Bioengineering最新文献

The classification methods of machine learning have been widely used in almost every discipline. A new classification method, called Taba regression, was introduced for analyzing binary, multinomial, and ordinal outcomes. To evaluate the performance of Taba regression, liver cirrhosis data obtained from a Mayo Clinic study were analyzed. The results were then compared with an artificial neural network (ANN), random forest (RF), logistic regression (LR), and probit analysis (PA). The results using cirrhosis data revealed that the Taba regression model could be a competitor to other classification models based on the true positive rate, F-score, accuracy, and area under the receiver operating characteristic curve (AUC). Taba regression can be used by researchers and practitioners as an alternative method of classification in machine learning. In conclusion, the Taba regression provided a reliable result with respect to accuracy, recall, F-score, and AUC when applied to the cirrhosis data.

Diabetes is a chronic condition, and traditional monitoring methods are invasive, significantly reducing the quality of life of the patients. This study proposes the design of an innovative system based on a microcontroller that performs real-time ECG acquisition and evaluates the presence of diabetes using an Edge-AI solution. A spectrogram-based preprocessing method is combined with a 1-Dimensional Convolutional Neural Network (1D-CNN) to analyze the ECG signals directly on the device. By applying quantization as an optimization technique, the model effectively balances memory usage and accuracy, achieving an accuracy of 89.52% with an average precision and recall of 0.91 and 0.90, respectively. These results were obtained with a minimal memory footprint of 347 kB flash and 23 kB RAM, showcasing the system's suitability for wearable embedded devices. Furthermore, a custom PCB was developed to validate the system in a real-world scenario. The hardware integrates high-performance electronics with low power consumption, demonstrating the feasibility of deploying Edge-AI for non-invasive, real-time diabetes detection in resource-constrained environments. This design represents a significant step forward in improving the accessibility and practicality of diabetes monitoring.

The Lateral Collateral Ligament (LCL), one of the four major ligaments in the knee joint, resides on the outer aspect of the knee. It forms a vital connection between the femur and the fibula. The LCL's primary role is to provide stability against Varus forces, safeguarding the knee from undue rotation and tibial displacement. Uniaxial mechanical testing was conducted on the dog bone (DB) samples in this study. The porcine of different ages, from 3 months to 48 months (4 years) old, were used to analyse the effect of age. A constant head speed of 200 mm/s was applied throughout the tests to mimic strain-stress and damage responses at an initial strain rate of 13.3/s. The mechanical properties of LCL were evaluated, with a specific focus on the effect of age. The LMM (Linear Mixed Model) analysis revealed a marginally significant positive slope for Young's modulus (p = 0.0512) and a significant intercept (p = 0.0016); for Maximum Stress, a negative slope (p = 0.0346) and significant intercept (p < 0.0001); while Maximum Stretch showed a significant negative slope (p = 0.0007) and intercept (p < 0.0001), indicating the muscle reduces compliance and load-bearing capacity with age.

Background: The large language model (LLM) has the potential to be applied to clinical practice. However, there has been scarce study on this in the field of gastroenterology. Aim: This study explores the potential clinical utility of two LLMs in the field of gastroenterology: a customized GPT model and a conventional GPT-4o, an advanced LLM capable of retrieval-augmented generation (RAG). Method: We established a customized GPT with the BM25 algorithm using Open AI's GPT-4o model, which allows it to produce responses in the context of specific documents including textbooks of internal medicine (in English) and gastroenterology (in Korean). Also, we prepared a conventional ChatGPT 4o (accessed on 16 October 2024) access. The benchmark (written in Korean) consisted of 15 clinical questions developed by four clinical experts, representing typical questions for medical students. The two LLMs, a gastroenterology fellow, and an expert gastroenterologist were tested to assess their performance. Results: While the customized LLM correctly answered 8 out of 15 questions, the fellow answered 10 correctly. When the standardized Korean medical terms were replaced with English terminology, the LLM's performance improved, answering two additional knowledge-based questions correctly, matching the fellow's score. However, judgment-based questions remained a challenge for the model. Even with the implementation of 'Chain of Thought' prompt engineering, the customized GPT did not achieve improved reasoning. Conventional GPT-4o achieved the highest score among the AI models (14/15). Although both models performed slightly below the expert gastroenterologist's level (15/15), they show promising potential for clinical applications (scores comparable with or higher than that of the gastroenterology fellow). Conclusions: LLMs could be utilized to assist with specialized tasks such as patient counseling. However, RAG capabilities by enabling real-time retrieval of external data not included in the training dataset, appear essential for managing complex, specialized content, and clinician oversight will remain crucial to ensure safe and effective use in clinical practice.

Most existing methods for magnetic resonance imaging (MRI) reconstruction with deep learning use fully supervised training, which assumes that a fully sampled dataset with a high signal-to-noise ratio (SNR) is available for training. In many circumstances, however, such a dataset is highly impractical or even technically infeasible to acquire. Recently, a number of self-supervised methods for MRI reconstruction have been proposed, which use sub-sampled data only. However, the majority of such methods, such as Self-Supervised Learning via Data Undersampling (SSDU), are susceptible to reconstruction errors arising from noise in the measured data. In response, we propose Robust SSDU, which provably recovers clean images from noisy, sub-sampled training data by simultaneously estimating missing k-space samples and denoising the available samples. Robust SSDU trains the reconstruction network to map from a further noisy and sub-sampled version of the data to the original, singly noisy, and sub-sampled data and applies an additive Noisier2Noise correction term upon inference. We also present a related method, Noiser2Full, that recovers clean images when noisy, fully sampled data are available for training. Both proposed methods are applicable to any network architecture, are straightforward to implement, and have a similar computational cost to standard training. We evaluate our methods on the multi-coil fastMRI brain dataset with novel denoising-specific architecture and find that it performs competitively with a benchmark trained on clean, fully sampled data.

Nannochloris sp. JB17 has been identified as an interesting microalgal species that can tolerate high salinity and high bicarbonate concentrations. In this study, Nannochloris sp. JB17 was long-term adapted to increased bicarbonate concentrations (10-60 g NaHCO₃ per L) in fresh or sea-water-based growing media. This study aimed to evaluate its growth performance and biochemical composition under different cultivation conditions. The highest biomass production (1.24-1.3 g/L) achieved in the study was obtained in fresh water media supplemented with 40 g/L and 60 g/L NaHCO₃, respectively. Total protein content fluctuated at similar levels among the different treatments (32.4-38.5%), displaying good essential amino acids indices of 0.85-1.02, but with low in vitro protein digestibility (15-20%) rates. Total lipids did not show any significant alteration among the different NaHCO₃ concentrations in both fresh and sea water (12.6-13.3%) but at increased sodium strength, a significant increase in unsaturated lipids and in particular a-linolenic acid (C18:3) and linoleic acid (C18:2) was observed. Carbohydrate content also ranged at very similar levels among the cultures (26-30.9%). The main fraction of carbohydrates was in the type of neutral sugars ranging from around 72% to 80% (of total carbohydrates), while uronic acids were in negligible amounts. Moreover, Nannochloris sp. showed that it contained around 8-9% sulfated polysaccharides. Since the microalgae display good growth patterns at high bicarbonate concentrations, they could be a potential species for microalgal-based carbon capture and utilization systems.

Knowledge of the impact of chemicals on the environment is important for assessing the risks that chemicals can generate in ecosystems. With the help of pilot-scale micro-tests, it was possible to evaluate the biological sludge in terms of its chemical and biological composition, information that can be applied on an industrial scale in treatment plants. The important parameters analyzed in the evaluation of the biodegradability of wastewater were pH, chemical composition (NH₄⁺, NO₃^-, NO₂^-, and PO₄^3-), dry substance (DS), inorganic substance (IS), and organic substance (OS), and the biological oxygen demand (BOD)/chemical oxygen consumption (COD) ratio. The examination revealed the presence of free active ciliates Aspidisca polystyla, Lyndonotus setigerum, Vorticella microstoma, fixed by Zooglee, Paramecium sp., Opercularia, Colpoda colpidium, Euplotes, Didinum nasutum, Stentor, and Acineta tuberosa, metazoa Rotifers, filamentous algae, Nostoc and Anabena, and bacteria Bacillus subtilis, Nocardia, and Microccocus luteus. The novelty of this study lies in the fact that we carried out a study to evaluate the population of microorganisms starting from the premise that the probability of biodegradation of substances is directly proportional to the number of microorganisms existing in the environment and their enzymatic equipment.

The complex collagen network of the native meniscus and the gradient of the density and alignment of this network through the meniscal enthesis is essential for the proper mechanical function of these tissues. This architecture is difficult to recapitulate in tissue-engineered replacement strategies. Prenatally, the organization of the collagen fiber network is established and aggrecan content is minimal. In vitro, fibrochondrocytes (FCCs) produce proteoglycans and associated glycosaminoglycan (GAG) chains early in culture, which can inhibit collagen fiber formation during the maturation of tissue-engineered menisci. Thus, it would be beneficial to both specifically and temporarily block deposition of proteoglycans early in culture. In this study, we transiently inhibited aggrecan production by meniscal fibrochondrocytes using siRNA in collagen gel-based tissue-engineered constructs. We evaluated the effect of siRNA treatment on the formation of collagen fibrils and bulk and microscale tensile properties. Specific inhibition of aggrecan production by fibrochondrocytes via siRNA was successful both in 2D monolayer cell culture and 3D tissue culture. This inhibition during early maturation of these in vitro constructs increased collagen fibril diameter by more than 2-fold. This increase in fibril diameter allowed these tissues to distribute strains more effectively at the local level, particularly at the interface of the bone and soft tissue. These data show that siRNA can be used to modulate the ECM to improve collagen fiber formation and mechanical properties in tissue-engineered constructs, and that a transient decrease in aggrecan promotes the formation of a more robust fiber network.

Accurate segmentation of brain tumors in MRI scans is critical for diagnosis and treatment planning. Traditional segmentation models, such as U-Net, excel in capturing spatial information but often struggle with complex tumor boundaries and subtle variations in image contrast. These limitations can lead to inconsistencies in identifying critical regions, impacting the accuracy of clinical outcomes. To address these challenges, this paper proposes a novel modification to the U-Net architecture by integrating a spatial attention mechanism designed to dynamically focus on relevant regions within MRI scans. This innovation enhances the model's ability to delineate fine tumor boundaries and improves segmentation precision. Our model was evaluated on the Figshare dataset, which includes annotated MRI images of meningioma, glioma, and pituitary tumors. The proposed model achieved a Dice similarity coefficient (DSC) of 0.93, a recall of 0.95, and an AUC of 0.94, outperforming existing approaches such as V-Net, DeepLab V3+, and nnU-Net. These results demonstrate the effectiveness of our model in addressing key challenges like low-contrast boundaries, small tumor regions, and overlapping tumors. Furthermore, the lightweight design of the model ensures its suitability for real-time clinical applications, making it a robust tool for automated tumor segmentation. This study underscores the potential of spatial attention mechanisms to significantly enhance medical imaging models and paves the way for more effective diagnostic tools.

In recent years, image-guided brachytherapy for cervical cancer has become an important treatment method for patients with locally advanced cervical cancer, and multi-modality image registration technology is a key step in this system. However, due to the patient's own movement and other factors, the deformation between the different modalities of images is discontinuous, which brings great difficulties to the registration of pelvic computed tomography (CT/) and magnetic resonance (MR) images. In this paper, we propose a multimodality image registration network based on multistage transformation enhancement features (MTEF) to maintain the continuity of the deformation field. The model uses wavelet transform to extract different components of the image and performs fusion and enhancement processing as the input to the model. The model performs multiple registrations from local to global regions. Then, we propose a novel shared pyramid registration network that can accurately extract features from different modalities, optimizing the predicted deformation field through progressive refinement. In order to improve the registration performance, we also propose a deep learning similarity measurement method combined with bistructural morphology. On the basis of deep learning, bistructural morphology is added to the model to train the pelvic area registration evaluator, and the model can obtain parameters covering large deformation for loss function. The model was verified by the actual clinical data of cervical cancer patients. After a large number of experiments, our proposed model achieved the highest dice similarity coefficient (DSC) metric compared with the state-of-the-art registration methods. The DSC index of the MTEF algorithm is 5.64% higher than that of the TransMorph algorithm. It will effectively integrate multi-modal image information, improve the accuracy of tumor localization, and benefit more cervical cancer patients.