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 apparatus for hierarchical parsing and semantic navigation of a full or partial body computed tomography CT scan is disclosed. In particular, organs are segmented and anatomic landmarks are detected in a full or partial body CT volume. One or more predetermined slices of the CT volume are detected. A plurality of anatomic landmarks and organ centers are then detected in the CT volume using a discriminative anatomical network, each detected in a portion of the CT volume constrained by at least one of the detected slices. A plurality of organs, such as heart, liver, kidneys, spleen, bladder, and prostate, are detected in a sense of a bounding box and segmented in the CT volume, detection of each organ bounding box constrained by the detected organ centers and anatomic landmarks. Organ segmentation is via a database-guided segmentation method.

Method and system for hierarchical parsing and semantic navigation of full body computed tomography data

The use of 3-D ultrasound data has several advantages over 2-D ultrasound for fetal biometric measurements, such as considerable decrease in the examination time, possibility of post-exam data processing by experts and the ability to produce 2-D views of the fetal anatomies in orientations that cannot be seen in common 2-D ultrasound exams. However, the search for standardized planes and the precise localization of fetal anatomies in ultrasound volumes are hard and time consuming processes even for expert physicians and sonographers. The relative low resolution in ultrasound volumes, small size of fetus anatomies and inter-volume position, orientation and size variability make this localization problem even more challenging. In order to make the plane search and fetal anatomy localization problems completely automatic, we introduce a novel principled probabilistic model that combines discriminative and generative classifiers with contextual information and sequential sampling. We implement a system based on this model, where the user queries consist of semantic keywords that represent anatomical structures of interest. After queried, the system automatically displays standardized planes and produces biometric measurements of the fetal anatomies. Experimental results on a held-out test set show that the automatic measurements are within the inter-user variability of expert users. It resolves for position, orientation and size of three different anatomies in less than 10 seconds in a dual-core computer running at 1.7 GHz.

/pdf/semantic-based-indexing-of-fetal-anatomies-from-3-d-1wgk9lahh7.pdf

Semantic-based indexing of fetal anatomies from 3-D ultrasound data using global/semi-local context and sequential sampling

There is a compelling demand for the integration and exploitation of heterogeneous biomedical information for improved clinical practice, medical research, and personalised healthcare across the EU. The Health-e-Child project aims at developing an integrated healthcare platform for European Paediatrics, providing seamless integration of traditional and emerging sources of biomedical information. The long-term goal of the project is to provide uninhibited access to universal biomedical knowledge repositories for personalised and preventive healthcare, large-scale information-based biomedical research and training, and informed policy making. The project focus will be on individualised disease prevention, screening, early diagnosis, therapy and follow-up of paediatric heart diseases, inflammatory diseases, and brain tumours. The project will build a Gridenabled European network of leading clinical centres that will share and annotate biomedical data, validate systems clinically, and diffuse clinical excellence across Europe by setting up new technologies, clinical workflows, and standards. This paper outlines the design approach being adopted in Health-e-Child to enable the delivery of an integrated biomedical information platform.

/pdf/health-e-child-an-integrated-biomedical-platform-for-grid-2x6okkqzzy.pdf

Health-e-Child: An Integrated Biomedical Platform for Grid-Based Pediatrics

Computerized characterization of cardiac wall motion is provided. Quantities for cardiac wall motion are determined (34) from a four-dimensional (i.e., 3D + time) sequence of ultrasound data. A processor (12) automatically processes the volume data to locate (28) the cardiac wall through the sequence and calculate (34) the quantity from the cardiac wall position or motion. Various machine learning is used for locating (28) and tracking (30) the cardiac wall, such as using a motion prior learned from training data for initially locating the cardiac wall and the motion prior, speckle tracking, boundary detection, and mass conservation cues for tracking with another machine learned classifier. Where the sequence extends over multiple cycles, the cycles are automatically divided (26) for independent tracking of the cardiac wall. The cardiac wall from one cycle may be used to propagate (32) to another cycle for initializing the tracking. Independent tracking (32) in each cycle may reduce or avoid inaccuracies due to drift.

Computerized characterization of cardiac motion in medical diagnostic ultrasound

Tracking of left ventricles in 3D echocardiography is a challenging topic because of the poor quality of ultrasound images and the speed consideration. In this paper, a fast and accurate learning based 3D tracking algorithm is presented. A novel one-step forward prediction is proposed to generate the motion prior using motion manifold learning. Collaborative trackers are introduced to achieve both temporal consistence anproc biomedical optical ima image segmentation cellular biophys fluores biology comd tracking robustness. The algorithm is completely automatic and computationally efficient. The mean point-to-mesh error of our algorithm is 1.28 mm. It requires less than 1.5 seconds to process a 3D volume (160 x 148 x 208 voxels).

/pdf/a-fast-and-accurate-tracking-algorithm-of-left-ventricles-in-27pgbivk15.pdf

Dorin Comaniciu

Papers

Method and system for hierarchical parsing and semantic navigation of full body computed tomography data

Semantic-based indexing of fetal anatomies from 3-D ultrasound data using global/semi-local context and sequential sampling

Health-e-Child: An Integrated Biomedical Platform for Grid-Based Pediatrics

Computerized characterization of cardiac motion in medical diagnostic ultrasound

A fast and accurate tracking algorithm of left ventricles in 3D echocardiography