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

The state-of-the-art object detection algorithm learns a binary classifier to differentiate the foreground object from the background. Since the detection algorithm exhaustively scans the input image for object instances by testing the classifier, its computational complexity linearly depends on the image size and, if say orientation and scale are scanned, the number of configurations in orientation and scale. We argue that exhaustive scanning is unnecessary when detecting medical anatomy because a medical image offers strong contextual information. We then present an approach to effectively leveraging the medical context, leading to a solution that needs only one scan in theory or several sparse scans in practice and only one integral image even when the rotation is considered. The core is to learn a regression function, based on an annotated database, that maps the appearance observed in a scan window to a displacement vector, which measures the difference between the configuration being scanned and that of the target object. To achieve the learning task, we propose an image-based boosting ridge regression algorithm, which exhibits good generalization capability and training efficiency. Coupled with a binary classifier as a confidence scorer, the regression approach becomes an effective tool for detecting left ventricle in echocardiogram, achieving improved accuracy over the state-of-the-art object detection algorithm with significantly less computation.

/pdf/a-boosting-regression-approach-to-medical-anatomy-detection-4nwf9ykmmu.pdf

A boosting regression approach to medical anatomy detection

A method and system for physiological image registration and fusion is disclosed. A physiological model of a target anatomical structure in estimated each of a first image and a second image. The physiological model is estimated using database-guided discriminative machine learning-based estimation. A fused image is then generated by registering the first and second images based on correspondences between the physiological model estimated in each of the first and second images.

Method and System for Physiological Image Registration and Fusion

A method and system for approximating a deep neural network for anatomical object detection is discloses. A deep neural network is trained to detect an anatomical object in medical images. An approximation of the trained deep neural network is calculated that reduces the computational complexity of the trained deep neural network. The anatomical object is detected in an input medical image of a patient using the approximation of the trained deep neural network.

Method and system for approximating deep neural networks for anatomical object detection

A method and apparatus for vascular disease detection and characterization using a recurrent neural network (RNN) is disclosed. A plurality of 2D cross-section image patches are extracted from a 3D computed tomography angiography (CTA) image, each extracted at a respective sampling point along a vessel centerline of a vessel of interest in the 3D CTA image. Vascular abnormalities in the vessel of interest are detected and characterized by classifying each of the sampling points along the vessel centerline based on the plurality of 2D cross-section image patches using a trained RNN.

Method and system for vascular disease detection using recurrent neural networks

A system and method for automatic scale selection in real-time image and video processing and computer vision applications. In one aspect, a non-parametric variable bandwidth mean shift technique, which is based on adaptive estimation of a normalized density gradient, is used for detecting one or more modes in the underlying data and clustering the underlying data. In another aspect, a data-driven bandwidth (or scale) selection technique is provided for the variable bandwidth mean shift method, which estimates for each data point the covariance matrix that is the most stable across a plurality of scales. The methods can be used for detecting modes and clustering data for various types of data such as image data, video data speech data, handwriting data, etc.

Dorin Comaniciu

Papers

A boosting regression approach to medical anatomy detection

Method and System for Physiological Image Registration and Fusion

Method and system for approximating deep neural networks for anatomical object detection

Method and system for vascular disease detection using recurrent neural networks

Systems and methods for automatic scale selection in real-time imaging