Bioengineering最新文献

{"title":"Progress in the Application of Artificial Intelligence in Ultrasound-Assisted Medical Diagnosis.","authors":"Li Yan, Qing Li, Kang Fu, Xiaodong Zhou, Kai Zhang","doi":"10.3390/bioengineering12030288","DOIUrl":"10.3390/bioengineering12030288","url":null,"abstract":"<p><p>The integration of artificial intelligence (AI) into ultrasound medicine has revolutionized medical imaging, enhancing diagnostic accuracy and clinical workflows. This review focuses on the applications, challenges, and future directions of AI technologies, particularly machine learning (ML) and its subset, deep learning (DL), in ultrasound diagnostics. By leveraging advanced algorithms such as convolutional neural networks (CNNs), AI has significantly improved image acquisition, quality assessment, and objective disease diagnosis. AI-driven solutions now facilitate automated image analysis, intelligent diagnostic assistance, and medical education, enabling precise lesion detection across various organs while reducing physician workload. AI's error detection capabilities further enhance diagnostic accuracy. Looking ahead, the integration of AI with ultrasound is expected to deepen, promoting trends in standardization, personalized treatment, and intelligent healthcare, particularly in underserved areas. Despite its potential, comprehensive assessments of AI's diagnostic accuracy and ethical implications remain limited, necessitating rigorous evaluations to ensure effectiveness in clinical practice. This review provides a systematic evaluation of AI technologies in ultrasound medicine, highlighting their transformative potential to improve global healthcare outcomes.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":"12 3","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11939760/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143728087","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}

{"title":"Deep Multi-Modal Skin-Imaging-Based Information-Switching Network for Skin Lesion Recognition.","authors":"Yingzhe Yu, Huiqiong Jia, Li Zhang, Suling Xu, Xiaoxia Zhu, Jiucun Wang, Fangfang Wang, Lianyi Han, Haoqiang Jiang, Qiongyan Zhou, Chao Xin","doi":"10.3390/bioengineering12030282","DOIUrl":"10.3390/bioengineering12030282","url":null,"abstract":"<p><p>The rising prevalence of skin lesions places a heavy burden on global health resources and necessitates an early and precise diagnosis for successful treatment. The diagnostic potential of recent multi-modal skin lesion detection algorithms is limited because they ignore dynamic interactions and information sharing across modalities at various feature scales. To address this, we propose a deep learning framework, Multi-Modal Skin-Imaging-based Information-Switching Network (MDSIS-Net), for end-to-end skin lesion recognition. MDSIS-Net extracts intra-modality features using transfer learning in a multi-scale fully shared convolutional neural network and introduces an innovative information-switching module. A cross-attention mechanism dynamically calibrates and integrates features across modalities to improve inter-modality associations and feature representation in this module. MDSIS-Net is tested on clinical disfiguring dermatosis data and the public Derm7pt melanoma dataset. A Visually Intelligent System for Image Analysis (VISIA) captures five modalities: spots, red marks, ultraviolet (UV) spots, porphyrins, and brown spots for disfiguring dermatosis. The model performs better than existing approaches with an mAP of 0.967, accuracy of 0.960, precision of 0.935, recall of 0.960, and f1-score of 0.947. Using clinical and dermoscopic pictures from the Derm7pt dataset, MDSIS-Net outperforms current benchmarks for melanoma, with an mAP of 0.877, accuracy of 0.907, precision of 0.911, recall of 0.815, and f1-score of 0.851. The model's interpretability is proven by Grad-CAM heatmaps correlating with clinical diagnostic focus areas. In conclusion, our deep multi-modal information-switching model enhances skin lesion identification by capturing relationship features and fine-grained details across multi-modal images, improving both accuracy and interpretability. This work advances clinical decision making and lays a foundation for future developments in skin lesion diagnosis and treatment.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":"12 3","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11939189/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143727801","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}

{"title":"Transcranial Direct Current Stimulation Can Modulate Brain Complexity and Connectivity in Children with Autism Spectrum Disorder: Insights from Entropy Analysis.","authors":"Jiannan Kang, Pengfei Hao, Haiyan Gu, Yukun Liu, Xiaoli Li, Xinling Geng","doi":"10.3390/bioengineering12030283","DOIUrl":"10.3390/bioengineering12030283","url":null,"abstract":"<p><p>The core characteristics of autism spectrum disorder (ASD) are atypical neurodevelopmental disorders. Transcranial direct current stimulation (tDCS), as a non-invasive brain stimulation technique, has been applied in the treatment of various neurodevelopmental disorders. Entropy analysis methods can quantitatively describe the complexity of EEG signals and information transfer. This study recruited 24 children with ASD and 24 age- and gender-matched typically developing (TD) children, using multiple entropy methods to analyze differences in brain complexity and effective connectivity between the two groups. Furthermore, this study explored the regulatory effect of tDCS on brain complexity and effective connectivity in children with ASD. The results showed that children with ASD had lower brain complexity, with excessive effective connectivity in the δ, θ, and α frequency bands and insufficient effective connectivity in the β frequency band. After tDCS intervention, the brain complexity of children with ASD significantly increased, while effective connectivity in the δ and θ frequency bands significantly decreased. The results from behavioral-scale assessments also indicated positive behavioral changes. These findings suggest that tDCS may improve brain function in children with ASD by regulating brain complexity and effective connectivity, leading to behavioral improvements, and they provide new perspectives and directions for intervention research in ASD.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":"12 3","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11939205/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143728047","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}

{"title":"Wearable Soft Robots: Case Study of Using Shape Memory Alloys in Rehabilitation.","authors":"Zain Shami, Tughrul Arslan, Peter Lomax","doi":"10.3390/bioengineering12030276","DOIUrl":"10.3390/bioengineering12030276","url":null,"abstract":"<p><p>Shape Memory Alloys (SMAs) have emerged as a promising actuation technology for wearable rehabilitation robots due to their unique properties, including the shape memory effect, high actuation stress, pseudoelasticity, and three-dimensional actuation. With a significantly higher Young's modulus than biological tissues, SMAs enable efficient and responsive interaction with the human body, making them well suited for musculoskeletal rehabilitation applications. This paper provides a comprehensive review of SMA-based wearable devices for both upper- and lower-limb rehabilitation. It explores their configurations, actuation mechanisms, associated challenges, and optimization strategies to enhance performance. By discussing recent advancements, this review aims to inform researchers and engineers on the development of sustainable, effective, and patient-centric wearable rehabilitation robots.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":"12 3","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11939777/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143728057","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}

{"title":"Dynamic Frequency-Decoupled Refinement Network for Polyp Segmentation.","authors":"Yao Tong, Jingxian Chai, Ziqi Chen, Zuojian Zhou, Yun Hu, Xin Li, Xuebin Qiao, Kongfa Hu","doi":"10.3390/bioengineering12030277","DOIUrl":"10.3390/bioengineering12030277","url":null,"abstract":"<p><p>Polyp segmentation is crucial for early colorectal cancer detection, but accurately delineating polyps is challenging due to their variations in size, shape, and texture and low contrast with surrounding tissues. Existing methods often rely solely on spatial-domain processing, which struggles to separate high-frequency features (edges, textures) from low-frequency ones (global structures), leading to suboptimal segmentation performance. We propose the Dynamic Frequency-Decoupled Refinement Network (DFDRNet), a novel segmentation framework that integrates frequency-domain and spatial-domain processing. DFDRNet introduces the Frequency Adaptive Decoupling (FAD) module, which dynamically separates high- and low-frequency components, and the Frequency Adaptive Refinement (FAR) module, which refines these components before fusing them with spatial features to enhance segmentation accuracy. Embedded within a U-shaped encoder-decoder framework, DFDRNet achieves state-of-the-art performance across three benchmark datasets, demonstrating superior robustness and efficiency. Our extensive evaluations and ablation studies confirm the effectiveness of DFDRNet in balancing segmentation accuracy with computational efficiency.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":"12 3","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11939780/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143727893","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}

{"title":"Real-Time Object Detector for Medical Diagnostics (RTMDet): A High-Performance Deep Learning Model for Brain Tumor Diagnosis.","authors":"Sanjar Bakhtiyorov, Sabina Umirzakova, Musabek Musaev, Akmalbek Abdusalomov, Taeg Keun Whangbo","doi":"10.3390/bioengineering12030274","DOIUrl":"10.3390/bioengineering12030274","url":null,"abstract":"<p><strong>Background: </strong>Brain tumor diagnosis requires precise and timely detection, which directly impacts treatment decisions and patient outcomes. The integration of deep learning technologies in medical diagnostics has improved the accuracy and efficiency of these processes, yet real-time processing remains a challenge due to the computational intensity of current models. This study introduces the Real-Time Object Detector for Medical Diagnostics (RTMDet), which aims to address these limitations by optimizing convolutional neural network (CNN) architectures for enhanced speed and accuracy.</p><p><strong>Methods: </strong>The RTMDet model incorporates novel depthwise convolutional blocks designed to reduce computational load while maintaining diagnostic precision. The effectiveness of the RTMDet was evaluated through extensive testing against traditional and modern CNN architectures using comprehensive medical imaging datasets, with a focus on real-time processing capabilities.</p><p><strong>Results: </strong>The RTMDet demonstrated superior performance in detecting brain tumors, achieving higher accuracy and speed compared to existing CNN models. The model's efficiency was validated through its ability to process large datasets in real time without sacrificing the accuracy required for a reliable diagnosis.</p><p><strong>Conclusions: </strong>The RTMDet represents a significant advancement in the application of deep learning technologies to medical diagnostics. By optimizing the balance between computational efficiency and diagnostic precision, the RTMDet enhances the capabilities of medical imaging, potentially improving patient outcomes through faster and more accurate brain tumor detection. This model offers a promising solution for clinical settings where rapid and precise diagnostics are critical.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":"12 3","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11939674/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143727810","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}

{"title":"Vortex Dynamics in the Sinus of Valsalva.","authors":"Jiaxuan Fan, Elias Sundström","doi":"10.3390/bioengineering12030279","DOIUrl":"10.3390/bioengineering12030279","url":null,"abstract":"<p><p>Patients undergoing aortic valve repair or replacement with associated alterations in stiffness characteristics often develop abnormalities in the aortic sinus vortex, which may impact aortic valve function. The correlation between altered aortic sinus vortex and aortic valve function remains poorly understood due to the complex fluid dynamics in the aortic valve and the challenges in simulating these conditions. The opening and closure mechanism of the aortic valve is studied using fluid-structure interaction (FSI) simulations, incorporating an idealized aortic valve model. The FSI approach models both the interaction between the fluid flow and the valve's leaflets and the dynamic response of the leaflets during pulsatile flow conditions. Differences in the hemodynamic and vortex dynamic behaviors of aortic valve leaflets with varying stiffness are analyzed. The results reveal that, during the systolic phase, the formation of the sinus vortex is closely coupled with the jet emanating from the aortic valve and the fluttering motion of the leaflets. As leaflet stiffness increases, the peak vorticity of the sinus vortex increases, and the phase space of the vortex core develops a pronounced spiral trajectory. During the diffusion phase, the vortex strength decays exponentially, and the diffusion time is longer for stiffer leaflets, indicating a longer residence time of the sinus vortex that reduces the pressure difference on the leaflet during valve closure. Changes in leaflet stiffness play a critical role in the formation and development of sinus vortices. Furthermore, the dynamic characteristics of vortices directly affect the pressure balance on both sides of the valve leaflets. This pressure difference not only determines the opening and closing processes of the valve but also significantly influences the stability and efficiency of these actions.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":"12 3","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11939515/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143728054","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}

{"title":"Advances in the Study of Age-Related Macular Degeneration Based on Cell or Cell-Biomaterial Scaffolds.","authors":"Ziming Li, Zhiyong Hu, Zhixian Gao","doi":"10.3390/bioengineering12030278","DOIUrl":"10.3390/bioengineering12030278","url":null,"abstract":"<p><p>Age-related macular degeneration (AMD), a progressive neurodegenerative disorder affecting the central retina, is pathologically defined by the irreversible degeneration of photoreceptors and retinal pigment epithelium (RPE), coupled with extracellular drusen deposition and choroidal neovascularization (CNV), and AMD constitutes the predominant etiological factor for irreversible vision impairment in adults aged ≥60 years. Cell-based or cell-biomaterial scaffold-based approaches have been popular in recent years as a major research direction for AMD; monotherapy with cell-based approaches typically involves subretinal injection of progenitor-derived or stem cell-derived RPE cells to restore retinal homeostasis. Meanwhile, cell-biomaterial scaffolds delivered to the lesion site by vector transplantation have been widely developed, and the implanted cell-biomaterial scaffolds can promote the reintegration of cells at the lesion site and solve the problems of translocation and discrete cellular structure produced by cell injection. While these therapeutic strategies demonstrate preliminary efficacy, rigorous preclinical validation and clinical trials remain imperative to validate their long-term safety, functional durability, and therapeutic consistency. This review synthesizes current advancements and translational challenges in cell-based and cell-biomaterial scaffold approaches for AMD, aiming to inform future development of targeted interventions for AMD pathogenesis and management.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":"12 3","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11939329/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143727747","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}

{"title":"Can Infrared Thermal Imaging Reflect Exercise Load? An Incremental Cycling Exercise Study.","authors":"Chenxi Hu, Ning Du, Zhongqian Liu, Yafeng Song","doi":"10.3390/bioengineering12030280","DOIUrl":"10.3390/bioengineering12030280","url":null,"abstract":"<p><p>Monitoring the training load is crucial in sports science research, as it provides scientific evidence for assessing training effects, optimizing athletic performance, and preventing overtraining by quantifying both external and internal loads. Although traditional monitoring methods have made significant progress, infrared thermography (IRT) technology, with its non-contact, real-time, and non-invasive characteristics, is gradually emerging as an effective tool for evaluating the relationship between the training load and physiological responses. This study evaluated 31 healthy male adults (age 21.9 ± 2.7 years, weight 75 ± 8.26 kg, and training duration 240 ± 65 min/week) performing incremental exhaustive exercise on a cycle ergometer (with a 60W starting load, increasing by 20W per minute). Entropy analysis was used to quantitatively assess the surface radiation patterns of regions of interest (forehead, chest, and abdomen) obtained through thermal imaging. Compared to baseline, significant differences in the surface radiation patterns of the regions of interest were observed at the point of exhaustion (<i>p</i> ≤ 0.01). Correlation analysis revealed strong associations between the external load, oxygen consumption, and chest temperature entropy (r = 0.973 and 0.980). Cluster analysis of the chest entropy, external load, and oxygen consumption showed a non-linear increasing trend in their inter-relationships. Further individual analysis demonstrated positive correlations between the percentage increase in the chest entropy and both the external load (r = 0.70-0.98) and oxygen consumption (r = 0.65-0.97). Entropy analysis offers a new approach for quantitatively assessing surface radiation patterns from infrared thermography, and reveals the coupling relationship between thermoregulation and metabolic responses during exercise.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":"12 3","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11939500/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143727773","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}

{"title":"Enhanced Skin Disease Classification via Dataset Refinement and Attention-Based Vision Approach.","authors":"Muhammad Nouman Noor, Farah Haneef, Imran Ashraf, Muhammad Masud","doi":"10.3390/bioengineering12030275","DOIUrl":"10.3390/bioengineering12030275","url":null,"abstract":"<p><p>Skin diseases are listed among the most frequently encountered diseases. Skin diseases such as eczema, melanoma, and others necessitate early diagnosis to avoid further complications. This study aims to enhance the diagnosis of skin disease by utilizing advanced image processing techniques and an attention-based vision approach to support dermatologists in solving classification problems. Initially, the image is being passed through various processing steps to enhance the quality of the dataset. These steps are adaptive histogram equalization, binary cross-entropy with implicit averaging, gamma correction, and contrast stretching. Afterwards, enhanced images are passed through the attention-based approach for performing classification which is based on the encoder part of the transformers and multi-head attention. Extensive experimentation is performed to collect the various results on two publicly available datasets to show the robustness of the proposed approach. The evaluation of the proposed approach on two publicly available datasets shows competitive results as compared to a state-of-the-art approach.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":"12 3","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11939559/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143727787","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}