Biomedical Physics & Engineering Express最新文献

In this paper, an automated feature selection (FS) method is presented to optimize machine learning (ML) models' performances, enhancing early keratoconus screening. A total of 448 parameters were analyzed from a dataset comprising 3162 observations sourced from the swept source optical coherence tomography imaging system developed by the Chinese Academy of Sciences Institute of Automation (SS-1000 CASIA OCT) and electronic health records (EHR). To identify the most relevant features, the analysis of variance (ANOVA) method was used in this study. The performance of three classifiers namely K-Nearest Neighbors (KNN), Support Vector Machine (SVM), and Artificial Neural Networks (ANN) was evaluated, yielding classification accuracies of 96.79% and 96.68% for KNN, 98.95% and 97.08% for SVM, and 95.64% and 95.62% for ANN when distinguishing between 2 and 4 keratoconus classes, respectively. The results show that selecting 50 features can significantly improve the performance of the model while reducing the computation time. The automated feature selection method can also assist ophthalmologists in better understanding the links between various ocular characteristics and keratoconus, potentially leading to advances in early diagnosis, risk prediction, and clinical management of this condition.

Polyps are one of the early stages of colon cancer. The detection of polyps by segmentation and their removal by surgical intervention is of great importance for making treatment decisions. Although the detection of polyps through colonoscopy images can lead to multiple expert needs and time losses, it can also include human error. Therefore, automatic, fast, and highly accurate segmentation of polyps from colonoscopy images is important. Many methods have been proposed, including deep learning-based approaches. In this study, a method using DeepLabv3+ with encoder-decoder structure and ResNet architecture as backbone network is proposed for the segmentation of colonic polyps. The Kvasir-SEG polyp dataset was used to train and test the proposed method. After images were preprocessed, the training of the proposed network was performed. The trained network was then tested and performance metrics were calculated, and additionally, a GUI (Graphical User Interface) was designed to enable the segmentation of colonoscopy images for polyp segmentation. The experimental results showed that the ResNet-50 based DeepLabv3+ model had high performance metrics such as DSC: 0.9609, mIoU: 0.9246, demonstrating its effectiveness in the segmentation of colonic polyps. In conclusion, our method utilizing DeepLabv3+ with a ResNet-50 backbone achieves highly accurate colonic polyp segmentation. The obtained results demonstrate its potential to significantly enhance colorectal cancer diagnosis and planning for polypectomy surgery through automated image analysis. .

Single-isocenter multitarget (SIMT) stereotactic-radiosurgery (SRS) has recently emerged as a powerful treatment regimen for intracranial tumors. With high specificity, SIMT SRS allows for rapid, high-dose delivery while maintaining integrity of adjacent healthy tissues and minimizing neurocognitive damage to patients. Highly robust and accurate quality assurance (QA) tests are critical to minimize off-targets and damage to surrounding healthy tissues. We have developed a novel QA phantom, named OneIso, to accurately and precisely measure off-axis accuracy, via off-axis Winston-Lutz (OAWL), to assist SIMT SRS programs. In this study, a comparison of three different quantitative numerical methods were performed for isolating and measuring the position of ball-bearings (BBs) used in the OAWL measurement. The three methods evaluated were: 1) feature extraction technique combined with manual intervention 2) a proprietary software utilizing optical image recognition (OIR) techniques, and 3) a machine learning (ML) model employing convolutional neural networks (CNNs). These methods were used to analyze OAWL datasets gathered from a OneIso phantom deployed on a Varian TrueBeam. The precision of localizing positional BBs within the OneIso QA phantom, analysis speed, and robustness were compared across the methods. Significantly, the trained ML model utilizing CNNs was found to exhibit superior precision, analysis speed, and efficiency compared to the other two methods. These results highlight the benefit in shifting from manual and OIR methods to that of ML techniques. The incorporation of CNNs in automated QA analysis can achieve improved precision, allowing for more rapid and wider adoption of SIMT SRS for treating intracranial metastases while preserving integrity of surrounding healthy tissues.

Medical imaging is pivotal in early disease diagnosis, providing essential insights that enable timely and accurate detection of health anomalies. Traditional imaging techniques, such as Magnetic Resonance Imaging (MRI), Computer Tomography (CT), ultrasound, and Positron Emission Tomography (PET), offer vital insights into three-dimensional structures but frequently fall short of delivering a comprehensive and detailed anatomical analysis, capturing only amplitude details. Three-dimensional holography microscopic medical imaging provides a promising solution by capturing the amplitude (brightness) and phase (structural information) details of biological structures. In this study, we investigate the novel collaborative potential of Deep Learning (DL) and holography microscopic phase imaging for cancer diagnosis. The study comprehensively examines existing literature, analyzes advancements, identifies research gaps, and proposes future research directions in cancer diagnosis through the integrated Quantitative Phase Imaging (QPI) and DL methodology. This novel approach addresses a critical limitation of traditional imaging by capturing detailed structural information, paving the way for more accurate diagnostics. The proposed approach comprises tissue sample collection, holographic image scanning, pre-processing in case of imbalanced datasets, and training on annotated datasets using DL architectures like U-Net and Vision Transformer(ViT's). Furthermore, sophisticated concepts in DL, like the incorporation of Explainable AI techniques (XAI), are suggested for comprehensive disease diagnosis and identification. The study thoroughly investigates the advantages of integrating holography imaging and DL for precise cancer diagnosis. Additionally, meticulous insights are presented by identifying the challenges associated with this integration methodology.

Despite new approaches in the treatment of cardiovascular disease (CVD) such as percutaneous coronary intervention, coronary artery bypass graft, and left ventricular assist devices, which cannot fully compensate for the effectiveness of the original heart, heart transplantation still remains as the most effective solution. A growing body of literature recognizes the importance of developing a whole heart constructed from living tissues to provide an alternative option for patients suffering from diseases of the cardiovascular system. A potential solution that shows a promise is to generate cell-free, i.e., decellularized, scaffolds using native heart tissue to be later cellularized and transplanted. This study reports the decellularization process and efficiency in an effort to create a whole heart scaffold. The hearts harvested from rabbits were perfused and the final bioartificial scaffolds were characterized for the efficiency of decellularization in terms of DNA content, collagen, and glycosaminoglycan. The compressive biomechanical properties of decellularized and native hearts were also determined and compared. Findings revealed that the DNA content of decellularized hearts was significantly reduced while keeping collagen and GAG content unchanged. Biomechanical properties of the hearth became inferior upon removal of the nuclear material. Decellularized hearts have significant importance in treating CVD as they serve as bioartificial hearts, providing a more clinically relevant model for potential human use. Future work will focus on the recellularization of the heart using induced pluripotent or embryonic stem cells to test its functionality.

Introduction. Open reduction internal fixation (ORIF) and external fixation are traditional surgical techniques for treating type VI Schatzker tibial plateau fractures. A newly developed technique integrates the intramedullary tibial nail with condylar bolts. This finite element study investigated the mechanical response of three surgical techniques for fixing type VI Schatzker tibial plateau fractures. We compared the intramedullary nail-bolt (IMNB) technique with the single lateral locking plate (SLLP) and dual plating (DP) techniques.Materials and Methods. A 4th generation Sawbone model of a left tibia with a Type VI tibial plateau fracture was scanned using computed tomography and reconstructed into a 3D model. The plates were digitally reconstructed using 3D scanning technology, while the screws, condylar bolt, and nail were replicated using commercial computer-aided design software. An application engineer guided by a surgeon, virtually positioned the bone-implant construct for the three surgical techniques to align with physical constructs from a previousin-vitrobiomechanical study. A commercial finite element analysis software was used for the computer simulation, with the tibial plateau subjected to uniaxial loads at 500, 1000, and 1500 Newton while the distal tip of the tibia remained fixed. Measurements of vertical subsidence, horizontal diastasis, and passive construct stiffness were recorded and compared to those of the previousin-vitrobiomechanical experiment.Results.DP had the highest stiffness, followed by IMNB and SLLP techniques. DP also resulted in smaller values for measured subsidence and diastasis compared to SLLP and IMNB. The simulation results aligned with those of thein-vitrobiomechanical study.Conclusions.The simulation results may further support the initial suggestion of thein-vitrobiomechanical study that the IMNB technique is a biomechanically suitable method for fixing Type VI Schatzker injuries.

The prediction of epileptic seizures is a classical research problem, representing one of the most challenging tasks in the analysis of brain disorders. There is active research into digital twins (DT) for various healthcare applications, as they can transform research into customized and personalized healthcare. The widespread adoption of DT technology relies on ample patient data to ensure precise monitoring and decision-making, leveraging Machine Learning (ML) and Deep Learning (DL) algorithms. Given the non-stationarity of EEG recordings, characterized by substantial frequency variations over time, there is a notable preference for advanced time-frequency methods in seizure prediction. This research proposes a DT-based seizure prediction system by applying an advanced time-frequency analysis approach known as Time-Reassigned MultiSynchroSqueezing Transform (TMSST) to EEG data to extract patient-specific impulse features and subsequently, a Deep Learning strategy, CNN-BiLSTM-Attention mechanism model is utilized in learning and classifying features for seizure prediction. The proposed architecture is named as 'Digital Twin-Net'. By estimating the group delay in the time direction, TMSST produces the frequency components that are responsible for the EEG signal's temporal behavior and those time-frequency signatures are learned by the developed CNN-BiLSTM-Attention mechanism model. Thus the combination acts as a digital twin of a patient for the prediction of epileptic seizures. The experimental results showed that the suggested approach achieved an accuracy of 99.70% when tested on 22 patients from the publicly accessible CHB-MIT dataset. The proposed method surpasses previous solutions in terms of overall performance. Consequently, the suggested method can be regarded as an efficient approach to EEG seizure prediction.

Cardiovascular diseases rank among the leading causes of mortality worldwide and the early identification of diseases is of paramount importance. This work focuses on developing a novel machine learning-based framework for early detection and classification of heart murmurs by analysing phonocardiogram signals. Our heart murmur detection and classification pipeline encompasses three classification settings. We first develop a set of methods based on transfer learning to determine the existence of heart murmurs and categorize them as present, absent, or unknown. If a murmur is present it will be classified as normal or abnormal based on its clinical outcome by using 1D convolution and audio spectrogram transformers. Finally, we use Wav2Vec encoder with raw audio data and AdaBoost abstain classifier for heart murmur quality identification. Heart murmurs are categorized based on their specific attributes, including murmur pitch, murmur shape, and murmur timing which are important for diagnosis. Using the PhysioNet 2022 dataset for training and validation, we achieve an 81.08% validation accuracy for murmur presence classification and a 68.23% validation accuracy for clinical outcome classification with 60.52% sensitivity and 74.46% specificity. The suggested approaches provide a promising framework for using phonocardiogram signals for the detection, classification, and quality analysis of heart murmurs. This has significant implications for the diagnosis and treatment of cardiovascular diseases.

Purpose.This work proposes a new method to assess the performance of radiographic anti-scatter grids (ASGs) without the use of a narrow primary beam, which is difficult to achieve.Method.Three general purpose ASGs were evaluated, two marketed ASGs and a low frequency and high ratio prototype ASG with molybdenum lamellae. A range of high scatter x-ray beams were used in a standardized geometry, with energies ranging from 60 kV to 121 kV, for five beam sizes between 10 × 10 and 30 × 30 cm². The scatter fraction (SF) of each beam was measured in the image plane with and without ASG using the lead beam stop method with an extrapolation function derived from the scatter point spread function (PSF).Results.The primary, scatter and total transmissions of the three ASGs measured for the different x-ray beams allowed the calculation of the grid factor, contrast improvement factor and detective quantum efficiency (DQE) as functions of the input SF. The results obtained for the three ASGs are consistent with those obtained with the standard narrow-beam method and data published in the literature, confirmed the prime importance of the ASG primary transmission and revealed important variations in ASG performance, especially as a function of the input SF and beam size. The break-even input SFs at which the imaging system efficiency was improved by the ASG ranged between 0.18 and 0.52 for the different ASGs and beam characteristics.Significance.The method is proposed as an alternative to current ASG characterization techniques.

Understanding the mechanics of the respiratory system is crucial for optimizing ventilator settings and ensuring patient safety. While simple models of the respiratory system typically consider only flow resistance and lung compliance, lung tissue resistance is usually neglected. This study investigated the effect of lung tissue viscoelasticity on delivered mechanical power in a physical model of the respiratory system and the possibility of distinguishing tissue resistance from airway resistance using proximal pressure measured at the airway opening. Three different configurations of a passive physical model of the respiratory system representing different mechanical properties (Tissue resistance model, Airway resistance model, and No-resistance model) were tested. The same volume-controlled ventilation and parameters were set for each configuration, with only the inspiratory flow rates being adjusted. Pressure and flow were measured with a Datex-Ohmeda S/5 vital signs monitor (Datex-Ohmeda, Madison, WI, USA). Tissue resistance was intentionally tuned so that peak pressures and delivered mechanical energy measured at airway opening were similar in Tissue and Airway Resistance models. However, measurements inside the artificial lung revealed significant differences, with Tissue resistance model yielding up to 20% higher values for delivered mechanical energy. The results indicate the need to revise current methods of calculating mechanical power delivery, which do not distinguish between tissue resistance and airway flow resistance, making it difficult to evaluate and interpret the significance of mechanical power delivery in terms of lung ventilation protectivity.