Non-imaging Data Research Articles

Hierarchical Segmentations with Graphs: Quasi-flat Zones, Minimum Spanning Trees, and Saliency Maps

Hierarchies of partitions are generally represented by dendrograms (direct representation). They can also be represented by saliency maps or minimum spanning trees. In this article, we precisely study the links between these three representations. In particular, we provide a new bijection between saliency maps and hierarchies based on quasi-flat zones as often used in image processing and we characterize saliency maps and minimum spanning trees as solutions to constrained minimization problems where the constraint is quasi-flat zones preservation. In practice, these results make up a toolkit for designing new hierarchical methods where one can choose the most convenient representation. They also invite us to process non-image data with morphological hierarchies. More precisely, we show the practical interest of the proposed framework for: i) hierarchical watershed image segmentations, ii) combinations of dierent hierarchical segmentations, iii) hierarchicalizations of some non-hierarchical image segmentation methods based on regional dissimilarities, and iv) hierarchical analysis of geographical data.

Fusion of fMRI and non-imaging data for ADHD classification

Resting state fMRI has emerged as a popular neuroimaging method for automated recognition and classification of different brain disorders. Attention Deficit Hyperactivity Disorder (ADHD) is one of the most common brain disorders affecting young children, yet its underlying mechanism is not completely understood and its diagnosis is mainly dependent on behavior analysis. This paper addresses the problem of classification of ADHD based on resting state fMRI and proposes a machine learning framework with integration of non-imaging data with imaging data to investigate functional connectivity alterations between ADHD and control subjects (not diagnosed with ADHD). Our aim is to apply computational techniques to (1) automatically classify a subject as ADHD or control, (2) identify differences in functional connectivity of these two groups and (3) evaluate the importance of fusing non-imaging with imaging data for classification. In the first stage of our framework, we determine the functional connectivity of brain regions by grouping brain activity using clustering algorithms. Next, we employ Elastic Net based feature selection to select the most discriminant features from the dense functional brain network and integrate non-imaging data. Finally, a Support Vector Machine classifier is trained to classify ADHD subjects vs. control. The proposed framework was evaluated on a public ADHD-200 dataset, and our results suggest that fusion of non-imaging data improves the performance of the framework. Classification results outperform the state-of-the-art on some subsets of the data.

SP-0597: Tissue classification models for prostate based on imaging and non-imaging data

SP-0597: Tissue classification models for prostate based on imaging and non-imaging data

SP-0596: Machine learning and bioinformatics approaches to combine imaging with non-imaging data for outcome prediction

SP-0596: Machine learning and bioinformatics approaches to combine imaging with non-imaging data for outcome prediction

A concept for holistic whole body MRI data analysis, Imiomics.

PurposeTo present and evaluate a whole-body image analysis concept, Imiomics (imaging–omics) and an image registration method that enables Imiomics analyses by deforming all image data to a common coordinate system, so that the information in each voxel can be compared between persons or within a person over time and integrated with non-imaging data.MethodsThe presented image registration method utilizes relative elasticity constraints of different tissue obtained from whole-body water-fat MRI.The registration method is evaluated by inverse consistency and Dice coefficients and the Imiomics concept is evaluated by example analyses of importance for metabolic research using non-imaging parameters where we know what to expect.The example analyses include whole body imaging atlas creation, anomaly detection, and cross-sectional and longitudinal analysis.ResultsThe image registration method evaluation on 128 subjects shows low inverse consistency errors and high Dice coefficients. Also, the statistical atlas with fat content intensity values shows low standard deviation values, indicating successful deformations to the common coordinate system.The example analyses show expected associations and correlations which agree with explicit measurements, and thereby illustrate the usefulness of the proposed Imiomics concept.ConclusionsThe registration method is well-suited for Imiomics analyses, which enable analyses of relationships to non-imaging data, e.g. clinical data, in new types of holistic targeted and untargeted big-data analysis.

Devising an interpretable calibrated scale to quantitatively assess the dementia stage of subjects with alzheimer's disease: A machine learning approach

Abstract Background: Machine learning and data mining techniques have been successfully applied on MRI images for detecting Alzheimer's disease (AD). But only a few studies have explored the possibility of AD detection from non-image data. These studies have applied traditional data visualization and classification algorithms. There is a need for new sophisticated learning algorithms, for detecting and quantifying the severity of AD by exploring the complex interactions between the features in AD subjects. Method: In this work, a supervised learning model to effectively capture the complex feature interactions, in the sample space of AD data, is presented for knowledge discovery. The discovered knowledge is further used to quantify the similarity of a test subject to the demented class. Results: Evaluation of the proposed model, on OASIS database of Alzheimer's subjects, validates the well established risk factors and identifiers for AD: Age, Socio-Economic Status, MMSE Score and Whole Brain Volume. The Test subjects are affiliated to either non-demented (ND) or AD class, with non-overlapping and measurable similarity indices: Female ND (CDR=0) [0.48–2.90], Female AD (CDR=0.5) [90.16–774.51], Female AD (CDR=1) [1633.90–7182.23], Female AD (CDR=2) [55258.51–66382.44], Male ND (CDR=0)[0.69–3.66], Male AD (CDR=0.5) [99.18–647.51] and Male AD (CDR=1) [3880.16–6519.40]. Conclusion: The outcome of the work clearly demonstrates that, supervised learning model can be used effectively to quantify the severity of AD on a standard measurable scale. This scale of distance can be used as a supplement for clinical dementia rating.

Advances in Classification of Crops using Remote Sensing Data

Remote sensing is an efficient technology and worthy source of earth surface information, as it can capture images of reasonably large area on the earth. Due to advancement in the sensor technologies there is availability of high spatial as well as spectral resolutions imageries, and also non imaging Spectroradiometer. With the use of these imaging and non-imaging data we can easily characterize the different species. In this article we have reported work done by worldwide researchers for spatial as well as spectral feature extraction from remote sensing data; specifically we have focused on classification of crops and use narrow band vegetation indices. It may be observed from the report that both spatial resolution and hyperspectral imageries need to be used for better classification.

Label-aligned multi-task feature learning for multimodal classification of Alzheimer's disease and mild cognitive impairment.

Multimodal classification methods using different modalities of imaging and non-imaging data have recently shown great advantages over traditional single-modality-based ones for diagnosis and prognosis of Alzheimer's disease (AD), as well as its prodromal stage, i.e., mild cognitive impairment (MCI). However, to the best of our knowledge, most existing methods focus on mining the relationship across multiple modalities of the same subjects, while ignoring the potentially useful relationship across different subjects. Accordingly, in this paper, we propose a novel learning method for multimodal classification of AD/MCI, by fully exploring the relationships across both modalities and subjects. Specifically, our proposed method includes two subsequent components, i.e., label-aligned multi-task feature selection and multimodal classification. In the first step, the feature selection learning from multiple modalities are treated as different learning tasks and a group sparsity regularizer is imposed to jointly select a subset of relevant features. Furthermore, to utilize the discriminative information among labeled subjects, a new label-aligned regularization term is added into the objective function of standard multi-task feature selection, where label-alignment means that all multi-modality subjects with the same class labels should be closer in the new feature-reduced space. In the second step, a multi-kernel support vector machine (SVM) is adopted to fuse the selected features from multi-modality data for final classification. To validate our method, we perform experiments on the Alzheimer's Disease Neuroimaging Initiative (ADNI) database using baseline MRI and FDG-PET imaging data. The experimental results demonstrate that our proposed method achieves better classification performance compared with several state-of-the-art methods for multimodal classification of AD/MCI.

A positive-negative mode of population covariation links brain connectivity, demographics and behavior.

We investigated the relationship between individual subjects’ functional connectomes and 280 behavioral and demographic measures, in a single holistic multivariate analysis relating imaging to non-imaging data from 461 subjects in the Human Connectome Project. We identified one strong mode of population co-variation; subjects were predominantly spread along a single “positive-negative” axis, linking lifestyle, demographic and psychometric measures to each other and to a specific pattern of brain connectivity.

Noninvasive Multimodal Imaging to Predict Recovery of Locomotion after Extended Limb Ischemia

Acute limb ischemia is a common cause of morbidity and mortality following trauma both in civilian centers and in combat related injuries. Rapid determination of tissue viability and surgical restoration of blood flow are desirable, but not always possible. We sought to characterize the response to increasing periods of hind limb ischemia in a porcine model such that we could define a period of critical ischemia (the point after which irreversible neuromuscular injury occurs), evaluate non-invasive methods for characterizing that ischemia, and establish a model by which we could predict whether or not the animal’s locomotion would return to baselines levels post-operatively. Ischemia was induced by either application of a pneumatic tourniquet or vessel occlusion (performed by clamping the proximal iliac artery and vein at the level of the inguinal ligament). The limb was monitored for the duration of the procedure with both 3-charge coupled device (3CCD) and infrared (IR) imaging for tissue oxygenation and perfusion, respectively. The experimental arms of this model are effective at inducing histologically evident muscle injury with some evidence of expected secondary organ damage, particularly in animals with longer ischemia times. Noninvasive imaging data shows excellent correlation with post-operative functional outcomes, validating its use as a non-invasive means of viability assessment, and directly monitors post-occlusive reactive hyperemia. A classification model, based on partial-least squares discriminant analysis (PLSDA) of imaging variables only, successfully classified animals as “returned to normal locomotion” or “did not return to normal locomotion” with 87.5% sensitivity and 66.7% specificity after cross-validation. PLSDA models generated from non-imaging data were not as accurate (AUC of 0.53) compared the PLSDA model generated from only imaging data (AUC of 0.76). With some modification, this limb ischemia model could also serve as a means on which to test therapies designed to prolong the time before critical ischemia.

Efficient field-programmable gate array implementation of CCSDS 121.0-B-2 lossless data compression algorithm for image compression

The Consultative Committee for Space Data Systems (CCSDS) 121.0-B-2 lossless data compression standard defines a lossless adaptive source coding algorithm which is applicable to a wide range of imaging and nonimaging data. We introduce a field-programmable gate array (FPGA) implementation of CCSDS 121.0-B-2 as an intellectual property (IP) core with the following features: (a) it is enhanced with a two-dimensional (2-D) second-order predictor making it more suitable for image compression, (b) it is enhanced with near-lossless compression functionality, (c) its parallel, pipelined architecture provides high data-rate performance with a maximum achievable throughput of 205 Msamples/s (3.2 Gbps at 16 bit) when targeting the Xilinx Virtex-5QV FPGA, and (d) it requires very low FPGA resources. When mission requirements impose lossless image compression, the CCSDS 121.0-B-2 IP core provides a very low implementation cost solution. According to European Space Agency PROBA-3 Bridging Phase, the CCSDS 121.0-B-2 IP core will be implemented in a Microsemi RTAX2000 FPGA, hosted in the data processing unit of the Coronagraph Control Box, of the Association of Spacecraft for Polarimetric and Imaging Investigation of the Corona of the Sun Coronagraph System Payload. To the best of our knowledge, it is the fastest FPGA implementation of CCSDS 121.0-B-2 to date, also including a 2-D second-order predictor making it more suitable for image compression.

Interactive Visual Analysis of Image-Centric Cohort Study Data.

Epidemiological population studies impose information about a set of subjects (a cohort) to characterize disease-specific risk factors. Cohort studies comprise heterogenous variables describing the medical condition as well as demographic and lifestyle factors and, more recently, medical image data. We propose an Interactive Visual Analysis (IVA) approach that enables epidemiologists to rapidly investigate the entire data pool for hypothesis validation and generation. We incorporate image data, which involves shape-based object detection and the derivation of attributes describing the object shape. The concurrent investigation of image-based and non-image data is realized in a web-based multiple coordinated view system, comprising standard views from information visualization and epidemiological data representations such as pivot tables. The views are equipped with brushing facilities and augmented by 3D shape renderings of the segmented objects, e.g., each bar in a histogram is overlaid with a mean shape of the associated subgroup of the cohort. We integrate an overview visualization, clustering of variables and object shape for data-driven subgroup definition and statistical key figures for measuring the association between variables. We demonstrate the IVA approach by validating and generating hypotheses related to lower back pain as part of a qualitative evaluation.

A kernel-based sparsity preserving method for semi-supervised classification

In this paper, we propose an effective approach to semi-supervised classification through kernel-based sparse representation. The new method computes the sparse representation of data in the feature space, and then the learner is subject to a cost function which aims to preserve the sparse representing coefficients. By mapping the data into the feature space, the so-called “l2-norm problem” that may be encountered when directly applying sparse representations to non-image data classification tasks will be naturally alleviated, and meanwhile, the label of a data point can be reconstructed more precisely by the labels of other data points using the sparse representing coefficients. Inherited from sparse representation, our method can adaptively establish the relationship between data points, and has high discriminative ability. Furthermore, the new method has a natural multi-class explicit expression for new samples. Experimental results on several benchmark data sets are provided to show the effectiveness of our method.

Content-based medical image retrieval: a survey of applications to multidimensional and multimodality data.

Medical imaging is fundamental to modern healthcare, and its widespread use has resulted in the creation of image databases, as well as picture archiving and communication systems. These repositories now contain images from a diverse range of modalities, multidimensional (three-dimensional or time-varying) images, as well as co-aligned multimodality images. These image collections offer the opportunity for evidence-based diagnosis, teaching, and research; for these applications, there is a requirement for appropriate methods to search the collections for images that have characteristics similar to the case(s) of interest. Content-based image retrieval (CBIR) is an image search technique that complements the conventional text-based retrieval of images by using visual features, such as color, texture, and shape, as search criteria. Medical CBIR is an established field of study that is beginning to realize promise when applied to multidimensional and multimodality medical data. In this paper, we present a review of state-of-the-art medical CBIR approaches in five main categories: two-dimensional image retrieval, retrieval of images with three or more dimensions, the use of nonimage data to enhance the retrieval, multimodality image retrieval, and retrieval from diverse datasets. We use these categories as a framework for discussing the state of the art, focusing on the characteristics and modalities of the information used during medical image retrieval.

Designing user interfaces to enhance human interpretation of medical content-based image retrieval: application to PET-CT images

Content-based image retrieval (CBIR) in medicine has been demonstrated to improve evidence-based diagnosis, education, and teaching. However, the low clinical adoption of CBIR is partially because the focus of most studies has been the development of feature extraction and similarity measurement algorithms with limited work on facilitating better understanding of the similarity between complex volumetric and multi-modality medical images. In this paper, we present a method for defining user interfaces (UIs) that enable effective human user interpretation of retrieved images. We derived a set of visualisation and interaction requirements based on the characteristics of modern volumetric medical images. We implemented a UI that visualised multiple views of a single image, displayed abstractions of image data, and provided access to supplementary non-image data. We also defined interactions for refining the search and visually indicating the similarities between images. We applied the UI for the retrieval of multi-modality positron emission tomography and computed tomography (PET-CT) images. We conducted a user survey to evaluate the capabilities of our UI. Our proposed method obtained a high rating ( ≥ 4 out of 5) in the majority of survey questions. In particular, the survey responses indicated the UI presented all the information necessary to understand the retrieved images, and did so in an intuitive manner. Our proposed UI design improved the ability of users to interpret and understand the similarity between retrieved PET-CT images. The implementation of CBIR UIs designed to assist human interpretation could facilitate wider adoption of medical CBIR systems.

Development of spectral indices for detecting and identifying plant diseases

Spectral vegetation indices (SVIs) have been shown to be useful for an indirect detection of plant diseases. However, these indices have not been evaluated to detect or to differentiate between plant diseases on crop plants. The aim of this study was to develop specific spectral disease indices (SDIs) for the detection of diseases in crops. Sugar beet plants and the three leaf diseases Cercospora leaf spot, sugar beet rust and powdery mildew were used as model system. Hyperspectral signatures of healthy and diseased sugar beet leaves were assessed with a non-imaging spectroradiometer at different developing stages and disease severities of pathogens. Significant and most relevant wavelengths and two band normalized differences from 450 to 950nm, describing the impact of a disease on sugar beet leaves were extracted from the data-set using the RELIEF-F algorithm. To develop hyperspectral indices for the detection of sugar beet diseases the best weighted combination of a single wavelength and a normalized wavelength difference was exhaustively searched testing all possible combinations. The optimized disease indices were tested for their ability to detect and to classify healthy and diseased sugar beet leaves. With a high accuracy and sensitivity healthy sugar beet leaves and leaves, infected with Cercospora leaf spot, sugar beet rust and powdery mildew were classified (balanced classification accuracy: 89%, 92%, 87%, 85%, respectively). Spectral disease indices were also successfully applied on hyperspectral imaging data and on non-imaging data from a sugar beet field. Specific disease indices will improve disease detection, identification and monitoring in precision agriculture applications.

Consensus embedding: theory, algorithms and application to segmentation and classification of biomedical data

BackgroundDimensionality reduction (DR) enables the construction of a lower dimensional space (embedding) from a higher dimensional feature space while preserving object-class discriminability. However several popular DR approaches suffer from sensitivity to choice of parameters and/or presence of noise in the data. In this paper, we present a novel DR technique known as consensus embedding that aims to overcome these problems by generating and combining multiple low-dimensional embeddings, hence exploiting the variance among them in a manner similar to ensemble classifier schemes such as Bagging. We demonstrate theoretical properties of consensus embedding which show that it will result in a single stable embedding solution that preserves information more accurately as compared to any individual embedding (generated via DR schemes such as Principal Component Analysis, Graph Embedding, or Locally Linear Embedding). Intelligent sub-sampling (via mean-shift) and code parallelization are utilized to provide for an efficient implementation of the scheme.ResultsApplications of consensus embedding are shown in the context of classification and clustering as applied to: (1) image partitioning of white matter and gray matter on 10 different synthetic brain MRI images corrupted with 18 different combinations of noise and bias field inhomogeneity, (2) classification of 4 high-dimensional gene-expression datasets, (3) cancer detection (at a pixel-level) on 16 image slices obtained from 2 different high-resolution prostate MRI datasets. In over 200 different experiments concerning classification and segmentation of biomedical data, consensus embedding was found to consistently outperform both linear and non-linear DR methods within all applications considered.ConclusionsWe have presented a novel framework termed consensus embedding which leverages ensemble classification theory within dimensionality reduction, allowing for application to a wide range of high-dimensional biomedical data classification and segmentation problems. Our generalizable framework allows for improved representation and classification in the context of both imaging and non-imaging data. The algorithm offers a promising solution to problems that currently plague DR methods, and may allow for extension to other areas of biomedical data analysis.

Supervised regularized canonical correlation analysis: integrating histologic and proteomic measurements for predicting biochemical recurrence following prostate surgery.

BackgroundMultimodal data, especially imaging and non-imaging data, is being routinely acquired in the context of disease diagnostics; however, computational challenges have limited the ability to quantitatively integrate imaging and non-imaging data channels with different dimensionalities and scales. To the best of our knowledge relatively few attempts have been made to quantitatively fuse such data to construct classifiers and none have attempted to quantitatively combine histology (imaging) and proteomic (non-imaging) measurements for making diagnostic and prognostic predictions. The objective of this work is to create a common subspace to simultaneously accommodate both the imaging and non-imaging data (and hence data corresponding to different scales and dimensionalities), called a metaspace. This metaspace can be used to build a meta-classifier that produces better classification results than a classifier that is based on a single modality alone. Canonical Correlation Analysis (CCA) and Regularized CCA (RCCA) are statistical techniques that extract correlations between two modes of data to construct a homogeneous, uniform representation of heterogeneous data channels. In this paper, we present a novel modification to CCA and RCCA, Supervised Regularized Canonical Correlation Analysis (SRCCA), that (1) enables the quantitative integration of data from multiple modalities using a feature selection scheme, (2) is regularized, and (3) is computationally cheap. We leverage this SRCCA framework towards the fusion of proteomic and histologic image signatures for identifying prostate cancer patients at the risk of 5 year biochemical recurrence following radical prostatectomy.ResultsA cohort of 19 grade, stage matched prostate cancer patients, all of whom had radical prostatectomy, including 10 of whom had biochemical recurrence within 5 years of surgery and 9 of whom did not, were considered in this study. The aim was to construct a lower fused dimensional metaspace comprising both the histological and proteomic measurements obtained from the site of the dominant nodule on the surgical specimen. In conjunction with SRCCA, a random forest classifier was able to identify prostate cancer patients, who developed biochemical recurrence within 5 years, with a maximum classification accuracy of 93%.ConclusionsThe classifier performance in the SRCCA space was found to be statistically significantly higher compared to the fused data representations obtained, not only from CCA and RCCA, but also two other statistical techniques called Principal Component Analysis and Partial Least Squares Regression. These results suggest that SRCCA is a computationally efficient and a highly accurate scheme for representing multimodal (histologic and proteomic) data in a metaspace and that it could be used to construct fused biomarkers for predicting disease recurrence and prognosis.

Finding the Meaning in Images: Annotation and Image Markup

Finding the Meaning in Images:Annotation and Image Markup Daniel L. Rubin (bio) Keywords ontologies, semantic annotation, imaging, knowledge representation Biomedical images and ontologies are closely related conceptually, yet currently they are studied in isolation. Biomedical ontologies provide a representation of the canonical entities considered in biomedical research and clinical observations, and the relations among them. Images reveal instances of those entities and, taken in aggregate, inform the construction of ontologies describing the pertinent domain content revealed in the images. The article by Fielding and Marwede (2011) notes the differences between the ontology of the body and the ontology of the image, developing toward an application of ontology of the psychiatric domain. Although such ontology development is important for knowledge representation, it is also important to relate and integrate such ontologies with the actual images to which they relate. In this commentary, we describe ongoing work to accomplish this linkage. Connecting biomedical ontologies to images is an important activity. Biomedical images provide rich information, but the contents of images, such as the modality used to acquire them, the anatomy they contain, and visual observations made about images, are not explicit or computable. Image data are accumulating in a variety of online databases at an explosive pace, similar to nonimage data. But whereas nonimage data, such as genetic data, are easily processed by machines, image data are generally not exploited directly—images typically are stored in archives, and only particular data needed for the study in which the images were originally acquired are generally available for subsequent analysis. Consequently, informatics methods are in development to enable the community to leverage the vast amounts of images accumulating as products of biomedical research. The Challenges of Using Images in e-Science There is growing interest in applying semantic web technologies to biomedicine, because these methods can make biomedical data explicit and computable. An "e-Science" paradigm is emerging, and the biomedical community is looking for tools to help them access, query, and analyze the myriad of data available online. Specifically, they are beginning to embrace technologies for semantic scientific knowledge integration, such as ontologies (Bodenreider and Stevens 2006), standard syntaxes and semantics to make biomedical [End Page 311] knowledge explicit, and the Semantic Web (Ruttenberg et al. 2007). These technologies are enabling the community to access large amounts of data, and to interoperate among diverse data archives. Such technologies are showing promise in tackling the information challenges in biomedicine, and a variety of applications are quickly appearing (Ruttenberg et al. 2007). Although researchers can now access a broad diversity of biomedical data, a critical type of data—images—remains difficult to leverage. Those wanting to access and use imaging in their work face similar difficulties as the rest of the e-Science community, namely to manage, find, and use the voluminous amounts of imaging data accruing at an explosive pace. However, imaging poses unique challenges hindering direct translation of the informatics methods that are currently being applied to nonimaging biomedical data. Image Content Is Not Explicit and Machine Accessible Images contain rich information about anatomy and abnormal structures contained in the images; however, this is implicit knowledge that is deduced by the person viewing the image. For example, a researcher viewing an image may want to indicate where in the image particular areas of interest lie, and whether they are abnormal (Figure 1). This information, the semantic image content, is often considered "image metadata," including observations about images, interpretations, and conclusions, and it is generally not recorded in a structured manner nor directly linked to the image. Thus, images cannot be easily searched for their semantic content (e.g., find all images containing particular anatomy or representing particular abnormalities). No Controlled Image Terminology or Standard Syntax for Image Information There are no standard terminologies specifically for describing medical image contents—the imaging observations, the anatomy, and the pathology—and the syntax in which the information is recorded varies, with no widely adopted standards, resulting in limited interoperability. Descriptions of medical images are most frequently recorded in free text in an unstructured manner, limiting the ability of computers to analyze and access this information. Schemes for annotating images have been proposed in nonmedical domains...

Optimizing Analysis, Visualization, and Navigation of Large Image Data Sets: One 5000-Section CT Scan Can Ruin Your Whole Day

The technology revolution in image acquisition, instrumentation, and methods has resulted in vast data sets that far outstrip the human observers' ability to view, digest, and interpret modern medical images by using traditional methods. This may require a paradigm shift in the radiologic interpretation process. As human observers, radiologists must search for, detect, and interpret targets. Potential interventions should be based on an understanding of human perceptual and attentional abilities and limitations. New technologies and tools already in use in other fields can be adapted to the health care environment to improve medical image analysis, visualization, and navigation through large data sets. This historical psychophysical and technical review touches on a broad range of disciplines but focuses mainly on the analysis, visualization, and navigation of image data performed during the interpretive process. Advanced postprocessing, including three-dimensional image display, multimodality image fusion, quantitative measures, and incorporation of innovative human-machine interfaces, will likely be the future. Successful new paradigms will integrate image and nonimage data, incorporate workflow considerations, and be informed by evidence-based practices. This overview is meant to heighten the awareness of the complexities and limitations of how radiologists interact with images, particularly the large image sets generated today. Also addressed is how human-machine interface and informatics technologies could combine to transform the interpretation process in the future to achieve safer and better quality care for patients and a more efficient and effective work environment for radiologists. http://radiology.rsna.org/lookup/suppl/doi:10.1148/radiol.11091276/-/DC1.