Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Deep learning based classification of breast tumors with shear-wave elastography.

The ultrasound imaging is one of the most common schemes to detect diseases in the clinical practice. There are many advantages of ultrasound imaging such as safety, convenience, and low cost. However, reading ultrasound imaging is not easy. To support the diagnosis of clinicians and reduce the load of doctors, many ultrasound computer-aided diagnosis (CAD) systems are proposed. In recent years, the success of deep learning in the image classification and segmentation led to more and more scholars realizing the potential of performance improvement brought by utilizing the deep learning in the ultrasound CAD system. This paper summarized the research which focuses on the ultrasound CAD system utilizing machine learning technology in recent years. This study divided the ultrasound CAD system into two categories. One is the traditional ultrasound CAD system which employed the manmade feature and the other is the deep learning ultrasound CAD system. The major feature and the classifier employed by the traditional ultrasound CAD system are introduced. As for the deep learning ultrasound CAD, newest applications are summarized. This paper will be useful for researchers who focus on the ultrasound CAD system.

/pdf/machine-learning-in-ultrasound-computer-aided-diagnostic-58mdlay4eg.pdf

Machine Learning in Ultrasound Computer-Aided Diagnostic Systems: A Survey.

A radiomics approach to sonoelastography, called "sonoelastomics," is proposed for classification of benign and malignant breast tumors. From sonoelastograms of breast tumors, a high-throughput 364-dimensional feature set was calculated consisting of shape features, intensity statistics, gray-level co-occurrence matrix texture features and contourlet texture features, which quantified the shape, hardness and hardness heterogeneity of a tumor. The high-throughput features were then selected for feature reduction using hierarchical clustering and three-feature selection metrics. For a data set containing 42 malignant and 75 benign tumors from 117 patients, seven selected sonoelastomic features achieved an area under the receiver operating characteristic curve of 0.917, an accuracy of 88.0%, a sensitivity of 85.7% and a specificity of 89.3% in a validation set via the leave-one-out cross-validation, revealing superiority over the principal component analysis, deep polynomial networks and manually selected features. The sonoelastomic features are valuable in breast tumor differentiation.

/pdf/sonoelastomics-for-breast-tumor-classification-a-radiomics-ld28fgecj8.pdf

Sonoelastomics for Breast Tumor Classification: A Radiomics Approach with Clustering-Based Feature Selection on Sonoelastography

Ultrasound as a well-established imaging modality is widely used in imaging lymph nodes for clinical diagnosis and disease analysis. Quantitative analysis of lymph node features, morphology, and relations can provide valuable information for diagnosis and immune system studies. For such analysis, it is necessary to first accurately segment the lymph node areas in ultrasound images. In this paper, we develop a new deep learning method, called Coarse-to-Fine Stacked Fully Convolutional Nets (CFS-FCN), for automatically segmenting lymph nodes in ultrasound images. Our method consists of multiple stages of FCN modules. We train the CFS-FCN model to learn the segmentation knowledge from a coarse-to-fine, simple-to-complex manner. A data set of 80 ultrasound images containing both normal and diseased lymph nodes is used in our experiments, which show that our method considerably outperforms the state-of-the-art deep learning methods for lymph node segmentation.

Coarse-to-Fine Stacked Fully Convolutional Nets for lymph node segmentation in ultrasound images

Computer-aided quantification of contrast agent spatial distribution within atherosclerotic plaque in contrast-enhanced ultrasound image sequences

Quantification of carotid plaque elasticity and intraplaque neovascularization using contrast-enhanced ultrasound and image registration-based elastography

A multi-scale fuzzy c-means method integrated with particle swarm optimization (MsFCM-PSO) is proposed for ultrasound image segmentation. First, speckle reducing anisotropic diffusion is used to suppress noise in an ultrasound image and construct a series of images at multiple scales. Then the particle swarm optimization is incorporated into the multi-scale fuzzy c-means (MsFCM) to search for the global optima of cluster centers and update the membership of each pixel in a coarse-to-fine fashion. Finally, the image is segmented by assigning each pixel to the cluster with the highest membership. The method was validated on both synthetic and in vivo ultrasound images. It outperformed the traditional fuzzy c-means methods including MsFCM by 39.6% and 13.6%, in terms of the Pratt's figure of merit and segmentation accuracy, respectively. These results demonstrate that the MsFCM-PSO can provide an accurate tool for ultrasound image segmentation.

Ultrasound image segmentation based on multi-scale fuzzy c-means and particle swarm optimization

It is valuable to segment carotid atherosclerotic plaques in contrast-enhanced ultrasound (CEUS) images. Traditional methods for plaque segmentation neglect the temporal information in video images, and it limits the accuracy of the segmentation. We propose an algorithm for accurate segmentation of plaques in CEUS images using spatial-temporal analysis and snakes. First, the spatial correlation of time intensity curves is used to capture detailed information from spatial-temporal neighborhoods of plaques and detect initial contours of the plaques. Then the speckle reducing anisotropic diffusion is adopted to modify the edge map of the gradient vector flow snake, and the initial contours are deformed using the modified snake and converged to refined contours. The proposed method was evaluated via 21 in vivo images, and it outperformed the boundary vector field snake by 0.06 mm, 2.0%, 0.04 mm and 5.3%, in terms of the mean distance error, relative mean distance error, mean signed distance error, and relative difference degree, respectively. The results revealed that the proposed method can accurately detect plaques and delineate their contours.

Chaolun Li

Papers

Computer-aided quantification of contrast agent spatial distribution within atherosclerotic plaque in contrast-enhanced ultrasound image sequences

Quantification of carotid plaque elasticity and intraplaque neovascularization using contrast-enhanced ultrasound and image registration-based elastography

Ultrasound image segmentation based on multi-scale fuzzy c-means and particle swarm optimization

Contrast-enhanced ultrasound image segmentation of atherosclerotic plaques using spatial-temporal analysis and snakes