Medical & Biological Engineering & Computing最新文献

Purpose: In silico trials using computational modeling and simulations can complement clinical trials to improve the time-to-market of complex cardiovascular devices in humans. This study aims to investigate the significance of synthetic data in developing in silico trials for assessing the safety and efficacy of cardiovascular devices, focusing on bioprostheses designed for transcatheter aortic valve implantation (TAVI).

Methods: A statistical shape model (SSM) was employed to extract uncorrelated shape features from TAVI patients, enabling the augmentation of the original patient population into a clinically validated synthetic cohort. Machine learning techniques were utilized not only for risk stratification and classification but also for predicting the physiological variability within the original patient population.

Results: By randomly varying the statistical shape modes within a range of ± 2σ, a hundred virtual patients were generated, forming the synthetic cohort. Validation against the original patient population was conducted using morphological measurements. Support vector machine regression, based on selected shape modes (principal component scores), effectively predicted the peak pressure gradient across the stenosis (R-squared of 0.551 and RMSE of 11.67 mmHg). Multilayer perceptron neural network accurately predicted the optimal device size for implantation with high sensitivity and specificity (AUC = 0.98).

Conclusion: The study highlights the potential of integrating computational predictions, advanced machine learning techniques, and synthetic data generation to improve predictive accuracy and assess TAVI-related outcomes through in silico trials.

The counting and characterization of neurons in primary cultures have long been areas of significant scientific interest due to their multifaceted applications, ranging from neuronal viability assessment to the study of neuronal development. Traditional methods, often relying on fluorescence or colorimetric staining and manual segmentation, are time consuming, labor intensive, and prone to error, raising the need for the development of automated and reliable methods. This paper delves into the evaluation of three pivotal deep learning techniques: semantic segmentation, which allows for pixel-level classification and is solely suited for characterization; object detection, which focuses on counting and locating neurons; and instance segmentation, which amalgamates the features of the other two but employing more intricate structures. The goal of this research is to discern what technique or combination of those techniques yields the optimal results for automatic counting and characterization of neurons in images of neuronal cultures. Following rigorous experimentation, we conclude that instance segmentation stands out, providing superior outcomes for both challenges.

The aim of this study was to investigate and compare the biomechanical properties of the conventional and novel hip prosthetic socket by using the finite element and gait analysis. According to the CT scan model of the subject's residual limb, the bones, soft tissues, and the socket model were reconstructed in three dimensions by using inverse modeling. The distribution of normal and shear stresses at the residual limb-socket interface under the standing condition was investigated using the finite element method and verified by designing a pressure acquisition module system. The gait experiment compared and analyzed the conventional and novel sockets. The results show that the simulation results are consistent with the experimental data. The novel socket exhibited superior stress performance and gait outcomes compared to the conventional design. Our findings provide a research basis for evaluating the comfort of the hip prosthetic socket, optimizing and designing the structure of the socket of the hip.

Heart failure represents the ultimate stage in the progression of diverse cardiac ailments. Throughout the management of heart failure, physicians require observation of medical imagery to formulate therapeutic regimens for patients. Automated report generation technology serves as a tool aiding physicians in patient management. However, previous studies failed to generate targeted reports for specific diseases. To produce high-quality medical reports with greater relevance across diverse conditions, we introduce an automatic report generation model HF-CMN, tailored to heart failure. Firstly, the generated report includes comprehensive information pertaining to heart failure gleaned from chest radiographs. Additionally, we construct a storage query matrix grouping based on a multi-label type, enhancing the accuracy of our model in aligning images with text. Experimental results demonstrate that our method can generate reports strongly correlated with heart failure and outperforms most other advanced methods on benchmark datasets MIMIC-CXR and IU X-Ray. Further analysis confirms that our method achieves superior alignment between images and texts, resulting in higher-quality reports.

In response to the challenge of low accuracy in retinal vessel segmentation attributed to the minute nature of the vessels, this paper proposes a retinal vessel segmentation model based on an improved U-Net, which combines multi-scale feature extraction and fusion techniques. An improved dilated residual module was first used to replace the original convolutional layer of U-Net, and this module, coupled with a dual attention mechanism and diverse expansion rates, facilitates the extraction of multi-scale vascular features. Moreover, an adaptive feature fusion module was added at the skip connections of the model to improve vessel connectivity. To further optimize network training, a hybrid loss function is employed to mitigate the class imbalance between vessels and the background. Experimental results on the DRIVE dataset and CHASE_DB1 dataset show that the proposed model has an accuracy of 96.27% and 96.96%, sensitivity of 81.32% and 82.59%, and AUC of 98.34% and 98.70%, respectively, demonstrating superior segmentation performance.

Using echocardiography to assess the left ventricular function is one of the most crucial cardiac examinations in clinical diagnosis, and LV segmentation plays a particularly vital role in medical image processing as many important clinical diagnostic parameters are derived from the segmentation results, such as ejection function. However, echocardiography typically has a lower resolution and contains a significant amount of noise and motion artifacts, making it a challenge to accurate segmentation, especially in the region of the cardiac chamber boundary, which significantly restricts the accurate calculation of subsequent clinical parameters. In this paper, our goal is to achieve accurate LV segmentation through a simplified approach by introducing a branch sub-network into the decoder of the traditional U-Net. Specifically, we employed the LV contour features to supervise the branch decoding process and used a cross attention module to facilitate the interaction relationship between the branch and the original decoding process, thereby improving the segmentation performance in the region LV boundaries. In the experiments, the proposed branch U-Net (BU-Net) demonstrated superior performance on CAMUS and EchoNet-dynamic public echocardiography segmentation datasets in comparison to state-of-the-art segmentation models, without the need for complex residual connections or transformer-based architectures. Our codes are publicly available at Anonymous Github https://anonymous.4open.science/r/Anoymous_two-BFF2/ .

With the rapid advancement of modern medical technology, microscopy imaging systems have become one of the key technologies in medical image analysis. However, manual use of microscopes presents issues such as operator dependency, inefficiency, and time consumption. To enhance the efficiency and accuracy of medical image capture and reduce the burden of subsequent quantitative analysis, this paper proposes an improved microscope salient object detection algorithm based on U²-Net, incorporating deep learning technology. The improved algorithm first enhances the network's key information extraction capability by incorporating the Convolutional Block Attention Module (CBAM) into U²-Net. It then optimizes network complexity by constructing a Simple Pyramid Pooling Module (SPPM) and uses Ghost convolution to achieve model lightweighting. Additionally, data augmentation is applied to the slides to improve the algorithm's robustness and generalization. The experimental results show that the size of the improved algorithm model is 72.5 MB, which represents a 56.85% reduction compared to the original U²-Net model size of 168.0 MB. Additionally, the model's prediction accuracy has increased from 92.24 to 97.13%, providing an efficient means for subsequent image processing and analysis tasks in microscopy imaging systems.

Diabetic retinopathy is a chronic disease of the eye that is precipitated via diabetes. As the disease progresses, the blood vessels in the retina are issue to modifications such as dilation, leakage, and new blood vessel formation. Early detection and treatment of the lesions are vital for the prevention and reduction of imaginative and prescient loss. A new dual-path multi-module network algorithm for diabetic retinopathy classification is proposed in this paper, aiming to accurately classify the diabetic retinopathy stage to facilitate early diagnosis and intervention. To obtain the purpose of fact augmentation, the algorithm first enhances retinal lesion features using color correcting and multi-scale fusion algorithms. It then optimizes the local records via a multi-path multiplexing structure with convolutional kernels of exclusive sizes. Finally, a multi-feature fusion module is used to improve the accuracy of the diabetic retinopathy classification model. Two public datasets and a real hospital dataset are used to validate the algorithm. The accuracy is 98.9%, 99.3%, and 98.3%, respectively. The experimental results not only confirm the advancement and practicability of the algorithm in the field of automatic DR diagnosis, but also foretell its broad application prospects in clinical settings, which is expected to provide strong technical support for the early screening and treatment of diabetic retinopathy.

Inert gas washout methods have been shown to detect pathological changes in the small airways that occur in the early stages of obstructive lung diseases such as asthma and COPD. Numerical lung models support the analysis of characteristic washout curves, but are limited in their ability to simulate the complexity of lung anatomy over an appropriate time period. Therefore, the interpretation of patient-specific washout data remains a challenge. A new numerical lung model is presented in which electrical components describe the anatomical and physiological characteristics of the lung as well as gas-specific properties. To verify that the model is able to reproduce characteristic washout curves, the phase 3 slopes (S₃) of helium washouts are simulated using simple asymmetric lung anatomies consisting of two parallel connected lung units with volume ratios of $\frac{1.25}{0.75}$ , $\frac{1.50}{0.50}$ , and $\frac{1.75}{0.25}$ and a total volume flow of 250 ml/s which are evaluated for asymmetries in both the convection- and diffusion-dominated zone of the lung. The results show that the model is able to reproduce the S₃ for helium and thus the processes underlying the washout methods, so that electrical components can be used to model these methods. This approach could form the basis of a hardware-based real-time simulator.

Segmentation of organs at risks (OARs) in the thorax plays a critical role in radiation therapy for lung and esophageal cancer. Although automatic segmentation of OARs has been extensively studied, it remains challenging due to the varying sizes and shapes of organs, as well as the low contrast between the target and background. This paper proposes a cascaded FAS-UNet+ framework, which integrates convolutional neural networks and nonlinear multi-grid theory to solve a modified Mumford-shah model for segmenting OARs. This framework is equipped with an enhanced iteration block, a coarse-to-fine multiscale architecture, an iterative optimization strategy, and a model ensemble technique. The enhanced iteration block aims to extract multiscale features, while the cascade module is used to refine coarse segmentation predictions. The iterative optimization strategy improves the network parameters to avoid unfavorable local minima. An efficient data augmentation method is also developed to train the network, which significantly improves its performance. During the prediction stage, a weighted ensemble technique combines predictions from multiple models to refine the final segmentation. The proposed cascaded FAS-UNet+ framework was evaluated on the SegTHOR dataset, and the results demonstrate significant improvements in Dice score and Hausdorff Distance (HD). The Dice scores were 95.22%, 95.68%, and HD values were 0.1024, and 0.1194 for the segmentations of the aorta and heart in the official unlabeled dataset, respectively. Our code and trained models are available at https://github.com/zhuhui100/C-FASUNet-plus .