Template-based balloon-marker and guidewire detection for coronary stents in cardiac fluoroscopy.

The placement and visualization of coronary stents during fluoroscopy depends mainly on the detection of balloon markers and their connecting guidewires. In this paper, a novel template-based approach is proposed to detect balloon markers and guidewires in cardiac fluoroscopic images. In particular, guidewires are detected based on balloon markers only, without prior knowledge of the background or guidewire elements. Also, while earlier techniques used circular models of balloon markers, we propose a more realistic elliptical model. Training and the testing datasets for balloon marker and guidewire detection were collected from different Cathlab systems and annotated by an application specialist with 10 years of experience in this field. The balloon-marker detector achieved a precision of 98.5%. Within 3-pixel tolerance, the guidewire detector achieved a matching percentage of 99.5% with the true guidewire using a customized evaluation method. Moreover, the guidewire detector achieved a mean Hausdorff distance of 3.3 pixels (0.6 mm) and a longest-common-substring (LCS) distance with a mean matching percentage of 87% within 1-pixel tolerance. Clinical Relevance- The proposed novel technique of detecting the guidewire offers a constant computational time and insensitivity to the body structures or the guidewire-like elements (such as the surgical wires). This leads to improved stent visualization and reasonable processing times.

Feature and decision-level fusion for schizophrenia detection based on resting-state fMRI data.

Mental disorders, especially schizophrenia, still pose a great challenge for diagnosis in early stages. Recently, computer-aided diagnosis techniques based on resting-state functional magnetic resonance imaging (Rs-fMRI) have been developed to tackle this challenge. In this work, we investigate different decision-level and feature-level fusion schemes for discriminating between schizophrenic and normal subjects. Four types of fMRI features are investigated, namely the regional homogeneity, voxel-mirrored homotopic connectivity, fractional amplitude of low-frequency fluctuations and amplitude of low-frequency fluctuations. Data denoising and preprocessing were first applied, followed by the feature extraction module. Four different feature selection algorithms were applied, and the best discriminative features were selected using the algorithm of feature selection via concave minimization (FSV). Support vector machine classifiers were trained and tested on the COBRE dataset formed of 70 schizophrenic subjects and 70 healthy subjects. The decision-level fusion method outperformed the single-feature-type approaches and achieved a 97.85% accuracy, a 98.33% sensitivity, a 96.83% specificity. Moreover, feature-fusion scheme resulted in a 98.57% accuracy, a 99.71% sensitivity, a 97.66% specificity, and an area under the ROC curve of 0.9984. In general, decision-level and feature-level fusion schemes boosted the performance of schizophrenia detectors based on fMRI features.

Electromyography Signal Analysis and Classification using Time-Frequency Representations and Deep Learning.

Analysis and classification of electromyography (EMG) signals are crucial for rehabilitation and motor control. This study investigates electromyogram (EMG) time-frequency representations and then creates conventional and deep learning models for EMG signal classification. Firstly, a dataset of single-channel surface EMG signals has been recorded for four subjects to differentiate between forearm flexion and extension. Then, different time-frequency EMG representations have been used to build conventional and deep learning models for EMG classification. We compared the performance of pre-trained convolutional neural network models, namely GoogLeNet, SqueezeNet and AlexNet, and achieved accuracies of 92.71%, 90.63% and 87.5%, respectively. Also, data augmentation techniques on the levels of raw EMG signals and their time- frequency representations helped improve the accuracy of GoogLeNet to 96.88%. Furthermore, our approach demonstrated superior performance on another publicly available 10-class EMG dataset, and also using traditional classifiers trained on hand-crafted features.

Melanoma Detection Using Spatial and Spectral Analysis on Superpixel Graphs.

Melanoma is the most fatal type of skin cancer. Detection of melanoma from dermoscopic images in an early stage is critical for improving survival rates. Numerous image processing methods have been devised to discriminate between melanoma and benign skin lesions. Previous studies show that the detection performance depends significantly on the skin lesion image representations and features. In this work, we propose a melanoma detection approach that combines graph-theoretic representations with conventional dermoscopic image features to enhance the detection performance. Instead of using individual pixels of skin lesion images as nodes for complex graph representations, superpixels are generated from the skin lesion images and are then used as graph nodes in a superpixel graph. An edge of such a graph connects two adjacent superpixels where the edge weight is a function of the distance between feature descriptors of these superpixels. A graph signal can be defined by assigning to each graph node the output of some single-valued function of the associated superpixel descriptor. Features are extracted from weighted and unweighted graph models in the vertex domain at both local and global scales and in the spectral domain using the graph Fourier transform (GFT). Other features based on color, geometry and texture are extracted from the skin lesion images. Several conventional and ensemble classifiers have been trained and tested on different combinations from those features using two datasets of dermoscopic images from the International Skin Imaging Collaboration (ISIC) archive. The proposed system achieved an AUC of [Formula: see text], an accuracy of [Formula: see text], a specificity of [Formula: see text] and a sensitivity of [Formula: see text].

Optimisation of medical equipment replacement using stochastic dynamic programming.

In this paper, the medical equipment replacement strategy is optimised using a multistage stochastic dynamic programming (SDP) approach. The outcome is an optimal path which shows whether to keep an existing piece of medical equipment (defender) or replace it with a more economical alternative (challenger). We assume that each decision can result in a number of different possible outcomes, each with a known probability. Contrary to deterministic dynamic programming, the state at the next stage is not completely determined by the state and policy decision at the current stage. Instead, the next stage depends on the operation and maintenance cost which is modelled as a stochastic variable. A Keep-Replace sequence of the highest returns (lowest costs) is the result of solving the problem using forward decision making. The benefit of the SDP solution versus that of keeping medical equipment until the end of its expected life is investigated for three scenarios: (1) no revenue for the defender and the challenger, (2) equal revenues for both, and (3) higher revenue for the challenger. The percentage of benefits relative to the current acquisition cost for the three scenarios are 616.9%, 728.2%, and 789.29%, respectively. Each percentage represents the relative difference between the equipment life cycle cost of the optimal sequence and that of the conventional sequence.

Wavelet-based Computationally-Efficient Computer-Aided Characterization of Liver Steatosis using Conventional B-mode Ultrasound Images.

Hepatic steatosis occurs when lipids accumulate in the liver leading to steatohepatitis, which can evolve into cirrhosis and consequently may end with hepatocellular carcinoma. Several automatic classification algorithms have been proposed to detect liver diseases. However, some algorithms are manufacturer-dependent, while others require extensive calculations and consequently prolonged computational time. This may limit the development of real-time and manufacturer-independent computer-aided detection of liver steatosis. This work demonstrates the feasibility of a computationally-efficient and manufacturer-independent wavelet-based computer-aided liver steatosis detection system using conventional B-mode ultrasound (US) imaging. Seven features were extracted from the approximation part of the second-level wavelet packet transform (WPT) of US images. The proposed technique was tested on two datasets of ex-vivo mice livers with and without gelatin embedding, in addition to a third dataset of in-vivo human livers acquired using two different US machines. Using the gelatin-embedded mice liver dataset, the technique exhibited 98.8% accuracy, 97.8% sensitivity, and 100% specificity, and the frame classification time was reduced from 0.4814 s using original US images to 0.1444 s after WPT preprocessing. When the other mice liver dataset was used, the technique showed 85.74% accuracy, 84.4% sensitivity, and 88.5% specificity, and the frame classification time was reduced from 0.5612s to 0.2903 s. Using human liver image data, the best classifier exhibited 92.5% accuracy, 93.0% sensitivity, 91.0% specificity, and the classification time was reduced from 0.660 s to 0.146 s. This technique can be useful for developing computationally-efficient and manufacturer-independent noninvasive CAD systems for fatty liver detection.

Morphological characterization of breast tumors using conventional B-mode ultrasound images.

This work aims to develop and test a vendor-independent computer-aided diagnosis (CAD) system that uses conventional B-mode ultrasound images to distinguish between benign and malignant breast tumors. Three morphological features were extracted from 323 breast tumor lesions including the perimeter, regularity variance, and circularity range ratio. Lesions were segmented using the active contour method via semi- andfully-automated algorithms. Then, the support vector machine classifier was used to identify breast lesions. Results of the CAD system exhibited accuracies of 95.98% and 95.67%using the semi- and fully-automated segmentation, respectively. Based on the preliminary results, this CAD system with such unique combination of geometrical features shall improve the diagnostic decisions and may reduce the need of unnecessary needle biopsies.

Tag removal in cardiac tagged MRI images using coupled dictionary learning.

Tagged Magnetic Resonance Imaging (tMRI) is considered to be the gold standard for quantitative assessment of the cardiac local functions. However, the tagging patterns and low myocardium-to-blood-pool contrast of tagged images bring great challenges to cardiac image processing and analysis tasks such as myocardium segmentation and tracking. Hence, there has been growing interest in techniques for removing tagging lines. In this work, a method for removing tagging patterns in tagged MR images using a coupled dictionary learning (CDL) model is proposed. In this model, identical sparse representations are assumed for image patches in the tagged MRI and corresponding cine MRI image spaces. First, we learn a dictionary for the tagged MRI image space. Then, we compute a dictionary for the cine MRI image space so that corresponding tagged and cine patches have the same sparse codes in terms of their respective dictionaries. Finally, in order to produce the de-tagged (cine version) of a test tagged image, the sparse codes of the tagged patches and the trained cine dictionary are used together to construct the de-tagged patches. We have tested this tag removal method on a dataset of tagged cardiac MR images. Our experimental results compared favorably with a recently proposed tag removal method that removes tags in the frequency domain using an optimal band-stop filter of harmonic peaks.

Speckle reduction in medical ultrasound: a novel scatterer density weighted nonlinear diffusion algorithm implemented as a neural-network filter.

This paper proposes a novel algorithm for speckle reduction in medical ultrasound imaging while preserving the edges with the added advantages of adaptive noise filtering and speed. We propose a nonlinear image diffusion algorithm that incorporates two local parameters of image quality, namely, scatterer density and texture-based contrast in addition to gradient, to weight the nonlinear diffusion process. The scatterer density is proposed to replace the existing traditional measures of quality of the ultrasound diffusion process such as MSE, RMSE, SNR, and PSNR. This novel diffusion filter was then implemented using back propagation neural network for fast parallel processing of volumetric images. The experimental results show that weighting the image diffusion with these parameters produces better noise reduction and produces a better edge detection quality with reasonable computational cost. The proposed filter can be used as a preprocessing phase before applying any ultrasound segmentation or active contour model processes.