Chronic back pain (CBP) is a global health concern with significant societal and economic burden. While various predictors of back pain chronicity have been proposed, including demographic and psychosocial factors, neuroimaging studies have pointed to brain characteristics as predictors of CBP. However, large-scale, multisite validation of these predictors is currently lacking. In two independent longitudinal studies, we examined white matter diffusion imaging data and pain characteristics in patients with subacute back pain (SBP) over 6- and 12-month periods. Diffusion data from individuals with CBP and healthy controls (HC) were analyzed for comparison. Whole-brain tract-based spatial statistics analyses revealed that a cluster in the right superior longitudinal fasciculus (SLF) tract had larger fractional anisotropy (FA) values in patients who recovered (SBPr) compared to those with persistent pain (SBPp), and predicted changes in pain severity. The SLF FA values accurately classified patients at baseline and follow-up in a third publicly available dataset (Area under the Receiver Operating Curve ~0.70). Notably, patients who recovered had FA values larger than those of HC suggesting a potential role of SLF integrity in resilience to CBP. Structural connectivity-based models also classified SBPp and SBPr patients from the three data sets (validation accuracy 67%). Our results validate the right SLF as a robust predictor of CBP development, with potential for clinical translation. Cognitive and behavioral processes dependent on the right SLF, such as proprioception and visuospatial attention, should be analyzed in subacute stages as they could prove important for back pain chronicity.

Mindboggle (http://mindboggle.info) is an open source brain morphometry platform that takes in preprocessed T1-weighted MRI data and outputs volume, surface, and tabular data containing label, feature, and shape information for further analysis. In this article, we document the software and demonstrate its use in studies of shape variation in healthy and diseased humans. The number of different shape measures and the size of the populations make this the largest and most detailed shape analysis of human brains ever conducted. Brain image morphometry shows great potential for providing much-needed biological markers for diagnosing, tracking, and predicting progression of mental health disorders. Very few software algorithms provide more than measures of volume and cortical thickness, while more subtle shape measures may provide more sensitive and specific biomarkers. Mindboggle computes a variety of (primarily surface-based) shapes: area, volume, thickness, curvature, depth, Laplace-Beltrami spectra, Zernike moments, etc. We evaluate Mindboggle's algorithms using the largest set of manually labeled, publicly available brain images in the world and compare them against state-of-the-art algorithms where they exist. All data, code, and results of these evaluations are publicly available.

This paper proposes a novel temporal knowledge representation and learning framework to perform large-scale temporal signature mining of longitudinal heterogeneous event data. The framework enables the representation, extraction, and mining of high-order latent event structure and relationships within single and multiple event sequences. The proposed knowledge representation maps the heterogeneous event sequences to a geometric image by encoding events as a structured spatial-temporal shape process. We present a doubly constrained convolutional sparse coding framework that learns interpretable and shift-invariant latent temporal event signatures. We show how to cope with the sparsity in the data as well as in the latent factor model by inducing a double sparsity constraint on the β-divergence to learn an overcomplete sparse latent factor model. A novel stochastic optimization scheme performs large-scale incremental learning of group-specific temporal event signatures. We validate the framework on synthetic data and on an electronic health record dataset.

Purpose The purpose of this study is to optimise the settings of the Retinal Image Analysis Laboratory (RIALAB), a semi-automatic drusen quantification software, in planning for high-throughput quantification of drusen in clinical studies of age-related macular degeneration (AMD). Patients and methods A comparison of five different settings in RIALAB was made on 67 images from the Rotterdam eye study (population-based study) and 56 images from the fellow eye of patients with active neovascular AMD in King’s College Hospital, London (hospital-based study). Results The ‘Few Outer’ setting was the best setting, with it being most appropriate for 52 (77.6%) of the Rotterdam cohort and 47 (83.9%) for the London cohort. Pearson’s χ 2 -test revealed both results to be statistically significant ( P <0.0001). Conclusions RIALAB is a viable algorithm and software package that can detect, quantify, and analyse drusen efficiently in both population-based and hospital-based studies. We have shown that the ‘Few Outer’ drusen setting can be employed as the default setting, with fine-tuning only needed in a minority of cases, thus helping to speed up workflow.

Large collections of electronic clinical records today provide us with a vast source of information on medical practice. However, the utilization of those data for exploratory analysis to support clinical decisions is still limited. Extracting useful patterns from such data is particularly challenging because it is longitudinal, sparse and heterogeneous. In this paper, we propose a Nonnegative Matrix Factorization (NMF) based framework using a convolutional approach for open-ended temporal pattern discovery over large collections of clinical records. We call the method One-Sided Convolutional NMF (OSC-NMF). Our framework can mine common as well as individual shift-invariant temporal patterns from heterogeneous events over different patient groups, and handle sparsity as well as scalability problems well. Furthermore, we use an event matrix based representation that can encode quantitatively all key temporal concepts including order, concurrency and synchronicity. We derive efficient multiplicative update rules for OSC-NMF, and also prove theoretically its convergence. Finally, the experimental results on both synthetic and real world electronic patient data are presented to demonstrate the effectiveness of the proposed method.

We live in a world where data surround us in every aspect of our lives. The key challenge for humans and machines is how we can make better use of such data. Imagine what would happen if you were to have intelligent machines that could give you insight into the data. Insight that will enable you to better 1) reason about, 2) learn, and 3) understand the underlying phenomena that produced the data. The possibilities of combined human-machine intelligence are endless and will impact our lives in ways we can not even imagine today. Synergistic human-machine intelligence aims to facilitate the analytical reasoning and inference process of humans by creating machines that maximize a human's ability to 1) reason about, 2) learn, and 3) understand large, complex, and heterogeneous data. Combined human-machine intelligence is a powerful symbiosis of mutual benefit, in which we depend on the computational capabilities of the machine for the tasks we are not good at, and the machine requires human intervention for the tasks it performs poorly on. This relationship provides a compelling alternative to either approach in isolation for solving today's and tomorrow's arising data challenges. In his regard, this dissertation proposes a diverse analytical framework that leverages synergistic human-machine intelligence to maximize a human's ability to better 1) reason about, 2) learn, and 3) understand different biomedical imaging and healthcare data present in the patient's electronic health record (EHR). Correspondingly, we approach the data analyses problem from the 1) visualization, 2) labeling, and 3) mining perspective and demonstrate the efficacy of our analytics on specific application scenarios and various data domains. In the first part of this dissertation we explore the question how we can build intelligent imaging analytics that are commensurate with human capabilities and constraints, specifically for optimizing data visualization and automated labeling workflows. Our journey starts with heuristic rule-based analytical models that are derived from task-specific human knowledge. From this experience, we move on to data-driven analytics, where we adapt and combine the intelligence of the model based on prior information provided by the human and synthetic knowledge learned from partial data observations. Within this realm, we propose a novel Bayesian transductive Markov random field model that requires minimal human intervention and is able to cope with scarce label information to learn and infer object shapes in complex spatial, multimodal, spatio-temporal, and longitudinal data. We then study the question how machines can learn discriminative object representations from dense human provided label information by investigating learning and inference mechanisms that make use of deep learning architectures. The developed analytics can aid visualization and labeling tasks, which enables the interpretation and quantification of clinically relevant image information. The second part explores the question how we can build data-driven analytics for exploratory analysis in longitudinal event data that are commensurate with human capabilities and constraints. We propose human-intuitive analytics that enable the representation and discovery of interpretable event patterns to ease knowledge absorption and comprehension of the employed analytics model and the underlying data. We propose a novel doubly-constrained convolutional sparse-coding framework that learns interpretable and shift-invariant latent temporal event patterns. We apply the model to mine complex event data in EHRs. By mapping the event space to heterogeneous patient encounters in the EHR we explore the linkage between healthcare resource utilization (HRU) in relation to disease severity. This linkage may help to better understand how disease specific co-morbidities and their clinical attributes incur different HRU patterns. Such insight helps to characterize the patient's care history, which then enables the comparison against clinical practice guidelines, the discovery of prevailing practices based on common HRU group patterns, and the identification of outliers that might indicate poor patient management. In general, we present novel approaches that exploit the synergistic aspect of human-machine intelligence by addressing problems from biomedical imaging to healthcare informatics. The generic nature and applicability of the proposed techniques, when integrated together, enable the holistic analysis of the electronic health record and its diverse data sources, which in turn can reveal hidden patterns across the different data sources.

Sparse Coding (SC), which models the data vectors as sparse linear combinations over basis vectors (i.e., dictionary), has been widely applied in machine learning, signal processing and neuroscience. Recently, one specific SC technique, Group Sparse Coding (GSC), has been proposed to learn a common dictionary over multiple different groups of data, where the data groups are assumed to be pre-defined. In practice, this may not always be the case. In this paper, we propose Automatic Group Sparse Coding (AutoGSC), which can (1) discover the hidden data groups; (2) learn a common dictionary over different data groups; and (3) learn an individual dictionary for each data group. Finally, we conduct experiments on both synthetic and real world data sets to demonstrate the effectiveness of AutoGSC, and compare it with traditional sparse coding and Nonnegative Matrix Factorization (NMF) methods.

We investigated the feasibility of a novel method for hyperspectral mapping of macular pigment (MP) in vivo. Six healthy subjects were recruited for noninvasive imaging using a snapshot hyperspectral system. The three-dimensional full spatial-spectral data cube was analyzed using non-negative matrix factorization (NMF), wherein the data was decomposed to give spectral signatures and spatial distribution, in search for the MP absorbance spectrum. The NMF was initialized with the in vitro MP spectrum and rank 4 spectral signature decomposition was used to recover the MP spectrum and optical density in vivo. The recovered MP spectra showed two peaks in the blue spectrum, characteristic of MP, giving a detailed in vivo demonstration of these absorbance peaks. The peak MP optical densities ranged from 0.08 to 0.22 (mean 0.15+∕-0.05) and became spatially negligible at diameters 1100 to 1760 μm (4 to 6 deg) in the normal subjects. This objective method was able to exploit prior knowledge (the in vitro MP spectrum) in order to extract an accurate in vivo spectral analysis and full MP spatial profile, while separating the MP spectra from other ocular absorbers. Snapshot hyperspectral imaging in combination with advanced mathematical analysis provides a simple cost-effective approach for MP mapping in vivo.

Establishing correspondences across structural and functional brain images via labeling, or parcellation, is an important and challenging task for clinical neuroscience and cognitive psychology. A limitation with existing approaches is that they i) possess shallow architectures, ii) are based on heuristic manual feature engineering, and iii) assume the validity of the designed feature model. In contrast, we advocate a deep learning approach to automate brain parcellation. We present a novel application of convolutional networks to build discriminative features for brain parcellation, which are automatically learned from labels provided by human experts. Initial validation experiments show promising results for automatic brain parcellation, suggesting that the proposed approach has potential to be an alternative to template or atlas-based parcellation approaches.

Knowledge discovery in electronic health records (EHRs) is a central aspect for improved clinical decision making, prognosis, and patient management. While EHRs show great promise towards better data integration, automated access, and clinical workflow improvement, the vast information they capture over time pose challenges not only for medical practitioners, but also for the information analysis by machines. The objective of this paper is to promote and emphasize the importance of exploratory analytics that are commensurate with human capabilities and constraints. Within this realm we present a novel temporal event matrix representation and learning framework that discovers complex latent event patterns, which are easily interpretable by humans. We demonstrate our framework on synthetic data and on EHRs together with an extensive validation involving over 70,000 computed latent factor models. The present study is the first to link temporal patterns of healthcare resource utilization (HRU) against a diabetic disease complications severity index to better understand the relationships between disease severity and care delivery.

Aims To demonstrate and quantify the dynamic remodelling process of soft drusen resorption and new drusen formation in age-related macular degeneration (AMD) with novel interactive methods. Methods Twenty patients with large soft drusen bilaterally and without advanced AMD were imaged at baseline and again at a mean interval of 2 years (40 eyes, 80 images). Each of the 40 serial pairs of images was precisely registered by an automated technique. The drusen were segmented by a user-interactive method based on a background levelling algorithm and classified into three groups: new drusen (only in the final image), resorbed drusen (present initially but not in the final image) and stable drusen (present in both images). We measured each of these classes as well as the absolute change in drusen |D1 − D0| and the dynamic drusen activity (creation and resorption) Dnew+Dresorbed. Results Mean dynamic activity for the right eye (OD) was 7.33±5.50%, significantly greater than mean absolute change (2.71±2.89%, p=0.0002, t test), with similar results for the left eye (OS). However, dynamic activity OD compared with OS (mean 7.33±5.50 vs 7.91±4.16%, NS) and absolute net change OD versus OS (2.71±2.89 vs 3.46±3.97%, NS) tended to be symmetrical between fellow eyes. Conclusions Dynamic remodelling processes of drusen resorption and new drusen formation are distinct disease activities that can occur simultaneously and are not captured by change in total drusen load. Dynamic changes occur at rates more than twice that of net changes, and may be a useful marker of disease activity.

Drusen, the hallmark lesions of age related macular degeneration (AMD), are biochemically heterogeneous and the identification of their biochemical distribution is key to the understanding of AMD. Yet the challenges are to develop imaging technology and analytics, which respect the physical generation of the hyperspectral signal in the presence of noise, artifacts, and multiple mixed sources while maximally exploiting the full data dimensionality to uncover clinically relevant spectral signatures. This paper reports on the statistical analysis of hyperspectral signatures of drusen and anatomical regions of interest using snapshot hyperspectral imaging and non-negative matrix factorization (NMF). We propose physical meaningful priors as initialization schemes to NMF for finding low-rank decompositions that capture the underlying physiology of drusen and the macular pigment. Preliminary results show that snapshot hyperspectral imaging in combination with NMF is able to detect biochemically meaningful components of drusen and the macular pigment. To our knowledge, this is the first reported demonstration in vivo of the separate absorbance peaks for lutein and zeaxanthin in macular pigment.

Detection of vascular bifurcations is a challenging task in multimodal retinal image registration. Existing algorithms based on bifurcations usually fail in correctly aligning poor quality retinal image pairs. To solve this problem, we propose a novel highly distinctive local feature descriptor named partial intensity invariant feature descriptor (PIIFD) and describe a robust automatic retinal image registration framework named Harris-PIIFD. PIIFD is invariant to image rotation, partially invariant to image intensity, affine transformation, and viewpoint/perspective change. Our Harris-PIIFD framework consists of four steps. First, corner points are used as control point candidates instead of bifurcations since corner points are sufficient and uniformly distributed across the image domain. Second, PIIFDs are extracted for all corner points, and a bilateral matching technique is applied to identify corresponding PIIFDs matches between image pairs. Third, incorrect matches are removed and inaccurate matches are refined. Finally, an adaptive transformation is used to register the image pairs. PIIFD is so distinctive that it can be correctly identified even in nonvascular areas. When tested on 168 pairs of multimodal retinal images, the Harris-PIIFD far outperforms existing algorithms in terms of robustness, accuracy, and computational efficiency.

The development of low-dose spiral computed tomography (CT) has rekindled hope that effective lung cancer screening might yet be found. Screening is justified when there is evidence that it will extend lives at reasonable cost and acceptable levels of risk. A screening test should detect all extant cancers while avoiding unnecessary workups. Thus optimal screening modalities have both high sensitivity and specificity. Due to the present state of technology, radiologists must opt to increase sensitivity and rely on follow-up diagnostic procedures to rule out the incurred false positives. There is evidence in published reports that computer-aided diagnosis technology may help radiologists alter the benefit-cost calculus of CT sensitivity and specificity in lung cancer screening protocols. This review will provide insight into the current discussion of the effectiveness of lung cancer screening and assesses the potential of state-of-the-art computer-aided design developments.