The brain-computer interface (BCI) is one of the most powerful tools in neuroscience and generally includes a recording system, a processor system, and a stimulation system. Optogenetics has the advantages of bidirectional regulation, high spatiotemporal resolution, and cell-specific regulation, which expands the application scenarios of BCIs. In recent years, optogenetic BCIs have become widely used in the lab with the development of materials and software. The systems were designed to be more integrated, lightweight, biocompatible, and power efficient, as were the wireless transmission and chip-level embedded BCIs. The software is also constantly improving, with better real-time performance and accuracy and lower power consumption. On the other hand, as a cutting-edge technology spanning multidisciplinary fields including molecular biology, neuroscience, material engineering, and information processing, optogenetic BCIs have great application potential in neural decoding, enhancing brain function, and treating neural diseases. Here, we review the development and application of optogenetic BCIs. In the future, combined with other functional imaging techniques such as near-infrared spectroscopy (fNIRS) and functional magnetic resonance imaging (fMRI), optogenetic BCIs can modulate the function of specific circuits, facilitate neurological rehabilitation, assist perception, establish a brain-to-brain interface, and be applied in wider application scenarios.
{"title":"Optogenetic Brain-Computer Interfaces.","authors":"Feifang Tang, Feiyang Yan, Yushan Zhong, Jinqian Li, Hui Gong, Xiangning Li","doi":"10.3390/bioengineering11080821","DOIUrl":"https://doi.org/10.3390/bioengineering11080821","url":null,"abstract":"<p><p>The brain-computer interface (BCI) is one of the most powerful tools in neuroscience and generally includes a recording system, a processor system, and a stimulation system. Optogenetics has the advantages of bidirectional regulation, high spatiotemporal resolution, and cell-specific regulation, which expands the application scenarios of BCIs. In recent years, optogenetic BCIs have become widely used in the lab with the development of materials and software. The systems were designed to be more integrated, lightweight, biocompatible, and power efficient, as were the wireless transmission and chip-level embedded BCIs. The software is also constantly improving, with better real-time performance and accuracy and lower power consumption. On the other hand, as a cutting-edge technology spanning multidisciplinary fields including molecular biology, neuroscience, material engineering, and information processing, optogenetic BCIs have great application potential in neural decoding, enhancing brain function, and treating neural diseases. Here, we review the development and application of optogenetic BCIs. In the future, combined with other functional imaging techniques such as near-infrared spectroscopy (fNIRS) and functional magnetic resonance imaging (fMRI), optogenetic BCIs can modulate the function of specific circuits, facilitate neurological rehabilitation, assist perception, establish a brain-to-brain interface, and be applied in wider application scenarios.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":null,"pages":null},"PeriodicalIF":3.8,"publicationDate":"2024-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11351350/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142091756","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-12DOI: 10.3390/bioengineering11080819
Michael Weiser, Lindsay Stoy, Valerie Lallo, Sriram Balasubramanian, Anita Singh
Spinal cord injury (SCI) can lead to significant bone loss below the level of the lesion increasing the risk of fracture and increased morbidity. Body-weight-supported treadmill training (BWSTT) and transplantation strategies using neurotrophins have been shown to improve motor function after SCI. While rehabilitation training including BWSTT has also been effective in reducing bone loss post-SCI, the effects of transplantation therapies in bone restoration are not fully understood. Furthermore, the effects of a combinational treatment strategy on bone post-SCI also remain unknown. The aim of this study was to determine the effect of a combination therapy including transplantation of scaffold-releasing neurotrophins and BWSTT on the forelimb and hindlimb bones of a T9-T10 contused SCI animals. Humerus and tibia bones were harvested for Micro-CT scanning and a three-point bending test from four animal groups, namely injury, BWSTT (injury with BWSTT), scaffold (injury with scaffold-releasing neurotrophins), and combinational (injury treated with scaffold-releasing neurotrophins and BWSTT). BWSTT and combinational groups reported higher biomechanical properties in the tibial bone (below injury level) and lower biomechanical properties in the humerus bone (above injury level) when compared to the injury and scaffold groups. Studied structural parameters, including the cortical thickness and bone volume/tissue volume (BV/TV) were also higher in the tibia and lower in the humerus bones of BWSTT and combinational groups when compared to the injury and scaffold groups. While no significant differences were observed, this study is the first to report the effects of a combinational treatment strategy on bone loss in contused SCI animals and can help guide future interventions.
{"title":"The Efficacy of Body-Weight Supported Treadmill Training and Neurotrophin-Releasing Scaffold in Minimizing Bone Loss Following Spinal Cord Injury.","authors":"Michael Weiser, Lindsay Stoy, Valerie Lallo, Sriram Balasubramanian, Anita Singh","doi":"10.3390/bioengineering11080819","DOIUrl":"https://doi.org/10.3390/bioengineering11080819","url":null,"abstract":"<p><p>Spinal cord injury (SCI) can lead to significant bone loss below the level of the lesion increasing the risk of fracture and increased morbidity. Body-weight-supported treadmill training (BWSTT) and transplantation strategies using neurotrophins have been shown to improve motor function after SCI. While rehabilitation training including BWSTT has also been effective in reducing bone loss post-SCI, the effects of transplantation therapies in bone restoration are not fully understood. Furthermore, the effects of a combinational treatment strategy on bone post-SCI also remain unknown. The aim of this study was to determine the effect of a combination therapy including transplantation of scaffold-releasing neurotrophins and BWSTT on the forelimb and hindlimb bones of a T9-T10 contused SCI animals. Humerus and tibia bones were harvested for Micro-CT scanning and a three-point bending test from four animal groups, namely injury, BWSTT (injury with BWSTT), scaffold (injury with scaffold-releasing neurotrophins), and combinational (injury treated with scaffold-releasing neurotrophins and BWSTT). BWSTT and combinational groups reported higher biomechanical properties in the tibial bone (below injury level) and lower biomechanical properties in the humerus bone (above injury level) when compared to the injury and scaffold groups. Studied structural parameters, including the cortical thickness and bone volume/tissue volume (BV/TV) were also higher in the tibia and lower in the humerus bones of BWSTT and combinational groups when compared to the injury and scaffold groups. While no significant differences were observed, this study is the first to report the effects of a combinational treatment strategy on bone loss in contused SCI animals and can help guide future interventions.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":null,"pages":null},"PeriodicalIF":3.8,"publicationDate":"2024-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11351937/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142091833","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-12DOI: 10.3390/bioengineering11080822
Fatma M Talaat, Ahmed R Elnaggar, Warda M Shaban, Mohamed Shehata, Mostafa Elhosseini
The global prevalence of cardiovascular diseases (CVDs) as a leading cause of death highlights the imperative need for refined risk assessment and prognostication methods. The traditional approaches, including the Framingham Risk Score, blood tests, imaging techniques, and clinical assessments, although widely utilized, are hindered by limitations such as a lack of precision, the reliance on static risk variables, and the inability to adapt to new patient data, thereby necessitating the exploration of alternative strategies. In response, this study introduces CardioRiskNet, a hybrid AI-based model designed to transcend these limitations. The proposed CardioRiskNet consists of seven parts: data preprocessing, feature selection and encoding, eXplainable AI (XAI) integration, active learning, attention mechanisms, risk prediction and prognosis, evaluation and validation, and deployment and integration. At first, the patient data are preprocessed by cleaning the data, handling the missing values, applying a normalization process, and extracting the features. Next, the most informative features are selected and the categorical variables are converted into a numerical form. Distinctively, CardioRiskNet employs active learning to iteratively select informative samples, enhancing its learning efficacy, while its attention mechanism dynamically focuses on the relevant features for precise risk prediction. Additionally, the integration of XAI facilitates interpretability and transparency in the decision-making processes. According to the experimental results, CardioRiskNet demonstrates superior performance in terms of accuracy, sensitivity, specificity, and F1-Score, with values of 98.7%, 98.7%, 99%, and 98.7%, respectively. These findings show that CardioRiskNet can accurately assess and prognosticate the CVD risk, demonstrating the power of active learning and AI to surpass the conventional methods. Thus, CardioRiskNet's novel approach and high performance advance the management of CVDs and provide healthcare professionals a powerful tool for patient care.
{"title":"CardioRiskNet: A Hybrid AI-Based Model for Explainable Risk Prediction and Prognosis in Cardiovascular Disease.","authors":"Fatma M Talaat, Ahmed R Elnaggar, Warda M Shaban, Mohamed Shehata, Mostafa Elhosseini","doi":"10.3390/bioengineering11080822","DOIUrl":"https://doi.org/10.3390/bioengineering11080822","url":null,"abstract":"<p><p>The global prevalence of cardiovascular diseases (CVDs) as a leading cause of death highlights the imperative need for refined risk assessment and prognostication methods. The traditional approaches, including the Framingham Risk Score, blood tests, imaging techniques, and clinical assessments, although widely utilized, are hindered by limitations such as a lack of precision, the reliance on static risk variables, and the inability to adapt to new patient data, thereby necessitating the exploration of alternative strategies. In response, this study introduces CardioRiskNet, a hybrid AI-based model designed to transcend these limitations. The proposed CardioRiskNet consists of seven parts: data preprocessing, feature selection and encoding, eXplainable AI (XAI) integration, active learning, attention mechanisms, risk prediction and prognosis, evaluation and validation, and deployment and integration. At first, the patient data are preprocessed by cleaning the data, handling the missing values, applying a normalization process, and extracting the features. Next, the most informative features are selected and the categorical variables are converted into a numerical form. Distinctively, CardioRiskNet employs active learning to iteratively select informative samples, enhancing its learning efficacy, while its attention mechanism dynamically focuses on the relevant features for precise risk prediction. Additionally, the integration of XAI facilitates interpretability and transparency in the decision-making processes. According to the experimental results, CardioRiskNet demonstrates superior performance in terms of accuracy, sensitivity, specificity, and F1-Score, with values of 98.7%, 98.7%, 99%, and 98.7%, respectively. These findings show that CardioRiskNet can accurately assess and prognosticate the CVD risk, demonstrating the power of active learning and AI to surpass the conventional methods. Thus, CardioRiskNet's novel approach and high performance advance the management of CVDs and provide healthcare professionals a powerful tool for patient care.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":null,"pages":null},"PeriodicalIF":3.8,"publicationDate":"2024-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11351968/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142091805","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-10DOI: 10.3390/bioengineering11080814
Xu Jin, Hong An, Mengxian Chi
Recent advances in deep learning have shown significant potential for accurate cell detection via density map regression using point annotations. However, existing deep learning models often struggle with multi-scale feature extraction and integration in complex histopathological images. Moreover, in multi-class cell detection scenarios, current density map regression methods typically predict each cell type independently, failing to consider the spatial distribution priors of different cell types. To address these challenges, we propose CellRegNet, a novel deep learning model for cell detection using point annotations. CellRegNet integrates a hybrid CNN/Transformer architecture with innovative feature refinement and selection mechanisms, addressing the need for effective multi-scale feature extraction and integration. Additionally, we introduce a contrastive regularization loss that models the mutual exclusiveness prior in multi-class cell detection cases. Extensive experiments on three histopathological image datasets demonstrate that CellRegNet outperforms existing state-of-the-art methods for cell detection using point annotations, with F1-scores of 86.38% on BCData (breast cancer), 85.56% on EndoNuke (endometrial tissue) and 93.90% on MBM (bone marrow cells), respectively. These results highlight CellRegNet's potential to enhance the accuracy and reliability of cell detection in digital pathology.
{"title":"CellRegNet: Point Annotation-Based Cell Detection in Histopathological Images via Density Map Regression.","authors":"Xu Jin, Hong An, Mengxian Chi","doi":"10.3390/bioengineering11080814","DOIUrl":"https://doi.org/10.3390/bioengineering11080814","url":null,"abstract":"<p><p>Recent advances in deep learning have shown significant potential for accurate cell detection via density map regression using point annotations. However, existing deep learning models often struggle with multi-scale feature extraction and integration in complex histopathological images. Moreover, in multi-class cell detection scenarios, current density map regression methods typically predict each cell type independently, failing to consider the spatial distribution priors of different cell types. To address these challenges, we propose CellRegNet, a novel deep learning model for cell detection using point annotations. CellRegNet integrates a hybrid CNN/Transformer architecture with innovative feature refinement and selection mechanisms, addressing the need for effective multi-scale feature extraction and integration. Additionally, we introduce a contrastive regularization loss that models the mutual exclusiveness prior in multi-class cell detection cases. Extensive experiments on three histopathological image datasets demonstrate that CellRegNet outperforms existing state-of-the-art methods for cell detection using point annotations, with F1-scores of 86.38% on BCData (breast cancer), 85.56% on EndoNuke (endometrial tissue) and 93.90% on MBM (bone marrow cells), respectively. These results highlight CellRegNet's potential to enhance the accuracy and reliability of cell detection in digital pathology.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":null,"pages":null},"PeriodicalIF":3.8,"publicationDate":"2024-08-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11352042/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142091806","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-10DOI: 10.3390/bioengineering11080815
Adrián Pedreira, José A Vázquez, Andrey Romanenko, Míriam R García
During adaptive laboratory evolution experiments, any unexpected interruption in data monitoring or control could lead to the loss of valuable experimental data and compromise the integrity of the entire experiment. Most homemade mini-bioreactors are built employing microcontrollers such as Arduino. Although affordable, these platforms lack the robustness of the programmable logic controller (PLC), which enhances the safety and robustness of the control process. Here, we describe the design and validation of a PLC-controlled morbidostat, an innovative automated continuous-culture mini-bioreactor specifically created to study the evolutionary pathways to drug resistance in microorganisms. This morbidostat includes several improvements, both at the hardware and software level, for better online monitoring and a more robust operation. The device was validated employing Escherichia coli, exploring its adaptive evolution in the presence of didecyldimethylammonium chloride (DDAC), a quaternary ammonium compound widely used for its antimicrobial properties. E. coli was subjected to increasing concentrations of DDAC over 3 days. Our results demonstrated a significant increase in DDAC susceptibility, with evolved populations exhibiting substantial changes in their growth after exposure.
{"title":"Design and Validation of a PLC-Controlled Morbidostat for Investigating Bacterial Drug Resistance.","authors":"Adrián Pedreira, José A Vázquez, Andrey Romanenko, Míriam R García","doi":"10.3390/bioengineering11080815","DOIUrl":"https://doi.org/10.3390/bioengineering11080815","url":null,"abstract":"<p><p>During adaptive laboratory evolution experiments, any unexpected interruption in data monitoring or control could lead to the loss of valuable experimental data and compromise the integrity of the entire experiment. Most homemade mini-bioreactors are built employing microcontrollers such as Arduino. Although affordable, these platforms lack the robustness of the programmable logic controller (PLC), which enhances the safety and robustness of the control process. Here, we describe the design and validation of a PLC-controlled morbidostat, an innovative automated continuous-culture mini-bioreactor specifically created to study the evolutionary pathways to drug resistance in microorganisms. This morbidostat includes several improvements, both at the hardware and software level, for better online monitoring and a more robust operation. The device was validated employing <i>Escherichia coli</i>, exploring its adaptive evolution in the presence of didecyldimethylammonium chloride (DDAC), a quaternary ammonium compound widely used for its antimicrobial properties. <i>E. coli</i> was subjected to increasing concentrations of DDAC over 3 days. Our results demonstrated a significant increase in DDAC susceptibility, with evolved populations exhibiting substantial changes in their growth after exposure.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":null,"pages":null},"PeriodicalIF":3.8,"publicationDate":"2024-08-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11351851/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142091816","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-09DOI: 10.3390/bioengineering11080808
Rukui Zhang, Zhaorui Liu, Chaoyu Zhu, Hui Cai, Kai Yin, Fan Zhong, Lei Liu
Objectives: Clinical molecular genetic testing and molecular imaging dramatically increase the quantity of clinical data. Combined with the extensive application of electronic health records, a medical data ecosystem is forming, which calls for big-data-based medicine models. We tried to use big data analytics to search for similar patients in a cancer cohort, showing how to apply artificial intelligence (AI) algorithms to clinical data processing to obtain clinically significant results, with the ultimate goal of improving healthcare management. Methods: In order to overcome the weaknesses of most data processing algorithms that rely on expert labeling and annotation, we uniformly adopted one-hot encoding for all types of clinical data, calculating the Euclidean distance to measure patient similarity and subgrouping via an unsupervised learning model. Overall survival (OS) was investigated to assess the clinical validity and clinical relevance of the model. Results: We took gastric cancers (GCs) as an example to build a high-dimensional clinical patient similarity network (cPSN). When performing the survival analysis, we found that Cluster_2 had the longest survival rates, while Cluster_5 had the worst prognosis among all the subgroups. As patients in the same subgroup share some clinical characteristics, the clinical feature analysis found that Cluster_2 harbored more lower distal GCs than upper proximal GCs, shedding light on the debates. Conclusion: Overall, we constructed a cancer-specific cPSN with excellent interpretability and clinical significance, which would recapitulate patient similarity in the real-world. The constructed cPSN model is scalable, generalizable, and performs well for various data types.
{"title":"Constructing a Clinical Patient Similarity Network of Gastric Cancer","authors":"Rukui Zhang, Zhaorui Liu, Chaoyu Zhu, Hui Cai, Kai Yin, Fan Zhong, Lei Liu","doi":"10.3390/bioengineering11080808","DOIUrl":"https://doi.org/10.3390/bioengineering11080808","url":null,"abstract":"Objectives: Clinical molecular genetic testing and molecular imaging dramatically increase the quantity of clinical data. Combined with the extensive application of electronic health records, a medical data ecosystem is forming, which calls for big-data-based medicine models. We tried to use big data analytics to search for similar patients in a cancer cohort, showing how to apply artificial intelligence (AI) algorithms to clinical data processing to obtain clinically significant results, with the ultimate goal of improving healthcare management. Methods: In order to overcome the weaknesses of most data processing algorithms that rely on expert labeling and annotation, we uniformly adopted one-hot encoding for all types of clinical data, calculating the Euclidean distance to measure patient similarity and subgrouping via an unsupervised learning model. Overall survival (OS) was investigated to assess the clinical validity and clinical relevance of the model. Results: We took gastric cancers (GCs) as an example to build a high-dimensional clinical patient similarity network (cPSN). When performing the survival analysis, we found that Cluster_2 had the longest survival rates, while Cluster_5 had the worst prognosis among all the subgroups. As patients in the same subgroup share some clinical characteristics, the clinical feature analysis found that Cluster_2 harbored more lower distal GCs than upper proximal GCs, shedding light on the debates. Conclusion: Overall, we constructed a cancer-specific cPSN with excellent interpretability and clinical significance, which would recapitulate patient similarity in the real-world. The constructed cPSN model is scalable, generalizable, and performs well for various data types.","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":null,"pages":null},"PeriodicalIF":3.8,"publicationDate":"2024-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141924169","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-09DOI: 10.3390/bioengineering11080813
Antonio D'Ambrosio, Fatjon Itaj, Filippo Cacace, Vincenzo Piemonte
The objective of this study is to demonstrate the potential of a multicompartmental mathematical model to simulate the activity of the gastrointestinal system after the intake of drugs, with a limited number of parameters. The gastrointestinal system is divided into five compartments, modeled as both continuous systems with discrete events (stomach and duodenum) and systems with delay (jejunum, ileum, and colon). The dissolution of the drug tablet occurs in the stomach and is described through the Noyes-Whitney equation, with pH dependence expressed through the Henderson-Hasselbach relationship. The boluses resulting from duodenal activity enter the jejunum, ileum, and colon compartments, where drug absorption takes place as blood flows countercurrent. The model includes only three parameters with assigned physiological meanings. It was tested and validated using data from in vivo experiments. Specifically, the model was tested with the concentration profiles of nine different drugs and validated using data from two drugs with varying initial concentrations. Overall, the outputs of the model are in good agreement with experimental data, particularly with regard to the time of peak concentration. The primary sources of discrepancy were identified in the concentration decay. The model's main strength is its relatively low computational cost, making it a potentially excellent tool for in silico assessment and prediction of drug adsorption in the intestine.
{"title":"Mathematical Modeling of the Gastrointestinal System for Preliminary Drug Absorption Assessment.","authors":"Antonio D'Ambrosio, Fatjon Itaj, Filippo Cacace, Vincenzo Piemonte","doi":"10.3390/bioengineering11080813","DOIUrl":"https://doi.org/10.3390/bioengineering11080813","url":null,"abstract":"<p><p>The objective of this study is to demonstrate the potential of a multicompartmental mathematical model to simulate the activity of the gastrointestinal system after the intake of drugs, with a limited number of parameters. The gastrointestinal system is divided into five compartments, modeled as both continuous systems with discrete events (stomach and duodenum) and systems with delay (jejunum, ileum, and colon). The dissolution of the drug tablet occurs in the stomach and is described through the Noyes-Whitney equation, with pH dependence expressed through the Henderson-Hasselbach relationship. The boluses resulting from duodenal activity enter the jejunum, ileum, and colon compartments, where drug absorption takes place as blood flows countercurrent. The model includes only three parameters with assigned physiological meanings. It was tested and validated using data from in vivo experiments. Specifically, the model was tested with the concentration profiles of nine different drugs and validated using data from two drugs with varying initial concentrations. Overall, the outputs of the model are in good agreement with experimental data, particularly with regard to the time of peak concentration. The primary sources of discrepancy were identified in the concentration decay. The model's main strength is its relatively low computational cost, making it a potentially excellent tool for in silico assessment and prediction of drug adsorption in the intestine.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":null,"pages":null},"PeriodicalIF":3.8,"publicationDate":"2024-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11352181/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142091739","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-09DOI: 10.3390/bioengineering11080810
I. Manole, A. Butacu, Raluca Nicoleta Bejan, G. Tiplica
Background: Despite recent advancements, medical technology has not yet reached its peak. Precision medicine is growing rapidly, thanks to machine learning breakthroughs powered by increased computational capabilities. This article explores a deep learning application for computer-aided diagnosis in dermatology. Methods: Using a custom model based on EfficientNetB3 and deep learning, we propose an approach for skin lesion classification that offers superior results with smaller, cheaper, and faster inference times compared to other models. The skin images dataset used for this research includes 8222 files selected from the authors’ collection and the ISIC 2019 archive, covering six dermatological conditions. Results: The model achieved 95.4% validation accuracy in four categories—melanoma, basal cell carcinoma, benign keratosis-like lesions, and melanocytic nevi—using an average of 1600 images per category. Adding two categories with fewer images (about 700 each)—squamous cell carcinoma and actinic keratoses—reduced the validation accuracy to 88.8%. The model maintained accuracy on new clinical test images taken under the same conditions as the training dataset. Conclusions: The custom model demonstrated excellent performance on the diverse skin lesions dataset, with significant potential for further enhancements.
{"title":"Enhancing Dermatological Diagnostics with EfficientNet: A Deep Learning Approach","authors":"I. Manole, A. Butacu, Raluca Nicoleta Bejan, G. Tiplica","doi":"10.3390/bioengineering11080810","DOIUrl":"https://doi.org/10.3390/bioengineering11080810","url":null,"abstract":"Background: Despite recent advancements, medical technology has not yet reached its peak. Precision medicine is growing rapidly, thanks to machine learning breakthroughs powered by increased computational capabilities. This article explores a deep learning application for computer-aided diagnosis in dermatology. Methods: Using a custom model based on EfficientNetB3 and deep learning, we propose an approach for skin lesion classification that offers superior results with smaller, cheaper, and faster inference times compared to other models. The skin images dataset used for this research includes 8222 files selected from the authors’ collection and the ISIC 2019 archive, covering six dermatological conditions. Results: The model achieved 95.4% validation accuracy in four categories—melanoma, basal cell carcinoma, benign keratosis-like lesions, and melanocytic nevi—using an average of 1600 images per category. Adding two categories with fewer images (about 700 each)—squamous cell carcinoma and actinic keratoses—reduced the validation accuracy to 88.8%. The model maintained accuracy on new clinical test images taken under the same conditions as the training dataset. Conclusions: The custom model demonstrated excellent performance on the diverse skin lesions dataset, with significant potential for further enhancements.","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":null,"pages":null},"PeriodicalIF":3.8,"publicationDate":"2024-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141921817","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-09DOI: 10.3390/bioengineering11080812
Yu Li, Liwen Zou, Jiajia Song, Kailin Gong
Ultrasound imaging is vital for diagnosing carotid artery vascular lesions, highlighting the importance of accurately segmenting lumens in ultrasound images to prevent, diagnose and treat vascular diseases. However, noise artifacts, blood residue and discontinuous lumens significantly affect segmentation accuracy. To achieve accurate lumen segmentation in low-quality images, we propose a novel segmentation algorithm which is guided by an adaptively generated shape prior. To tackle the above challenges, we introduce a shape-prior-based segmentation method for carotid artery lumen walls. The shape prior in this study is adaptively generated based on the evolutionary trend of vessel growth. Shape priors guide and constrain the active contour, resulting in precise segmentation. The efficacy of the proposed model was confirmed using 247 carotid artery ultrasound images, with experimental results showing an average Dice coefficient of 92.38%, demonstrating superior segmentation performance compared to existing mathematical models. Our method can quickly and effectively perform accurate lumen segmentation on low-quality carotid artery ultrasound images, which is of great significance for the diagnosis of cardiovascular and cerebrovascular diseases.
{"title":"Automated Lumen Segmentation in Carotid Artery Ultrasound Images Based on Adaptive Generated Shape Prior.","authors":"Yu Li, Liwen Zou, Jiajia Song, Kailin Gong","doi":"10.3390/bioengineering11080812","DOIUrl":"https://doi.org/10.3390/bioengineering11080812","url":null,"abstract":"<p><p>Ultrasound imaging is vital for diagnosing carotid artery vascular lesions, highlighting the importance of accurately segmenting lumens in ultrasound images to prevent, diagnose and treat vascular diseases. However, noise artifacts, blood residue and discontinuous lumens significantly affect segmentation accuracy. To achieve accurate lumen segmentation in low-quality images, we propose a novel segmentation algorithm which is guided by an adaptively generated shape prior. To tackle the above challenges, we introduce a shape-prior-based segmentation method for carotid artery lumen walls. The shape prior in this study is adaptively generated based on the evolutionary trend of vessel growth. Shape priors guide and constrain the active contour, resulting in precise segmentation. The efficacy of the proposed model was confirmed using 247 carotid artery ultrasound images, with experimental results showing an average Dice coefficient of 92.38%, demonstrating superior segmentation performance compared to existing mathematical models. Our method can quickly and effectively perform accurate lumen segmentation on low-quality carotid artery ultrasound images, which is of great significance for the diagnosis of cardiovascular and cerebrovascular diseases.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":null,"pages":null},"PeriodicalIF":3.8,"publicationDate":"2024-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11352051/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142091797","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Surface electromyography (sEMG) is commonly used as an interface in human–machine interaction systems due to their high signal-to-noise ratio and easy acquisition. It can intuitively reflect motion intentions of users, thus is widely applied in gesture recognition systems. However, wearable sEMG-based gesture recognition systems are susceptible to changes in environmental noise, electrode placement, and physiological characteristics. This could result in significant performance degradation of the model in inter-session scenarios, bringing a poor experience to users. Currently, for noise from environmental changes and electrode shifting from wearing variety, numerous studies have proposed various data-augmentation methods and highly generalized networks to improve inter-session gesture recognition accuracy. However, few studies have considered the impact of individual physiological states. In this study, we assumed that user exercise could cause changes in muscle conditions, leading to variations in sEMG features and subsequently affecting the recognition accuracy of model. To verify our hypothesis, we collected sEMG data from 12 participants performing the same gesture tasks before and after exercise, and then used Linear Discriminant Analysis (LDA) for gesture classification. For the non-exercise group, the inter-session accuracy declined only by 2.86%, whereas that of the exercise group decreased by 13.53%. This finding proves that exercise is indeed a critical factor contributing to the decline in inter-session model performance.
{"title":"Effects of Exercise on the Inter-Session Accuracy of sEMG-Based Hand Gesture Recognition","authors":"Xiangyu Liu, Chenyun Dai, Jionghui Liu, Yangyang Yuan","doi":"10.3390/bioengineering11080811","DOIUrl":"https://doi.org/10.3390/bioengineering11080811","url":null,"abstract":"Surface electromyography (sEMG) is commonly used as an interface in human–machine interaction systems due to their high signal-to-noise ratio and easy acquisition. It can intuitively reflect motion intentions of users, thus is widely applied in gesture recognition systems. However, wearable sEMG-based gesture recognition systems are susceptible to changes in environmental noise, electrode placement, and physiological characteristics. This could result in significant performance degradation of the model in inter-session scenarios, bringing a poor experience to users. Currently, for noise from environmental changes and electrode shifting from wearing variety, numerous studies have proposed various data-augmentation methods and highly generalized networks to improve inter-session gesture recognition accuracy. However, few studies have considered the impact of individual physiological states. In this study, we assumed that user exercise could cause changes in muscle conditions, leading to variations in sEMG features and subsequently affecting the recognition accuracy of model. To verify our hypothesis, we collected sEMG data from 12 participants performing the same gesture tasks before and after exercise, and then used Linear Discriminant Analysis (LDA) for gesture classification. For the non-exercise group, the inter-session accuracy declined only by 2.86%, whereas that of the exercise group decreased by 13.53%. This finding proves that exercise is indeed a critical factor contributing to the decline in inter-session model performance.","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":null,"pages":null},"PeriodicalIF":3.8,"publicationDate":"2024-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141922907","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}