Irbm最新文献

Objectives

Inertial Measurement Units (IMUs) are a valid alternative to optical tracking systems for human motion capture, but they are subject to several disturbances that limit their accuracy. We aim to improve the accuracy of elbow joint angle estimation from IMU measurements by introducing a novel postprocessing algorithm that uses anatomical constraints and does not require any prior calibration or knowledge of anthropometric parameters.

Materials and Methods

We propose a new error model that addresses sensor misalignment and fusion errors. We use an error state extended Kalman filter (ESEKF) with state constraints to integrate the anatomical constraints. We validate the proposed algorithm by testing it in different scenarios and comparing it with a state-of-the-art optical tracking system.

Results

The research results highlight the superior performance of the proposed method compared with existing techniques. The study demonstrates a significant reduction in errors, particularly in complex arm movements and under strong external disturbances. The results obtained in the three different tested scenarios underscore the robustness and effectiveness of the developed algorithm, reaching half the error committed by the existing calibration-free correction algorithms proposed in the literature.

Conclusions

The developed technique provides highly accurate estimates of joint angles in several challenging real-world scenarios.

Objectives

Many molecular imaging diagnoses involve comparing two regions of interest (ROIs) in the image or different images. Since the images are obtained by measuring a random phenomenon, such comparisons should be based on a statistical test to ensure reliability. Recent studies have shown that use of the bootstrap approach provides access to the statistical variability of reconstructed values in molecular images. However, although there is general agreement that this increase in information should make diagnosis based on molecular images more reliable, no approach has been proposed in the relevant literature to use bootstrap replicates to enhance the reliability of comparisons of two ROIs. In this paper, we propose to fill this gap by introducing the first statistical test that allows us to compare two sets of pixels/voxels for which bootstrap replicates are available.

Material and methods

After presenting the theoretical basis of this non-parametric statistical test, this article describes how to calculate it in practice. Finally, it proposes two experiments based on quantitative comparisons and expert judgment to assess its relevance.

Results

The results obtained are consistent with expert diagnosis on synthetic data. This validates the relevance of the D-test.

Conclusion

This paper presents the first statistical test to compare two ROIs in reconstructed images for which the statistical variability information is accessible.

Objective

Constructing a 3D model from its 2D images, known as 2D-3D reconstruction, is a challenging task. Conventionally, a parametric 3D model such as a statistical shape model (SSM) is deformed by matching the shapes in its 2D images through a series of processes, including calibration, 2D-3D registration, and optimization for nonrigid deformation. To overcome this complicated procedure, a streamlined 2D-3D reconstruction using a single X-ray image is developed in this study.

Methods

We propose 2D-3D reconstruction of a femur by adopting a deep neural network, where the deformation parameters in the SSM determining the 3D shape of the femur are predicted from a single X-ray image using a deep transfer-learning network. For learning the network from distinct features representing the 3D shape information in the X-ray image, a specific proximal part of the femur from a unique X-ray pose that allows accurate prediction of the 3D femur shape is designated and used to train the network. Then, the corresponding proximal/distal 3D femur model is reconstructed from only the single X-ray image acquired at the designated position.

Results

Experiments were conducted using actual X-ray images of a femur phantom and X-ray images of a patient's femur derived from computed tomography to verify the proposed method. The average errors of the reconstructed 3D shape of the proximal and distal femurs from the proposed method were 1.20 mm and 1.08 mm in terms of root mean squared point-to-surface distance, respectively.

Conclusion

The proposed method presents an innovative approach to simplifying the 2D-3D reconstruction using deep neural networks that exhibits performance compatible with the existing methodologies.

Obstetric gynaecology, as a field in which diagnostic ultrasound has quickly found its place, especially in screening for birth defects and monitoring pregnancies, is also a speciality in which therapeutic ultrasound is used extensively.

In pelvic gynaecology, HIFU therapy is used more specifically in two types of uterine conditions: fibroids and adenomyosis. In both cases, studies have shown significant efficacy in reducing pain and bleeding associated with the conditions, secondarily (more moderately but still significantly) reducing the volume of the lesions. Impact on fertility has yet to be demonstrated.

In rectosigmoid endometriosis, clinical data indicates good treatment feasibility and significant efficacy on digestive and gynaecologic pain symptoms, as well as on quality of life, with no associated severe complications. Should the efficacy of HIFU in treating endometriosis be confirmed over time, it could revolutionise the management of digestive endometriosis by offering a valid minimally invasive alternative to rectosigmoid surgery.

In senology, where visible scars have a particularly significant psychological impact, several teams have been researching the use of HIFU for the destruction of some types of breast lesions (fibroadenomas and breast tumours).

In obstetrics, HIFU could become a treatment of choice for vascular anomalies such as twin-to-twin transfusion syndrome in twin pregnancies. Promising studies are also available regarding the use of HIFU in the treatment of post-partum placenta accreta.

Background

Monitoring of wound healing progression is critical due to the risk of infection, non-healing wounds, or evolution towards a chronic state. Tissue vasculature is one of the most representative features reflecting healing status. This study explores the feasibility of vascular ultrasound imaging of open wounds and the extraction of vascular-related features in a longitudinal study.

Material and methods

C57BL/6 mice received a 1 cm-diameter full-thickness wound on their dorsum and were imaged using ultrasound from the surgical day (Day 0) to 25 days post-wounding. The high frame rate, plane waves acquisitions with a 15 MHz transducer were postprocessed with Singular Value Decomposition (SVD) filtering to provide vascular information.

Results

Vascularity Index (VI) calculations showed an increased vascular signal in the wound from Day 2 post-wounding and were significantly higher from day 6 to day 10 post-wounding compared to Day 0 (p<0.05). VI values were back to the basal level after 3 weeks. In comparison, no significant difference was highlighted for the vascular signal in the peri-wound area.

Conclusions

These results show that vascular ultrasound imaging can be applied to track vascular changes of open wounds during the healing process. This approach may also be extended to other types of wounds for detecting early signs likely to cause complications.

Background: Wall shear stress (WSS) plays an indispensable role in shaping the trajectory of vascular diseases such as atherosclerosis and aneurysms. Specific patterns of low and oscillating WSS are implicated in the promotion of plaque accumulation, whereas elevated WSS levels are associated with inflammatory responses, the synthesis of metalloproteases, and eventual rupture of plaque. Therefore, an accurate, noninvasive quantification of local hemodynamics and WSS is integral to the precise diagnosis of vascular disorders. Ultrasound imaging has emerged as a favored modality for measuring the WSS owing to its noninvasive nature, ease of access, and user-friendly interface. However, existing reviews primarily focus on the assessment of blood flow characteristics, including velocity profiles and volume flow rates. To the best of our knowledge, thus far, no review has been dedicated to ultrasound imaging techniques for the measurement of in vivo WSS.

Purpose: This study aimed to perform a thorough overview of current and emerging ultrasound imaging methodologies tailored for in vivo WSS quantification.

Basic procedure: The fundamental principles of WSS measurements were explored, and various techniques—-Doppler ultrasound imaging, ultrasound imaging velocimetry, and speckle decorrelation—-that are employed for WSS assessment were studied.

Main findings: These techniques show promise for clinical applications by facilitating noninvasive and accurate WSS measurements of vital parameters concerning vascular physiology. Further investigations are warranted to overcome specific challenges, such as the accurate detection of vascular wall boundaries.

Conclusions: The findings of this review are anticipated to contribute to advancements in ultrasound imaging techniques for in vivo WSS measurements.

Objectives

Intravascular optical coherence tomography (IVOCT) is a crucial micro-resolution imaging modality used to assess the internal structure of blood vessels. Lumen segmentation in IVOCT images is vital for measuring the location and the extent of vessel blockages and for guiding percutaneous coronary intervention. Obtaining such information in real-time is essential, necessitating the use of fast automated algorithms. In this paper, we proposed an innovative polynomial-regression convolutional neural network (CNN) for fast and automated IVOCT lumen segmentation.

Materials and methods

The polynomial-regression CNN architecture was uniquely crafted to enable single-pass extraction of lumen borders via IVOCT image regression, ensuring real-time processing efficiency without compromising accuracy. The architecture designed convolution for regression while omitting fully connected layers, leading to the spatial output of lumen representation as polynomial coefficients, thus enabling the formation of interconnected lumen points. The approach equipped the network to comprehend the intricate and continuous geometries and curvatures intrinsic to blood vessels in transverse and longitudinal dimensions. The network was trained on a dataset of 16,165 images and evaluated using 7,016 images.

Results

The predicted segmentations exhibited a distance error of less than 2 pixels (26.40 μm), Dice's coefficient of 0.982, Jaccard Index of 0.966, sensitivity of 0.980, specificity of 0.999, and a prediction time of 4 s (for a pullback containing 360 images). This technique demonstrated significantly improved performance in both accuracy and speed compared to published techniques.

Conclusion

The strong segmentation performance, fast speed, and robustness to image variations highlight the practical clinical utility of the proposed polynomial-regression network.

The Brain-Computer Interface (BCI) system based on motor imagery (MI) is a hot research topic nowadays, which can control external devices through the brain and has a wide range of applications in rehabilitation, gaming, and entertainment. Due to the non-smooth, non-linear, and low signal-to-noise ratio of the MI EEG signal, it is challenging to accurately decode the MI task intention. A new end-to-end deep learning method is proposed to decode raw MI EEG signals without preprocessing, such as filtering and feature reinforcement. The 1D convolution is used to learn the time-frequency features in MI signals, and a four-branch fusion network is used as the main body to add a 1D CNN-AE block and 1D SE-block to enhance the algorithm's performance. Experiments on two publicly available datasets demonstrate that our proposed algorithm outperforms the current state-of-the-art methods. It achieves 86.11% and 89.51% on the BCI Competition IV-2a and the BCI Competition IV-2b datasets, respectively, and a 6.9% improvement in the generalizability test. The proposed data enhancement method can effectively alleviate the overfitting of the algorithm and improve the decoding performance. Further analysis shows that 1D convolution can effectively extract the features associated with the MI task.