Objectives: </strong>Fatigue has a considerable impact on the driver's vehicle and even the driver's own operating ability.</p><p><strong>Methods: </strong>An intelligent algorithm is proposed for the problem that it is difficult to classify the degree of drowsiness generated by the driver during the driving process. By studying the driver's electrocardiogram (ECG) during driving, two models were established to jointly classify the ECG signals as awake, stress, and fatigue or drowsiness states for drowsiness levels. Firstly, the deep learning method was used to establish the model_1 to predict the drowsiness of the original ECG, and model_2 was developed using the combination of principal component analysis (PCA) and weighted K-nearest neighbor (WKNN) algorithm to classify the heart rate variability characteristics. Then, the drowsiness prediction results of the two models were weighted according to certain rules, and the hybrid learning model combining dilated convolution and bidirectional long short-term memory network with PCA and WKNN algorithm was established, and the mixed model was denoted as DiCNN-BiLSTM and PCA-WKNN (DBPW). Finally, the validity of the DBPW model was verified by simulation of the public database.</p><p><strong>Results: </strong>The experimental results show that the average accuracy, sensitivity and F1 score of the test model in the dataset containing multiple drivers are 98.79, 98.81, and 98.79 % respectively, and the recognition accuracy for drowsiness or drowsiness state is 99.33 %.</p><p><strong>Conclusions: </strong>Using the proposed algorithm, it is possible to identify driver anomalies and provide new ideas for the development of intelligent vehicles.</p>","PeriodicalId":93905,"journal":{"name":"Biomedizinische Technik. Biomedical engineering","volume":" ","pages":"151-165"},"PeriodicalIF":0.0,"publicationDate":"2023-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41223509","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}