IEEE Journal of Biomedical and Health Informatics最新文献

Accurate medical image segmentation is crucial for precise diagnosis and treatment in clinical pathology analysis and surgical navigation. While Convolutional Neural Network (CNN)-based approaches excel in capturing and analyzing local features, they often lose key global context. Transformers, utilizing self-attention mechanisms, address this issue but often overlook localized and multi-scale features while also requiring significant computational resources. To integrate the advantages of CNNs and Transformers to achieve efficient and precise medical image segmentation, we propose a segmentation framework based on multi-feature fusion CNN and Bi-level Routing Attention Transformer (MCBTNet). MCBTNet integrates CNNs and Transformers within a U-shaped encoderdecoder architecture. This configuration not only extracts multi-scale features via the U-shaped structure but also efficiently captures global contextual information through the dynamic sparsity of the Bi-Level Routing Attention Transformer. Our novel Frequency-Channel-Spatial multidimensional attention mechanism is implemented on skip connections, enhancing segmentation accuracy and speed by maximizing multi-scale feature utilization. Finally, MCBTNet obtains the segmentation result by fusing the predictions of different scales. Experimental results on five public datasets demonstrate that MCBTNet outperforms state-of-the-art methods in Dice and HD metrics, with lower computational and memory requirements. The code will be available on https://github.com/670768312/MCBTNet.

Warfarin is a commonly prescribed anticoagulant with a narrow therapeutic window, requiring frequent and specialized monitoring. This work aims to develop standardized optimal warfarin dose decision support using a machine learning model based on time series anticoagulation data and patient demographic characteristics. We propose an offline reinforcement learning model (RL) using a Batch-Constrained Q-Learning algorithm (BCQ) in the discrete action setting to predict the cumulative warfarin dose for the days until the next INR (International Normalized Ratio) test. Prior approaches utilized time-series supervised learning methods such as regression or Long Short Term Memory (LSTM) neural networks. The key advantage of reinforcement learning is its capacity to learn optimal dosing strategies from suboptimal clinical states in the data. To evaluate the model we compared the predicted warfarin doses with the physician-prescribed doses. Our BCQ model with a prediction accuracy of 98.6% significantly outperformed our baseline Long Short Term Memory (LSTM) model with a prediction accuracy of 71.09%. Further qualitative evaluation for explainability indicated that the model correctly adjusted the warfarin dose at time steps when patients had out-of-range INRs.

The recently proposed short-time impedance spectroscopy (short-time IS) measures impedance spectra with high temporal resolution using a nonsinusoidal mode-switching oscillator. With a view to application for muscular disease diagnosis and human-machine interaction, this study presents the temporal and spectral impedance myography using the short-time IS system. We applied the proposed system to the measurement of human forearm impedance and analyzed impedance changes during wrist motion. The forearm's impedance at 40 frequency points was measured by our developed system. The forearm's rapid impedance response during wrist motion was captured with a high temporal resolution of about 0.5 ms, displaying the impedance magnitude and phase angle change as a color map. Furthermore, we experimentally and theoretically demonstrated that difference and differential Cole-Cole plots reduced skin impedance effects and produced a characteristic curve corresponding to wrist motion, even with two-terminal measurement. We anticipate that the IS system and visualization method will be beneficial for myoelectric control in prosthetic hands and noninvasive muscle disease diagnosis.

The research on identifying drug-disease associations (DDAs) is widely used in scenarios such as drug development, clinical decision-making, and drug repurposing, holding significant biological and medical significance. Existing methods for drug-disease association prediction have achieved decent performance, they primarily rely on simplistic drug-disease association graphs or similarity graphs. These methods often struggle to capture the high-order correlations of complex multimodal data, limiting their ability to handle the complexity of data associations effectively. In addition, real drug-disease associations are highly sparse, posing a significant challenge to prediction accuracy. To tackle these issues, we propose a general hypergraph neural network framework for drug-disease association prediction based on hierarchical contrastive learning and cross-attention learning. It leverages hypergraph neural networks to learn representations of drugs and diseases carrying high-order correlations and strengthens representation quality using interactive attention learning and hierarchical contrastive learning. Meanwhile, the -weighted loss function is utilized to adapt to the high sparsity property of real drug-disease associations during model training and improve prediction performance. Extensive experiments demonstrate that DD-HGNN surpasses other state-of-the-art methods in predicting drug-disease associations and further validation through case studies on Leukemia and Colorectal Neoplasms underscores its reliability.

Integrating Natural Language Processing (NLP) with Generative Pre-trained Transformer (GPT) models plays a pivotal role in enhancing the accuracy and efficiency of healthcare software, which is essential for patient safety and providing high-quality care. The precision of healthcare software is fundamental to protecting the well-being of the patient. In addition, it can ensure the delivery of superior care, maintain the integrity of healthcare systems, and promote trust and cost-effectiveness. It is necessary to emphasize the importance of software reliability in its development and deployment. Symbolic execution serves as a vital technology in automated vulnerability detection. However, symbolic execution often faces problems such as path explosion, which seriously affects efficiency. Although there have been several studies to reduce the number of computational paths in symbolic execution, this problem remains a major obstacle. Therefore, more efficient solutions are urgently needed to ensure the software security. This paper proposes a large-scale language model(LLM) induction method mitigating path explosion applied to symbolic execution engines. In contrast to traditional symbolic execution engines, which often result in timeout or out-of-memory detection, our approach achieves the task of detecting vulnerabilities in seconds. Furthermore, our proposal improves the scalability of symbolic execution, allowing more extensive and complex programs to be analyzed without significant increases in computational resources or time. This scalability is crucial to tackling modern software systems and improving the efficiency and effectiveness of automated defect verification in healthcare software.

Accurate and timely core body temperature measurement is essential for identifying and preventing heat-related illnesses. Infrared thermography (IRT) provides a non-invasive, full-scale and efficient temperature path for body temperature screening. However, the complexity of environmental factors and personal features continuously affect the measured skin temperature, resulting in low accuracy and reliability of existing body temperature monitoring by IRT. To address this issue, this study proposed an innovative core temperature prediction model (CTPM) for IRT based on heat transfer mechanism between the human body and the ambient environment. Based on human body thermoregulation, the optimal facial thermal feature that can reflect the impact of ambient temperature on skin temperature is proposed. Combining it with personal features and distributed facial skin temperature features, a CTPM is established based on Random Forest algorithm. The proposed CTPM are evaluated using a publicly available PhysioNet facial and oral temperature dataset. The results demonstrate that the proposed optimal CTPM achieves the best accuracy and consistency in predicting core body temperature. The root-mean-square error of the optimal CTPM is 0.259°C, and the mean lower and upper 95% limits of agreement are -0.505 °C and 0.507°C, respectively. Variable importance analysis indicates that the proposed optimal facial thermal feature makes a dominant contribution to the prediction performance of the optimal CTPM. Our method enables accurate and stable core body temperature prediction in complex ambient environments over a wide range of temperatures, and has the potential to replace traditional contact measurements to meet clinical needs.

Acoustic foundation models, through self-supervised learning on large amounts of unlabeled speech data, can acquire rich acoustic representations. In recent years, these models have demonstrated substantial potential in audio-based health-related tasks, remarkably enhancing the efficiency and quality of healthcare services and contributing to the advancement of smart healthcare. However, there is currently a lack of systematic research and exploration on the performance of acoustic foundation models in health-related tasks. Furthermore, inconsistencies in evaluation methods and experimental setups hinder fair comparisons between different methods, severely impeding progress in this field. To address these challenges, we establish a unified Benchmark for evaluating Bio-Acoustic health via acoustic foundation models, namely BAHBench. BAHBench encompasses 6 distinct health-related tasks and evaluates 12 acoustic foundation models within a unified evaluation framework and parameter settings, enabling fair comparisons across different models. Our objective is to explore the effectiveness of current acoustic foundation models in health-related tasks. Thus, we discuss the impact of model size and data diversity on performance, and investigate feature selection and efficient fine-tuning strategy. Experimental results show that different health-related tasks benefit from features from different layers of the foundation model, while LoRA fine-tuning further enhances the model's performance on downstream tasks. Our goal is to provide clear and comprehensive guidance for future researchers. The code related to this study will be available to the research community to promote transparency and reproducibility.

Prostate cancer is a critical healthcare challenge globally and is one of the most prevalent types of cancer in men. Early and accurate diagnosis is essential for effective treatment and improved patient outcomes. In the existing literature, computer-aided diagnosis (CAD) solutions have been developed to assist pathologists in various tasks, including classification, diagnosis, and prostate cancer grading. Content-based image retrieval (CBIR) techniques provide valuable approaches to enhance these computer-aided solutions. This study evaluates how generative deep learning models can improve the quality of retrievals within a CBIR system. Specifically, we propose applying a Siamese Network approach, which enables us to learn how to encode image patches into latent representations for retrieval purposes. We used the ProGleason-GAN framework trained on the SiCAPv2 dataset to create similar pairs of input patches. Our observations indicate that introducing synthetic patches leads to notable improvements in the evaluated metrics, underscoring the utility of generative models within CBIR tasks. Furthermore, this work is the first in the literature where latent representations optimized for CBIR are used to train an attention mechanism for performing Gleason Scoring of a WSI.

In prostate 3D MRI image segmentation methods, it is usually necessary to annotate each slice, and these annotations are generally time-consuming and specialized. In this study, we generate pseudo-labels using an annotation method with one foreground seed point and six edge relaxation points. We design a weakly supervised semantic learning segmentation framework, ACEA-Net. This segmentation framework solves the under-expansion problem due to the lack of semantic affinity of the seed point pixels in the pseudo-labeling generation process. We design a Seed Cluster Geodesic Distance Transform (SeedGeo) seed expansion strategy to provide a more complete supervised signal. In the segmentation model training phase, Adaptive Convolutional Normalization (ACN) and Enhanced Simple Parameter-Free Attention Module (SimAM) are utilized to smooth the convolutional layer's output in the U-Net baseline model to suppress noisy labels. The proposed segmentation framework achieves excellent segmentation results on the MSD prostate and PROMISE12 prostate datasets, with Dice similarity coefficients (Dice) of 87.23% and 81.00% for the two segmentation tasks, and Average Symmetry Surface Distances (ASSD) of 1.73mm and 2.02mm, respectively, which are superior to the current state-of-the-art method.

Medical video segmentation is fundamentally important in clinical diagnosis and treatment procedures, offering dynamic tracking of breast lesions across frames in ultrasound videos for improved segmentation performance. However, existing approaches face challenges in striking a balance between segmentation performance and inference speed, hindering real-time application in resource-constrained medical environments. In order to address these limitations, we present BaS, a blazing-fast on-device breast lesion segmentation model. BaS integrates the Stem module and BaSBlock to refine representations through inter- and intra-frame analysis on ultrasound videos. In addition, we release two versions of BaS: the BaS-S for superior segmentation performance and the BaS-L for accelerated inference times. Experimental Results indicate that BaS surpasses the top-performing models in terms of segmenting efficiency and accuracy of predictions on devices with limited resources. This work advances the development of efficient medical video segmentation frameworks applicable to multiple medical platforms.