Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

A general non-parametric technique is proposed for the analysis of a complex multimodal feature space and to delineate arbitrarily shaped clusters in it. The basic computational module of the technique is an old pattern recognition procedure: the mean shift. For discrete data, we prove the convergence of a recursive mean shift procedure to the nearest stationary point of the underlying density function and, thus, its utility in detecting the modes of the density. The relation of the mean shift procedure to the Nadaraya-Watson estimator from kernel regression and the robust M-estimators; of location is also established. Algorithms for two low-level vision tasks discontinuity-preserving smoothing and image segmentation - are described as applications. In these algorithms, the only user-set parameter is the resolution of the analysis, and either gray-level or color images are accepted as input. Extensive experimental results illustrate their excellent performance.

Mean shift: a robust approach toward feature space analysis

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

A survey on deep learning in medical image analysis

Computer vision applications have come to rely increasingly on superpixels in recent years, but it is not always clear what constitutes a good superpixel algorithm. In an effort to understand the benefits and drawbacks of existing methods, we empirically compare five state-of-the-art superpixel algorithms for their ability to adhere to image boundaries, speed, memory efficiency, and their impact on segmentation performance. We then introduce a new superpixel algorithm, simple linear iterative clustering (SLIC), which adapts a k-means clustering approach to efficiently generate superpixels. Despite its simplicity, SLIC adheres to boundaries as well as or better than previous methods. At the same time, it is faster and more memory efficient, improves segmentation performance, and is straightforward to extend to supervoxel generation.

/pdf/slic-superpixels-compared-to-state-of-the-art-superpixel-5d8sq04am9.pdf

SLIC Superpixels Compared to State-of-the-Art Superpixel Methods

A method and system for coronary artery detection in 3D cardiac volumes is disclosed. The heart chambers are segmented in the cardiac volume, and an initial estimation of a coronary artery is generated based on the segmented heart chambers. The initial estimation of the coronary artery is then refined based on local information in the cardiac volume in order to detect the coronary artery in the cardiac volume. The detected coronary artery can be extended using 3D dynamic programming.

Method and System for Automatic Coronary Artery Detection

A system and method for image segmentation using statistical clustering with saddle point detection includes representation means for representing the image data in a joint space of dimension d=r+2 that includes two special coordinates, where r=1 for gray-scale images, r=3 for color images, and r>3 for multi-spectral images; partitioning means for partitioning the data set comprising a plurality of image data points into a plurality of statistically meaningful clusters by decomposing the data set by a mean shift based data decomposition; and characterization means for characterizing the statistical significance of at least one of a plurality of clusters of data points by selecting a cluster and computing the value of a statistical measure for the saddle point lying on the border of the selected cluster and having the highest density.

Image segmentation using statistical clustering with saddle point detection

A method and system for measuring the volume of the left ventricle (LV) in a 3D medical image, such as a CT, volume is disclosed. Heart chambers are segmented in the CT volume, including at least the LV endocardium and the LV epicardium. An optimal threshold value is automatically determined based on voxel intensities within the LV endocardium and voxel intensities between the LV endocardium and the LV epicardium. Voxels within the LV endocardium are labeled as blood pool voxels or papillary muscle voxels based on the optimal threshold value. The LV volume can be measured excluding the papillary muscles based on the number of blood pool voxels, and the LV volume can be measured including the papillary muscles based on the total number of voxels within the LV endocardium.

Method and system for measuring left ventricle volume

Current treatments of heart rhythm troubles require careful planning and guidance for optimal outcomes. Computational models of cardiac electrophysiology are being proposed for therapy planning but current approaches are either too simplified or too computationally intensive for patient-specific simulations in clinical practice. This paper presents a novel approach, LBM-EP, to solve any type of mono-domain cardiac electrophysiology models at near real-time that is especially tailored for patient-specific simulations. The domain is discretized on a Cartesian grid with a level-set representation of patient's heart geometry, previously estimated from images automatically. The cell model is calculated node-wise, while the transmembrane potential is diffused using Lattice-Boltzmann method within the domain defined by the level-set. Experiments on synthetic cases, on a data set from CESC'10 and on one patient with myocardium scar showed that LBM-EP provides results comparable to an FEM implementation, while being 10−45 times faster. Fast, accurate, scalable and requiring no specific meshing, LBM-EP paves the way to efficient and detailed models of cardiac electrophysiology for therapy planning.

/pdf/lbm-ep-lattice-boltzmann-method-for-fast-cardiac-3a6p6w8rvs.pdf

LBM-EP: lattice-boltzmann method for fast cardiac electrophysiology simulation from 3d images

A system and method for defining and tracking a deformable shape of a candidate anatomical structure wall in a three dimensional (3D) image is disclosed. The shape of the candidate anatomical structure is represented by a plurality of labeled 3D landmark points. At least one 3D landmark point of the deformable shape in an image frame is defined. A 3D cuboid is defined around the detected 3D landmark point. For each landmark point associated with the anatomical structure, its location and location uncertainty matrix is estimated in subsequent frames relative to the reference anatomical structures. A shape model is generated to represent dynamics of the deformable shape in subsequent image frames. The shape model includes statistical information from a training data set of 3D images of representative anatomical structures. The shape model is aligned to the deformable shape of the candidate anatomical structure. The shape model is fused with the deformable shape. A current shape of the candidate anatomical structure is estimated.

Dorin Comaniciu

Papers

Method and System for Automatic Coronary Artery Detection

Image segmentation using statistical clustering with saddle point detection

Method and system for measuring left ventricle volume

LBM-EP: lattice-boltzmann method for fast cardiac electrophysiology simulation from 3d images

System and method for tracking anatomical structures in three dimensional images