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

Methods, systems, and apparatus for obtaining a sequence of x-ray images are disclosed. An object of interest in a first x-ray image is detected and an area of interest, based on a predicted motion of the object of interest, is determined. A second x-ray image of the area of interest is acquired using spatial x-ray modification to control an x-ray to pass through a portion of a patient corresponding to the area of interest.

Method and system for obtaining a sequence of x-ray images using a reduced dose of ionizing radiation

A system and method for visualization of cardiac changes under various pacing conditions for intervention planning and guidance is disclosed. A patient-specific anatomical heart model is generated based on medical image data of a patient. A patient-specific computational model of heart function is generated based on patient-specific anatomical heart model. A virtual intervention is performed at each of a plurality of positions on the patient-specific anatomical heart model using the patient-specific computational model of heart function to calculate one or more cardiac parameters resulting from the virtual intervention performed at each of the plurality of positions. One or more outcome maps are generated visualizing, at each of the plurality of positions on the patient-specific anatomical heart model, optimal values for the one or more cardiac parameters resulting from the virtual intervention performed at the that position on the patient-specific anatomical heart model.

System and method for visualization of cardiac changes under various pacing conditions

Chest radiography is the most common radiographic examination performed in daily clinical practice for the detection of various heart and lung abnormalities. The large amount of data to be read and reported, with more than 100 studies per day for a single radiologist, poses a challenge in consistently maintaining high interpretation accuracy. The introduction of large-scale public datasets has led to a series of novel systems for automated abnormality classification. However, the labels of these datasets were obtained using natural language processed medical reports, yielding a large degree of label noise that can impact the performance. In this study, we propose novel training strategies that handle label noise from such suboptimal data. Prior label probabilities were measured on a subset of training data re-read by 4 board-certified radiologists and were used during training to increase the robustness of the training model to the label noise. Furthermore, we exploit the high comorbidity of abnormalities observed in chest radiography and incorporate this information to further reduce the impact of label noise. Additionally, anatomical knowledge is incorporated by training the system to predict lung and heart segmentation, as well as spatial knowledge labels. To deal with multiple datasets and images derived from various scanners that apply different post-processing techniques, we introduce a novel image normalization strategy. Experiments were performed on an extensive collection of 297,541 chest radiographs from 86,876 patients, leading to a state-of-the-art performance level for 17 abnormalities from 2 datasets. With an average AUC score of 0.880 across all abnormalities, our proposed training strategies can be used to significantly improve performance scores.

Robust Classification from Noisy Labels: Integrating Additional Knowledge for Chest Radiography Abnormality Assessment

A method quantifies cardiac volume flow for an imaging sequence. The method includes receiving data representing three-dimensions and color Doppler flow data over a plurality of frames, constructing a ventricular model based on the data representing three-dimensions for the plurality of frames, the ventricular model including a sampling plane configured to measure the cardiac volume flow, computing volume flow samples based on the sampling plane and the color Doppler flow data, and correcting the volume flow samples for aliasing based on volumetric change in the ventricular model between successive frames of the plurality of frames.

Cardiac flow quantification with volumetric imaging data

A method and system for left ventricle (LV) detection in 2D magnetic resonance imaging (MRI) images is disclosed. In order to detect the LV in a 2D MRI image, a plurality of LV candidates are detected, for example using marginal space learning (MSL) based detection. Candidates for distinctive anatomic landmarks associated with the LV are then detected in the 2D MRI image. In particular, apex candidates and base candidates are detected in the 2D MRI image. One of the LV candidates is selected as a final LV detection result by ranking the LV candidates based on the LV candidates, the apex candidates, and the base candidates using a trained ranking model.

Dorin Comaniciu

Papers

Method and system for obtaining a sequence of x-ray images using a reduced dose of ionizing radiation

System and method for visualization of cardiac changes under various pacing conditions

Robust Classification from Noisy Labels: Integrating Additional Knowledge for Chest Radiography Abnormality Assessment

Cardiac flow quantification with volumetric imaging data

Method and system for left ventricle detection in 2D magnetic resonance images using ranking based multi-detector aggregation