Biomedical Physics & Engineering Express最新文献

Brain-computer interfaces (BCIs) offer disabled individuals the means to interact with devices by decoding the electroencephalogram (EEG). However, decoding intent in fine motor tasks can be challenging, especially in stroke survivors with cortical lesions. Here, we attempt to decode graded finger extension from the EEG in stroke patients with left-hand paresis and healthy controls. Participants extended their fingers to one of four levels: low, medium, high, or 'no-go' (none), while hand, muscle (electromyography: EMG), and brain (EEG) activity were monitored. Event-related desynchronization (ERD) was measured as the change in 8-30 Hz EEG power during movement. Classifiers were trained on EEG features, EMG power, or both (EEG+EMG) to decode finger extension, and accuracy assessed via four-fold cross-validation for each hand of each participant. Mean accuracy exceeded chance (25%) for controls (n = 11) at 62% for EMG, 60% for EEG, and 71% for EEG+EMG on the left hand; and 67%, 60%, and 74%, respectively, on the right hand. Accuracies were similar on the unimpaired right hand for the stroke group (n = 3): 61%, 68%, and 78%, respectively. But on the paretic left hand, EMG only discriminated no-go from movement above chance (41%); in contrast, EEG gave 65% accuracy (68% for EEG+EMG), comparable to the non-paretic hand. The median ERD was significant (p < 0.01) over the cortical hand area in both groups and increased with each level of finger extension. But while the ERD favored the hemisphere contralateral to the active hand as expected, it was ipsilateral for the left hand of stroke due to the lesion in the right hemisphere, which may explain its discriminative ability. Hence, the ERD captures effort in finger extension regardless of success or failure at the task; and harnessing residual EMG improves the correlation. This marker could be leveraged in rehabilitative protocols that focus on fine motor control.

Photoacoustic tomography (PAT) is a non-destructive, non-ionizing, and rapidly expanding hybrid biomedical imaging technique, yet it faces challenges in obtaining clear images due to limited data from detectors or angles. As a result, the methodology suffers from significant streak artifacts and low-quality images. The integration of deep learning (DL), specifically convolutional neural networks (CNNs), has recently demonstrated powerful performance in various fields of PAT. This work introduces a post-processing-based CNN architecture named residual-dense UNet (RDUNet) to address the stride artifacts in reconstructed PA images. The framework adopts the benefits of residual and dense blocks to form high-resolution reconstructed images. The network is trained with two different types of datasets to learn the relationship between the reconstructed images and their corresponding ground truths (GTs). In the first protocol, RDUNet (identified as RDUNet I) underwent training on heterogeneous simulated images featuring three distinct phantom types. Subsequently, in the second protocol, RDUNet (referred to as RDUNet II) was trained on a heterogeneous composition of 81% simulated data and 19% experimental data. The motivation behind this is to allow the network to adapt to diverse experimental challenges. The RDUNet algorithm was validated by performing numerical and experimental studies involving single-disk, T-shape, and vasculature phantoms. The performance of this protocol was compared with the famous backprojection (BP) and the traditional UNet algorithms. This study shows that RDUNet can substantially reduce the number of detectors from 100 to 25 for simulated testing images and 30 for experimental scenarios.

Traumatic injury remains a leading cause of death worldwide, with traumatic bleeding being one of its most critical and fatal consequences. The use of whole-body computed tomography (WBCT) in trauma management has rapidly expanded. However, interpreting WBCT images within the limited time available before treatment is particularly challenging for acute care physicians. Our group has previously developed an automated bleeding detection method in WBCT images. However, further reduction of false positives (FPs) is necessary for clinical application. To address this issue, we propose a novel automated detection for traumatic bleeding in CT images using deep learning and multi-organ segmentation; Methods: The proposed method integrates a three-dimensional U-Net# model for bleeding detection with an FP reduction approach based on multi-organ segmentation. The multi-organ segmentation method targets the bone, kidney, and vascular regions, where FPs are primarily found during the bleeding detection process. We evaluated the proposed method using a dataset of delayed-phase contrast-enhanced trauma CT images collected from four institutions; Results: Our method detected 70.0% of bleedings with 76.2 FPs/case. The processing time for our method was 6.3 ± 1.4 min. Compared with our previous ap-proach, the proposed method significantly reduced the number of FPs while maintaining detection sensitivity.

Background and Purpose. Although radiotherapy techniques are a primary treatment for head and neck cancer (HNC), they are still associated with substantial toxicity and side effects. Machine learning (ML) based radiomics models for predicting toxicity mostly rely on features extracted from pre-treatment imaging data. This study aims to compare different models in predicting radiation-induced xerostomia and sticky saliva in both early and late stages HNC patients using CT and MRI image features along with demographics and dosimetric information.Materials and Methods.A cohort of 85 HNC patients who underwent radiation treatment was evaluated. We built different ML-based classifiers to build a multi-objective, multimodal radiomics model by extracting 346 different features from patient data. The models were trained and tested for prediction, utilizing Relief feature selection method and eight classifiers consisting eXtreme Gradient Boosting (XGBoost), Multilayer Perceptron (MLP), Support Vector Machines (SVM), Random Forest (RF), K-Nearest Neighbor (KNN), Naive Bayes (NB), Logistic Regression (LR), and Decision Tree (DT). The performance of the models was evaluated using sensitivity, specificity, area under the curve (AUC), and accuracy metrics.Results.Using a combination of demographics, dosimetric, and image features, the SVM model obtained the best performance with AUC of 0.77 and 0.81 for predicting early sticky saliva and xerostomia, respectively. Also, SVM and MLP classifiers achieved a noteworthy AUC of 0.85 and 0.64 for predicting late sticky saliva and xerostomia, respectively.Conclusion. This study highlights the potential of baseline CT and MRI image features, combined with dosimetric data and patient demographics, to predict radiation-induced xerostomia and sticky saliva. The use of ML techniques provides valuable insights for personalized treatment planning to mitigate toxicity effects during radiation therapy for HNC patients.

In the medical field, endoscopic video analysis is crucial for disease diagnosis and minimally invasive surgery. The Endoscopic Foundation Models (Endo-FM) utilize large-scale self-supervised pre-training on endoscopic video data and leverage video transformer models to capture long-range spatiotemporal dependencies. However, detecting complex lesions such as gastrointestinal metaplasia (GIM) in endoscopic videos remains challenging due to unclear boundaries and indistinct features, and Endo-FM has not demonstrated good performance. To this end, we propose a fully fine-tuning strategy with an Extended Learnable Offset Parameter (ELOP), which improves model performance by introducing learnable offset parameters in the input space. Specifically, we propose a novel loss function that combines cross-entropy loss and focal loss through a weighted sum, enabling the model to better focus on hard-to-classify samples during training. We validated ELOP on a private GIM dataset from a local grade-A tertiary hospital and a public polyp detection dataset. Experimental results show that ELOP significantly improves the detection accuracy, achieving accuracy improvements of 6.25 % and 3.75%respectively compared to the original Endo-FM. In summary, ELOP provides an excellent solution for detecting complex lesions in endoscopic videos, achieving more precise diagnoses.

Objective.Mapping the myomagnetic field of a straight and easily accessible muscle after electrical stimulation using triaxial optically pumped magnetometers (OPMs) to assess potential benefits for magnetomyography (MMG).Approach.Six triaxial OPMs were arranged in two rows with three sensors each along the abductor digiti minimi (ADM) muscle. The upper row of sensors was inclined by 45° with respect to the lower row and all sensors were aligned closely to the skin surface without direct contact. Then, the electromagnetic muscle activity was electrically evoked utilizing stepwise increasing currents at the cubital tunnel at the ulnar nerve. Evoked myomagnetic activity was recorded with 18 channels, three per sensor. As the measurements were performed in PTB's magnetically shielded room (BMSR-2) no averaging and only moderate filtering was applied.Main results.The myomagnetic vector field could be successfully mapped. The obtained spatial structure with a radial symmetry corresponds to the expectations from the ADM's parallel muscle architecture. The temporal evolution exhibits an up to four-phasic shape. Implications for future experiments are derived and needs for sensor performance improvements are identified. Significance.The use of an OPM array with small (∼3 mm edge length) sensing voxels enabled the mapping of the magnetic vector field of the ADM. This allowed visualization of the spatiotemporal evolution of the muscle's evoked magnetic field and gives implications for future experiments. In the future, high density OPM grids may enable high-accuracy determination of muscle parameters such as innervation zone position, pennation angle, and propagation velocities.

The current study investigated the geometry, design and solid angle impacts on full energy peak efficiency (FEPE) of NaI(Tl) detectors for a line source. A line source is fabricated using^99mTc solution filled in a borosilicate glass tube of inner diameter 3 mm, tube wall thickness 2.5 mm and length 12.7 cm. The FEPE is measured for the fabricated linear source using 2″×2″ NaI(Tl) cylindrical detector at various source-detector distances. The experimental setup is simulated in GEANT4 and the computed FEPE values are compared with experimental values. The absolute error of 5% is observed between computed and measured FEPE values. Utilizing the advantages of MC simulations, the impact of numerous source parameters such as source length, diameter, source-detector distance, glass tube thickness and lead shield effects on FEPE are investigated to optimize the fabrication process of linear sources. A case study for current investigation has been analyzed by considering absolute FEPE of the NaI(Tl) system for a syringe filled with radioactive solution. This study provides an insight for the fabrication of standard linear sources by analyzing different source parameters and hence, may serve as a guideline to prepare standard linear sources for the calibration of radiation detectors.

Lung image segmentation is a crucial problem for autonomous understanding of the potential illness. However, existing approaches lead to a considerable decrease in accuracy for lung infection areas with varied shapes and sizes. Recently, researchers aimed to improve segmentation accuracy by combining diagnostic reports based on text prompts and image vision information. However, limited by the network structure, these methods are inefficient and ineffective. To address this issue, this paper proposes a Bilateral Network with Text Guided Aggregation Architecture (BNTGAA) to fully fuse local and global information for text and image vision. This proposed architecture involves (i) a global fusion branch with a Hadamard product to align text and vision feature representation and (ii) a multi-scale cross-fusion branch with positional coding and skip connection, performing text-guided segmentation in different resolutions. (iii) The global fusion and multi-scale cross-fusion branches are combined to feed a mamba module for efficient segmentation. Extensive quantitative and qualitative evaluations demonstrate that the proposed architecture performs better both in accuracy and efficiency. Our architecture outperforms the current best methods on the QaTa-COVID19 dataset, improving mIoU and Dice scores by 3.08% and 2.35%, respectively. Meanwhile, our architecture surpasses the computational speed of existing multimodal networks. Finally, the architecture has a quick convergence and generality. It can exceed the performance of the current best methods even if it is trained with only 50% of the dataset.

U-Net is widely used in medical image segmentation due to its simple and flexible architecture design. To address the challenges of scale and complexity in medical tasks, several variants of U-Net have been proposed. In particular, methods based on Vision Transformer (ViT), represented by Swin UNETR, have gained widespread attention in recent years. However, these improvements often focus on the encoder, overlooking the crucial role of the decoder in optimizing segmentation details. This design imbalance limits the potential for further enhancing segmentation performance. To address this issue, we analyze the roles of various decoder components, including upsampling method, skip connection, and feature extraction module, as well as the shortcomings of existing methods. Consequently, we propose Swin DER (i.e.,SwinUNETRDecoderEnhanced andRefined), by specifically optimizing the design of these three components. Swin DER performs upsampling using learnable interpolation algorithm called offset coordinate neighborhood weighted up sampling (Onsampling) and replaces traditional skip connection with spatial-channel parallel attention gate (SCP AG). Additionally, Swin DER introduces deformable convolution along with attention mechanism in the feature extraction module of the decoder. Our model design achieves excellent results, surpassing other state-of-the-art methods on both the Synapse dataset and the MSD brain tumor segmentation task. Code is available at:https://github.com/WillBeanYang/Swin-DER.

Objective. Arterial sampling for PET imaging often involves continuously measuring the radiotracer activity concentration in blood using an automatic blood sampling system (ABSS). We proposed and validated an external delay and dispersion correction procedure needed when a change in flow rate occurs during data acquisition. We also measured the external dispersion constant of [¹¹C]CURB, [¹⁸F]FDG, [¹⁸F]FEPPA, and [¹⁸F]SynVesT-1.Approach. External delay and dispersion constants were measured for the flow rates of 350, 300, 180, and 150 ml h^-1, using 1-minute-long rectangular inputs (n= 10;¹⁸F-fluoride in saline). Resulting constants were used to validate the external delay and dispersion corrections (n= 6;¹⁸F-fluoride in saline; flow rate change: 350 to 150 ml h^-1and 300 to 180 ml h^-1); constants were modelled to transition linearly between flow rates. Corrected curves were assessed using the percent area-under-the-curve (AUC) ratio and a modified model selection criterion (MSC). External delay and dispersion constants were measured for various radiotracers using a blood analog (i.e., similar viscoelastic properties).Main results. ABSS outputs were successfully corrected for external delay and dispersion using our proposed method accounting for a change in flow rate. AUC ratio reduced from ∼10% for the uncorrected 350-150 ml h^-1output (∼6% for the 300-180 ml h^-1) to < 1% after correction when compared to true input (511 keV energy window); approx. 5-fold increase in MSC. Assuming an internal dispersion constant of 5 s, the dispersion constant (internal + external) for [¹¹C]CURB, [¹⁸F]FDG, [¹⁸F]FEPPA, and [¹⁸F]SynVesT-1 was 13, 9, 16, and 10 s, respectively.Significance. This study presented an external delay and dispersion correction procedure needed when a change in flow rate occurs during ABSS data acquisition. Additionally, this is the first study to measure the external delay and dispersion constants using a blood analog solution, a suitable alternative to blood when estimating external dispersion.