Computer Methods in Biomechanics and Biomedical Engineering-Imaging and Visualization最新文献

We propose an automatic pipeline for creating shape modelling suitable parametric meshes of the trapeziometacarpal (TMC) joint from clinical CT images for the purpose of batch processing and analysis. The method uses 3D random forest regression voting (RFRV) with statistical shape model (SSM) segmentation. The method was demonstrated in a validation experiment involving 65 CT images, 15 of which were randomly selected to be excluded from the training set for testing. With mean root mean squared (RMS) errors of 1.066 mm and 0.632 mm for the first metacarpal and trapezial bones respectively, and a segmentation time of ~2 minutes per CT image, the preliminary results showed promise for providing accurate 3D meshes of TMC joint bones for batch processing.

Digital pathology has advanced substantially over the last decade with the adoption of slide scanners in pathology labs. The use of digital slides to analyse diseases at the microscopic level is both cost-effective and efficient. Identifying complex tumour patterns in digital slides is a challenging problem but holds significant importance for tumour burden assessment, grading and many other pathological assessments in cancer research. The use of convolutional neural networks (CNNs) to analyse such complex images has been well adopted in digital pathology. However, in recent years, the architecture of CNNs has altered with the introduction of inception modules which have shown great promise for classification tasks. In this paper, we propose a modified 'transition' module which encourages generalisation in a deep learning framework with few training samples. In the transition module, filters of varying sizes are used to encourage class-specific filters at multiple spatial resolutions followed by global average pooling. We demonstrate the performance of the transition module in AlexNet and ZFNet, for classifying breast tumours in two independent data-sets of scanned histology sections; the inclusion of the transition module in these CNNs improved performance.

Segmentation of epicardial and endocardial boundaries is a critical step in diagnosing cardiovascular function in heart patients. The manual tracing of organ contours in Computed Tomography Angiography (CTA) slices is subjective, time-consuming and impractical in clinical setting. We propose a novel multi-dimensional automatic edge detection algorithm based on shape priors and principal component analysis (PCA). We have developed a highly customized parametric model for implicit representations of segmenting curves (3D) for Left Ventricle (LV), Right Ventricle (RV), and Epicardium (Epi) used simultaneously to achieve myocardial segmentation. We have combined these representations in a region-based image modeling framework with high level constraints enabling the modeling of complex cardiac anatomical structures to automatically guide the segmentation of endo/epicardial boundaries. Test results on 30 short-axis CTA datasets show robust segmentation with error (mean ± std mm) of (1.46 ± 0.41), (2.06 ± 0.65), (2.88 ± 0.59) for LV, RV and Epi respectively.

The collagen fibers in the superficial layer of tibiofemoral articular cartilage exhibit distinct patterns in orientation revealed by split lines. In this study, we introduce a simulation framework to predict cartilage surface loading during walking to investigate if split line orientations correspond with principal strain directions in the cartilage surface. The two-step framework uses a multibody musculoskeletal model to predict tibiofemoral kinematics which are then imposed on a deformable surface model to predict surface strains. The deformable surface model uses absolute nodal coordinate formulation (ANCF) shell elements to represent the articular surface and a system of spring-dampers and internal pressure to represent the underlying cartilage. Simulations were performed to predict surface strains due to osmotic pressure, loading induced by walking, and the combination of both loading due to pressure and walking. Time-averaged magnitude-weighted first principal strain directions agreed well with split line maps from the literature for both the osmotic pressure and combined cases. This result suggests there is indeed a connection between collagen fiber orientation and mechanical loading, and indicates the importance of accounting for the pre-strain in the cartilage surface due to osmotic pressure.

Deep brain stimulation (DBS) is an established therapy for treating patients with movement disorders such as Parkinson's disease. Patient-specific computational modelling and visualisation have been shown to play a key role in surgical and therapeutic decisions for DBS. The computational models use brain imaging, such as magnetic resonance (MR) and computed tomography (CT), to determine the DBS electrode positions within the patient's head. The finite resolution of brain imaging, however, introduces uncertainty in electrode positions. The DBS stimulation settings for optimal patient response are sensitive to the relative positioning of DBS electrodes to a specific neural substrate (white/grey matter). In our contribution, we study positional uncertainty in the DBS electrodes for imaging with finite resolution. In a three-step approach, we first derive a closed-form mathematical model characterising the geometry of the DBS electrodes. Second, we devise a statistical framework for quantifying the uncertainty in the positional attributes of the DBS electrodes, namely the direction of longitudinal axis and the contact-centre positions at subvoxel levels. The statistical framework leverages the analytical model derived in step one and a Bayesian probabilistic model for uncertainty quantification. Finally, the uncertainty in contact-centre positions is interactively visualised through volume rendering and isosurfacing techniques. We demonstrate the efficacy of our contribution through experiments on synthetic and real datasets. We show that the spatial variations in true electrode positions are significant for finite resolution imaging, and interactive visualisation can be instrumental in exploring probabilistic positional variations in the DBS lead.

Statistical modeling of tongue motion during speech using cine magnetic resonance imaging (MRI) provides key information about the relationship between structure and motion of the tongue. In order to study the variability of tongue shape and motion in populations, a consistent integration and characterization of inter-subject variability is needed. In this paper, a method to construct a spatio-temporal atlas comprising a mean motion model and statistical modes of variation during speech is presented. The model is based on the cine-MRI from twenty two normal speakers and consists of several steps involving both spatial and temporal alignment problems independently. First, all images are registered into a common reference space, which is taken to be a neutral resting position of the tongue. Second, the tongue shapes of each individual relative to this reference space are produced. Third, a time warping approach (several are evaluated) is used to align the time frames of each subject to a common time series of initial mean images. Finally, the spatio-temporal atlas is created by time-warping each subject, generating new mean images at each time, and producing shape statistics around these mean images using principal component analysis at each reference time frame. Experimental results consist of comparison of various parameters and methods in creation of the atlas and a demonstration of the final modes of variations at various key time frames in a sample phrase.

The human tongue has a complex architecture, consistent with its complex roles in eating, speaking and breathing. Tongue muscle architecture has been depicted in drawings and photographs, but not quantified volumetrically. This paper aims to fill that gap by measuring the muscle architecture of the tongue for 14 people captured in high-resolution 3D MRI volumes. The results show the structure, relationships and variability among the muscles, as well as the effects of age, gender and weight on muscle volume. Since the tongue consists of partially interdigitated muscles, we consider the muscle volumes in two ways. The functional muscle volume encompasses the region of the tongue served by the muscle. The structural volume halves the volume of the muscle in regions where it interdigitates with other muscles. Results show similarity of scaling across subjects, and speculate on functional effects of the anatomical structure.

Interstitial lung diseases (ILD) involve several abnormal imaging patterns observed in computed tomography (CT) images. Accurate classification of these patterns plays a significant role in precise clinical decision making of the extent and nature of the diseases. Therefore, it is important for developing automated pulmonary computer-aided detection systems. Conventionally, this task relies on experts' manual identification of regions of interest (ROIs) as a prerequisite to diagnose potential diseases. This protocol is time consuming and inhibits fully automatic assessment. In this paper, we present a new method to classify ILD imaging patterns on CT images. The main difference is that the proposed algorithm uses the entire image as a holistic input. By circumventing the prerequisite of manual input ROIs, our problem set-up is significantly more difficult than previous work but can better address the clinical workflow. Qualitative and quantitative results using a publicly available ILD database demonstrate state-of-the-art classification accuracy under the patch-based classification and shows the potential of predicting the ILD type using holistic image.

The aim of this study was to visualize improved swallowing mechanics resulting from respiratory-swallow phase training using patient specific computational analysis of Modified Barium Swallow (MBS) videofluoroscopic images. Imaging from a single subject showing improved MBSImP^™© scores in 17 of 18 pre- to post-treatment swallows was selected for analysis. Using a semi-automated MATLAB tracker tool, a frame-by-frame annotation of 10 coordinates mapping muscle functional groups was performed during oropharyngeal swallowing. Computational analysis of coordinate shape change was executed using MorphoJ software to determine differences in swallowing mechanics associated with multiple independent variables. Canonical variant analysis indicated significant differences in mechanics associated with respiratory-swallow phase training (D=1.92,p<.0001). Vectors allowed for visualization of changes in swallowing mechanics associated with respiratory-swallow phase training. A regression of shape associated with laryngeal vestibular closure on respiratory-swallow phase training was highly significant (p<.0001) and accounted for 94.1% of the variance.