Biomedical Physics & Engineering Express最新文献

With the development of deep learning in the field of medical image segmentation, various network segmentation models have been developed. Currently, the most common network models in medical image segmentation can be roughly categorized into pure convolutional networks, Transformer-based networks, and networks combining convolution and Transformer architectures. However, when dealing with complex variations and irregular shapes in medical images, existing networks face issues such as incomplete information extraction, large model parameter sizes, high computational complexity, and long processing times. In contrast, models with lower parameter counts and complexity can efficiently, quickly, and accurately identify lesion areas, significantly reducing diagnosis time and providing valuable time for subsequent treatments. Therefore, this paper proposes a lightweight network named MCI-Net, with only 5.48 M parameters, a computational complexity of 4.41, and a time complexity of just 0.263. By performing linear modeling on sequences, MCI-Net permanently marks effective features and filters out irrelevant information. It efficiently captures local-global information with a small number of channels, reduces the number of parameters, and utilizes attention calculations with exchange value mapping. This achieves model lightweighting and enables thorough interaction of local-global information within the computation, establishing an overall semantic relationship of local-global information. To verify the effectiveness of the MCI-Net network, we conducted comparative experiments with other advanced representative networks on five public datasets: X-ray, Lung, ISIC-2016, ISIC-2018, and capsule endoscopy and gastrointestinal segmentation. We also performed ablation experiments on the first four datasets. The experimental results outperformed the other compared networks, confirming the effectiveness of MCI-Net. This research provides a valuable reference for achieving lightweight, accurate, and high-performance medical image segmentation network models.

The escalating prevalence of diabetes mellitus underscores the critical need for non-invasive screening tools capable of early disease detection. Present diagnostic techniques depend on invasive procedures, which highlights the need for advancement of non-invasive alternatives for initial disease detection. Machine learning in integration with the optical sensing technology can effectively analyze the signal patterns associated with diabetes. The objective of this research is to develop and evaluate a non-invasive optical-based method combined with machine learning algorithms for the classification of individuals into normal, prediabetic, and diabetic categories. A novel device was engineered to capture real-time optical vascular signals from participants representing the three glycemic states. The signals were then subjected to quality assessment and preprocessing to ensure data reliability. Subsequently, feature extraction was performed using time-domain analysis and wavelet scattering techniques to derive meaningful characteristics from the optical signals. The extracted features were subsequently employed to train and validate a suite of machine learning algorithms. An ensemble bagged trees classifier with wavelet scattering features and random forest classifier with time-domain features demonstrated superior performance, achieving an overall accuracy of 86.6% and 80.0% in differentiating between normal, prediabetic, and diabetic individuals based on the optical vascular signals. The proposed non-invasive optical-based approach, coupled with advanced machine learning techniques, holds promise as a potential screening tool for diabetes mellitus. The classification accuracy achieved in this study warrants further investigation and validation in larger and more diverse populations.

Objective. Methods of detecting apnea based on acoustic features can be prone to misdiagnosed and missed diagnoses due to the influence of noise. The aim of this paper is to improve the performance of apnea detection algorithms in the Post Anesthesia Care Unit (PACU) using a denoising method that processes tracheal sounds without the need for separate background noise.Approach. Tracheal sound data from laboratory subjects was collected using a microphone. Record a segment of clinical background noise and clean tracheal sound data to synthesize the noisy tracheal sound data according to a specified signal-to-noise ratio. Extract the frequency-domain features of the tracheal sounds using the Short Time Fourier Transform (STFT) and input the Cascaded Redundant Convolutional Encoder-Decoder network (CR-CED) network for training. Patients' tracheal sound data collected in the PACU were then fed into the CR-CED network as test data and inversely transformed by STFT to obtain denoised tracheal sounds. The apnea detection algorithm was used to detect the tracheal sound after denoising.Results. Apnea events were correctly detected 207 times and normal respiratory events 11,305 times using tracheal sounds denoised by the CR-CED network. The sensitivity and specificity of apnea detection were 88% and 98.6%, respectively.Significance. The apnea detection results of tracheal sounds after CR-CED network denoising in the PACU are accurate and reliable. Tracheal sound can be denoised using this approach without separate background noise. It effectively improves the applicability of the tracheal sound denoising method in the medical environment while ensuring its correctness.

Steady-State Visual Evoked Potentials (SSVEPs) are brain responses measurable via electroencephalography (EEG) in response to continuous visual stimulation at a constant frequency. SSVEPs have been instrumental in advancing our understanding of human vision and attention, as well as in the development of brain-computer interfaces (BCIs). Ongoing questions remain about which type of visual stimulus causes the most potent SSVEP response. The current study investigated the effects of color, size, and flicker frequency on the signal-to-noise ratio of SSVEPs, complemented by pupillary light reflex measurements obtained through an eye-tracker. Six participants were presented with visual stimuli that differed in terms of color (white, red, green), shape (circles, squares, triangles), size (10,000 to 30,000 pixels), flicker frequency (8 to 25 Hz), and grouping (one stimulus at a time versus four stimuli presented in a 2 × 2 matrix to simulate a BCI). The results indicated that larger stimuli elicited stronger SSVEP responses and more pronounced pupil constriction. Additionally, the results revealed an interaction between stimulus color and flicker frequency, with red being more effective at lower frequencies and white at higher frequencies. Future SSVEP research could focus on the recommended waveform, interactions between SSVEP and power grid frequency, a wider range of flicker frequencies, a larger sample of participants, and a systematic comparison of the information transfer obtained through SSVEPs, pupil diameter, and eye movements.

The importance of real-time dose evaluation has increased for recent advanced radiotherapy. However, conventional methods for real-time dosimetry using gel dosimeters face challenges owing to the delayed dose response caused by the slow completion of radiation-induced chemical reactions. In this study, a novel technique called photoluminescence-detected pulse radiolysis (PLPR) was developed, and its potential to allow real-time dose measurements using nano-clay radio-fluorogenic gel (NC-RFG) dosimeters was investigated. PLPR is a time-resolved observation method, and enables time-resolved fluorescence measurement. NC-RFG dosimeters were prepared, typically consisting of 100 μM dihydrorhodamine 123 (DHR123) and 2.0 wt.% nano-clay, along with catalytic and dissolving additives. We successfully achieved time-resolved observation of the increase in fluorescence intensity upon irradiation of the dosimeter. Dose evaluation was possible at 1 s after irradiation. The dose-rate effect was not observed for the deoxygenated dosimeter, but was observed for the aerated dosimeter. Besides the dose-rate effect, linear dose responses were obtained for both conditions. Furthermore, we made a novel observation of a decay in the fluorescence intensity over time in the early stages which named fluorescence secondary loss (FSL) and elucidated the conditions under which this phenomenon occurs.

Objective. We propose a criterion of biological effectiveness of nonuniform hypoxia-targeted dose distributions in heterogeneous hypoxic tumors based on equivalent uniform aerobic dose (EUAD). We demonstrate the utility of this criterion by applying it to the model problems in radiotherapy for tumors with different levels of oxygen enhancement ratio (OER) and different degrees of dose nonuniformity.Approach. The EUAD is defined as the uniform dose that, under well-oxygenated conditions, produces equal integrated survival of clonogenic cells in radiotherapy for heterogeneous hypoxic tumors with a non-uniform dose distribution. We define the dose nonuniformity effectiveness (DNE) in heterogeneous tumors as the ratio of the EUAD(D_N) for a non-uniform distributionD_Nand the reference EUAD(D_U) for the uniform dose distributionD_Uwith equal integral tumor dose. The DNE concept is illustrated in a radiotherapy model problem for non-small cell lung cancer treated with hypoxia targeted dose escalation. A two-level cell population tumor model was used to consider the hypoxic and oxygenated tumor cells.Results. Theoretical analysis of the DNE shows that the entire region of the OER can be separated in two regions by a threshold OER_th: (1) OER > OER_thwhere DNE > 1 indicating higher effectiveness of nonuniform dose distributions and (2) OER < OER_thwhere DNE < 1 indicating higher effectiveness of uniform dose distributions. Our simulations show that the value of the threshold OER_thin radiotherapy with conventional fractionation is significant in the range of about 1.2-1.6 depending on selected radiotherapy parameters. In general, the OER_thincreases with reoxygenation rate, relative hypoxic volume and dose escalation factor. The threshold value of OER_this smaller of about 1.1 for hypofractionated radiotherapy.Significance. The analysis of dose distributions using the DNE shows that the uniform dose distributions may improve biological cell killing effect in heterogeneous tumors with intermediate oxygen levels compared to targeted nonuniform dose distribution.

The colonic peristaltic pressure signal is helpful for the diagnosis of intestinal diseases, but it is difficult to reflect the real situation of colonic peristalsis due to the interference of various factors. To solve this problem, an improved wavelet threshold denoising method based on discrete wavelet transform is proposed in this paper. This algorithm can effectively extract colonic peristaltic pressure signals and filter out noise. Firstly, a threshold function with three shape adjustment factors is constructed to give the function continuity and better flexibility. Then, a threshold calculation method based on different decomposition levels is designed. By adjusting the three preset shape factors, an appropriate threshold function is determined, and denoising of colonic pressure signals is achieved through hierarchical thresholding. In addition, the experimental analysis of bumps signal verifies that the proposed denoising method has good reliability and stability when dealing with non-stationary signals. Finally, the denoising performance of the proposed method was validated using colonic pressure signals. The experimental results indicate that, compared to other methods, this approach performs better in denoising and extracting colonic peristaltic pressure signals, aiding in further identification and treatment of colonic peristalsis disorders.

Purpose. Bolus is often required for targets close to or on skin surface, however, standard bolus on complex surfaces can result in air gaps that compromise dosimetry. Brass mesh boluses (RPD, Inc., Albertville, MN) are designed to conform to the patient's surface and reduce air gaps. While they have been well characterized for their use with photons, minimal characterization exists in literature for their use with electrons.Methods and materials.Dosimetric characteristics of brass mesh bolus was investigated for use with 6, 9 and 12 MeV electrons using a 10 × 10 cm²applicator on standard multi-energy LINAC. Measurements for bolus equivalence and percentage depth doses (PDDs) under brass mesh, as well as surface dose measurements were performed on solid water and a 3D printed resin breast phantom (Anycubic Photon MonoX, Shenzhen, China) using Markus^®parallel-plate ionization chamber (Model 34045, PTW Freiburg, Germany), thermoluminescent detectors (TLD) and EBRT film. After obtaining surface dose measurements, these were compared to dose calculated on the Pinnacle3 treatment planning system (TPS, 16.2, Koninklijke Philips N.V.).Results. Measurements of surface dose under brass mesh showed consistently higher dose than without bolus, confirming that brass mesh can increase the PDD at surface up to ∼ 94% of dose at d_max, depending on incident electron energy. This increase is equivalent to using ∼ 7.2 mm water equivalent bolus for 6 MeV, ∼ 3.6 mm for 9 MeV and ∼ 2.2 mm bolus for 12 MeV electrons. TPS results showed close agreement within-vivomeasurements, confirming the potential for brass mesh as bolus for electron irradiation, provided blousing effect is correctly modelled.Conclusions. To increase electron surface dose, a brass mesh can be used with equivalent effect of water-density bolus varying with electron energy. Proper implementation could allow for ease of treatment, as well as increase bolus conformality in electron-only plans.

Objectives. The paper proposes a novel methodology for the classification of Chronic Obstructive Pulmonary Disease (COPD) utilizing respiratory sound attributes.Methods. The approach involves segmenting respiratory sounds into individual breaths and conducting extensive studies on this dataset. Spectral Transforms, various Wavelet Transforms are applied to capture distinct signal features. Complex Network is also employed to extract characteristic elements, generating novel representations of spectrogram data based on graph factors, including entropy, density, and position. The normalized and enriched data is then used to develop COPD classifiers using six machine learning algorithms, fine-tuning with appropriate training details and hyperparameter tuning.Results. Our results demonstrate robust performance, with ROC curves consistently exhibiting an Area Under the Curve (AUC) > 96% across different time-frequency transformations. Notably, the Random Forest algorithm achieves an AUC of 99.67%, outperforming other algorithms. Moreover, the Wavelet Daubechies 2 (Db2) consistently approaches 98% accuracy, particularly noteworthy in conjunction with the Naive Bayes algorithm.Conclusion. This study diagnosis patients through spectrogram images extracted from lung sounds. The application of Inverse Transforms, Complex Network, and Optimized Classification Algorithms yielded results beyond expectations. This methodology provides a promising approach for accurate COPD diagnosis, leveraging Machine Learning techniques applied to respiratory sound analysis.

Background. In the context of pharmacokinetic analyses, the segmentation method one uses has a large impact on the results obtained, thus the importance of transparency.Innovation. This paper introduces a graphical user interface (GUI), TRU-IMP, that analyzes time-activity curves and segmentations in dynamic nuclear medicine. This GUI fills a gap in the current technological tools available for the analysis of quantitative dynamic nuclear medicine image acquisitions. The GUI includes various techniques of segmentations, with possibilities to compute related uncertainties.Results. The GUI was tested on image acquisitions made on a dynamic nuclear medicine phantom. This allows the comparison of segmentations via their time-activity curves and the extracted pharmacokinetic parameters.Implications. The flexibility and user-friendliness allowed by the proposed interface make the analyses both easy to perform and adjustable to any specific case. This GUI permits researchers to better show and understand the reproducibility, precision, and accuracy of their work in quantitative dynamic nuclear medicine.Availability and Implementation. Source code freely available on GitHub:https://github.com/ArGilfea/TRU-IMPand location of the interface available from there. The GUI is fully compatible with iOS and Windows operating systems (not tested on Linux). A phantom acquisition is also available to test the GUI easily.