Biocybernetics and Biomedical Engineering最新文献

A crucial element in the diagnosis of breast cancer is the utilization of a classification method that is efficient, lightweight, and precise. Convolutional neural networks (CNNs) have garnered attention as a viable approach for classifying histopathological images. However, deeper and wider models tend to rely on first-order statistics, demanding substantial computational resources and struggling with fixed kernel dimensions that limit encompassing diverse resolution data, thereby degrading the model’s performance during testing. This study introduces BCHI-CovNet, a novel lightweight artificial intelligence (AI) model for histopathological breast image classification. Firstly, a novel multiscale depth-wise separable convolution is proposed. It is introduced to split input tensors into distinct tensor fragments, each subject to unique kernel sizes integrating various kernel sizes within one depth-wise convolution to capture both low- and high-resolution patterns. Secondly, an additional pooling module is introduced to capture extensive second-order statistical information across the channels and spatial dimensions. This module works in tandem with an innovative multi-head self-attention mechanism to capture the long-range pixels contributing significantly to the learning process, yielding distinctive and discriminative features that further enrich representation and introduce pixel diversity during training. These novel designs substantially reduce computational complexities regarding model parameters and FLOPs, which is crucial for resource-constrained medical devices. The outcomes achieved by employing the suggested model on two openly accessible datasets for breast cancer histopathological images reveal noteworthy performance. Specifically, the proposed approach attains high levels of accuracy: 99.15 % at 40× magnification, 99.08 % at 100× magnification, 99.22 % at 200× magnification, and 98.87 % at 400× magnification on the BreaKHis dataset. Additionally, it achieves an accuracy of 99.38 % on the BACH dataset. These results highlight the exceptional effectiveness and practical promise of BCHI-CovNet for the classification of breast cancer histopathological images.

The automated analysis of computed tomography (CT) scans of vertebrae, for the purpose of determining an individual's age and sex constitutes a vital area of research. Accurate assessment of bone age in children facilitates the monitoring of their growth and development. Moreover, the determination of both age and sex has significant relevance in various legal contexts involving human remains. We have built a dataset comprising CT scans of vertebral bodies from 166 patients of diverse genders, acquired during routine cardiac examinations. These images were rescaled to 8-bit data, and textural features were computed using the qMaZda software. The results were analysed employing conventional machine learning techniques and deep convolutional networks. The regression model, developed for the automatic estimation of bone age, accurately determined patients' ages, with a mean absolute error of 3.14 years and R2 = 0.79. In the context of classifying patient gender through textural analysis supported by machine learning, we achieved an accuracy of 69 %. However, the application of deep convolutional networks for this task yielded a slightly lower accuracy of 59 %.

Chronic liver disease and cirrhosis, that can lead to liver failure, are major public health issues, with liver transplantation as the only effective treatment. However, the limited availability of transplantable organs has spurred research into alternative therapies, including bioartificial livers. To date, liver hybrid support devices, using porcine hepatocytes or hepatoma-derived cell lines, have failed to demonstrate efficacy in clinical trials.

Here, for the first time, we report the construction of a model of biologically active function block of bioartificial liver based on a hollow fiber bioreactor populated with genetically modified hepatic cells. For comprehensive comparison the culturing of hepatic cells was carried out in both static and dynamic conditions in a medium that flowed through porous polysulfone capillaries. The most crucial parameters, such as cell viability, glucose consumption, albumin secretion and urea production, were analyzed in static conditions while glucose usage and albumin production were compared in dynamic cell cultures. This model has the potential to improve the development of bioartificial liver devices and contribute to the treatment of patients with impaired liver function.

Gastric slow waves (SWs) are commonly used for the quantitative assessment of gastric functional disorders. Compared with surface electrogastrography, using of magnetic signals to record SWs can achieve higher-quality signal recording. In this study, we discovered that optically pumped magnetometers (OPM) based on the spin exchange relaxation-free method have comparable weak magnetic detection capabilities to superconducting quantum interference devices but without liquid helium cooling. However, owing to the inevitable interference of low-frequency environmental drift, the characteristic features of SW are obscured, greatly increasing the difficulty in detecting gastric magnetic signals. Therefore, in this study, we constructed an OPM Magnetogastrography (OPM-MGG). We proposed an adaptive filtering architecture combined with environmental drift suppression and a non-stationary signal decomposition method for extracting SW signals. Through controlled human experiments, the results demonstrated that our testing system successfully extracted SW signals in the frequency range of 2–4 cycles per minute. The extracted SW signals exhibited consistent power and time–frequency characteristics with the reported results. This study validates the feasibility of (1) using the OPM-MGG system for capturing SW signals and (2) the proposed processing strategies for identifying ultralow-frequency SW signals. In conclusion, the OPM-MGG system and the signal extraction strategies developed in this study have the potential to provide a wearable technology for bioweak magnetic field measurements, offering new opportunities for both research and clinical applications.

In recent years, many diseases can be diagnosed in a short time with the use of deep learning models in the field of medicine. Most of the studies in this area focus on adult or pediatric patients. However, deep learning studies for the diagnosis of diseases in neonatal are not sufficient. Also, since it is known that respiratory disorders such as pneumonia have a large place among the causes of neonatal death, early and accurate diagnosis of respiratory diseases in neonates is crucial. For this reason, our study aims to detect the presence of respiratory disorders through the developed deep-learning approach using chest X-ray images of patients hospitalized in the Neonatal Intensive Care Unit. Accordingly, the enhanced version of C+EffxNet, the new hybrid deep learning model, is designed to predict respiratory disorders in neonates. In this version, the features selected by PCA are combined as 100, 200, and 300, then the binary classification process was carried out. In the study, the accuracy and kappa value were obtained as 0.965, and 0.904, respectively before feature merging, while these values were obtained as 0.977, and 0.935 after feature merging. This method, which was developed for the diagnosis of respiratory disorders in neonates, was also subsequently applied to a chest X-ray dataset that is frequently used in the literature for the diagnosis of pediatric pneumonia. For this data set, while the accuracy was 0.992, the kappa value was 0.982. The results obtained confirm the success of the proposed method for both datasets.

Automated surgical video analysis promises improved healthcare. We propose novel spatial context aware combined loss function for end-to-end Encoder-Decoder training for Surgical Phase Classification (SPC) on laparoscopic cholecystectomy (LC) videos. Proposed loss function leverages on fine-grained class activation maps obtained from fused multi-layer Layer-CAM for supervised learning of SPC, obtaining improved Layer-CAM explanations. Post classification, we introduce graph theory to incorporate known hierarchies of surgical phases. We report peak SPC accuracy of 96.16%, precision of 94.08% and recall of 90.02% on public dataset Cholec80, with 7 phases. Our proposed method utilizes just 73.5% of parameters as against existing state-of-the-art methodology, achieving improvement of 0.5% in accuracy, 1.76% in precision with comparable recall, with an order less standard deviation. We also propose DNN based surgical skill assessment methodology. This approach utilizes surgical phase prediction scores from the final fully-connected layer of spatial-context aware classifier to form multi-channel temporal signal of surgical phases. Time-invariant representation is obtained from this temporal signal through time- and frequency-domain analyses. Autoencoder based time-invariant features are utilized for reconstruction and identification of prominent peaks in dissimilarity curves. We devise a surgical skill measure (SSM) based on spatial-context aware temporal-prominence-of-peaks curve. SSM values are expected to be high when executed skillfully, aligning with expert assessed GOALS metric. We illustrate this trend on Cholec80 and m2cai16-tool datasets, in comparison with GOALS metric. Concurrence in the trend of SSM with respect to GOALS metric is obtained on these test videos, making it a promising step towards automated surgical skill assessment.

Motor imagery (MI) decoding is the core of an intelligent rehabilitation system in brain computer interface, and it has a potential advantage by using source signals, which have higher spatial resolution and the same time resolution compared to scalp electroencephalography (EEG). However, how to delve and utilize the personalized frequency characteristic of dipoles for improving decoding performance has not been paid sufficient attention. In this paper, a novel dipole feature imaging (DFI) and a hybrid convolutional neural network (HCNN) with an embedded squeeze-and-excitation block (SEB), denoted as DFI-HCNN, are proposed for decoding MI tasks. EEG source imaging technique is used for brain source estimation, and each sub-band spectrum powers of all dipoles are calculated through frequency analysis and band division. Then, the 3D space information of dipoles is retrieved, and by using azimuthal equidistant projection algorithm it is transformed to a 2D plane, which is combined with nearest neighbor interpolation to generate multi sub-band dipole feature images. Furthermore, a HCNN is designed and applied to the ensemble of sub-band dipole feature images, from which the importance of sub-bands is acquired to adjust the corresponding attentions adaptively by SEB. Ten-fold cross-validation experiments on two public datasets achieve the comparatively higher decoding accuracies of 84.23% and 92.62%, respectively. The experiment results show that DFI is an effective feature representation, and HCNN with an embedded SEB can enhance the useful frequency information of dipoles for improving MI decoding.

Purpose

Crystalline retinopathy is characterized by reflective crystal deposits in the macula and is caused by various systemic conditions including hereditary, toxic, and embolic etiologies. Herein, we introduce a novel application of deep learning with a multistage generative adversarial network (GAN) to detect crystalline retinopathy using fundus photography.

Methods

The dataset comprised major classes (healthy retina, diabetic retinopathy, exudative age-related macular degeneration, and drusen) and a crystalline retinopathy class (minor set). To overcome the limited data on crystalline retinopathy, we proposed a novel multistage GAN framework. The GAN was retrained after CutMix combination by inputting the GAN-generated synthetic data as new inputs to the original training data. After the multistage CycleGAN augmented the data for crystalline retinopathy, we built a deep-learning classifier model for detection.

Results

Using the multistage CycleGAN facilitated realistic fundus photography synthesis with the characteristic features of retinal crystalline deposits. The proposed method outperformed typical transfer learning, prototypical networks, and knowledge distillation for both multiclass and binary classifications. The final model achieved an area under the curve of the receiver operating characteristics of 0.962 for internal validation and 0.987 for external validation for the detection of crystalline retinopathy.

Conclusion

We introduced a deep learning approach for detecting crystalline retinopathy, a potential biomarker of underlying systemic pathological conditions. Our approach enables realistic pathological image synthesis and more accurate prediction of crystalline retinopathy, an essential but minor retinal condition.

Sleep apnea is a disease that occurs due to the decrease in oxygen saturation in the blood and directly affects people's lives. Detection of sleep apnea is crucial for assessing sleep quality. It is also an important parameter in the diagnosis of various other diseases (diabetes, chronic kidney disease, depression, and cardiological diseases). Recent studies show that detection of sleep apnea can be done via signal processing, especially EEG and ECG signals. However, the detection accuracy needs to be improved. In this paper, a ML model is used for the detection of sleep apnea using 19 static sensor data and 2 dynamic data (Sleep score and Arousal). The sensor data is recorded as a discrete signal and the sleep process is divided into 4.8 M segments. In this work, 19 different sensor data sets were recorded with polysomnography (PSG). These data sets have been used to perform sleep scoring. Then, arousal status marking is done. Model training was carried out with the feature vector consisting of 21 data obtained. Tests were performed with eight different machine learning techniques on a unique dataset consisting of 113 patients. After all, it was automatically determined whether people were diseased (a kind of apnea) or healthy. The proposed model had an average accuracy of 97.27%, while the recall, precision, and f-score values were 99.18%, 95.32%, and 97.20%, respectively. After all, the model that less feature engineering, less complex classification model, higher dataset usage, and higher classification performance has been revealed.

Bronchoscopy has a crucial role in the current treatment of lung diseases, and it is typical of interventional medical instruments led by manual intervention. The scientific study of bronchoscopy is now of primary importance in eliminating problems associated with manual intervention by scientific means. However, for its intervention environment, the trachea is often treated statically, without considering the effect of tracheal deformation on bronchoscopic intervention during respiratory motion. Therefore its findings can deviate from practical application. Thus, studying kinetic problems in respiratory motion is of great importance. This paper developed a mathematical model of mechanical properties of respiratory motion to express respiratory force from the perspective of dynamics of respiratory motion. The dynamical model was solved using MATLAB. Then, a finite element model of respiratory motion was built using Mimics, and the results of respiratory force solution were used as the load of model for dynamics simulation in ABAQUS. Then, a human–computer interaction platform was designed in MATLAB APP Designer to realize parametric calculation and fitting of respiratory force, and a personalized human respiratory motion dynamics simulation was completed in conjunction with ABAQUS. Finally, experimental validation of the interactive platform was performed using pulmonary function test data from three patients. Validation analysis by respiration striving solution, kinetic simulation and experiment found that Dynamical model and simulation results can be better adapted to the individualized study of human respiratory motion dynamics.