Visualisation and browsing of image databases

In this chapter we provide a comprehensive overview of the emerging field of visualising and browsing image databases. We start with a brief introduction to content-based image retrieval and the traditional query-by-example search paradigm that many retrieval systems employ. We specify the problems associated with this type of interface, such as users not being able to formulate a query due to not having a target image or concept in mind. The idea of browsing systems is then introduced as a means to combat these issues, harnessing the cognitive power of the human mind in order to speed up image retrieval.We detail common methods in which the often high-dimensional feature data extracted from images can be used to visualise image databases in an intuitive way. Systems using dimensionality reduction techniques, such as multi-dimensional scaling, are reviewed along with those that cluster images using either divisive or agglomerative techniques as well as graph-based visualisations. While visualisation of an image collection is useful for providing an overview of the contained images, it forms only part of an image database navigation system. We therefore also present various methods provided by these systems to allow for interactive browsing of these datasets. A further area we explore are user studies of systems and visualisations where we look at the different evaluations undertaken in order to test usability and compare systems, and highlight the key findings from these studies. We conclude the chapter with several recommendations for future work in this area. © 2011 Springer-Verlag Berlin Heidelberg.

Section III: Medical Students

Document detailing the recruitment process and requirements for medical students accepted the College of Medicine. Part of the Medical Education Database for Preliminary Accreditation, 2006-2007.

Knowledge assisted data management and retrieval in multimedia database systems

With the proliferation of multimedia data and ever-growing requests for multimedia applications, there is an increasing need for efficient and effective indexing, storage and retrieval of multimedia data, such as graphics, images, animation, video, audio and text. Due to the special characteristics of the multimedia data, the Multimedia Database management Systems (MMDBMSs) have emerged and attracted great research attention in recent years. Though much research effort has been devoted to this area, it is still far from maturity and there exist many open issues. In this dissertation, with the focus of addressing three of the essential challenges in developing the MMDBMS, namely, semantic gap, perception subjectivity and data organization, a systematic and integrated framework is proposed with video database and image database serving as the testbed. In particular, the framework addresses these challenges separately yet coherently from three main aspects of a MMDBMS: multimedia data representation, indexing and retrieval. In terms of multimedia data representation, the key to address the semantic gap issue is to intelligently and automatically model the mid-level representation and/or semi-semantic descriptors besides the extraction of the low-level media features. The data organization challenge is mainly addressed by the aspect of media indexing where various levels of indexing are required to support the diverse query requirements. In particular, the focus of this study is to facilitate the high-level video indexing by proposing a multimodal event mining framework associated with temporal knowledge discovery approaches. With respect to the perception subjectivity issue, advanced techniques are proposed to support users' interaction and to effectively model users' perception from the feedback at both the image-level and object-level.

Scheduling medical application workloads on virtualized computing systems

This dissertation presents and evaluates a methodology for scheduling medical application workloads in virtualized computing environments. Such environments are being widely adopted by providers of "cloud computing" services. In the context of provisioning resources for medical applications, such environments allow users to deploy applications on distributed computing resources while keeping their data secure. Furthermore, higher level services that further abstract the infrastructure-related issues can be built on top of such infrastructures. For example, a medical imaging service can allow medical professionals to process their data in the cloud, easing them from the burden of having to deploy and manage these resources themselves. In this work, we focus on issues related to scheduling scientific workloads on virtualized environments. We build upon the knowledge base of traditional parallel job scheduling to address the specific case of medical applications while harnessing the benefits afforded by virtualization technology. To this end, we provide the following contributions: (1) An in-depth analysis of the execution characteristics of the target applications when run in virtualized environments. (2) A performance prediction methodology applicable to the target environment. (3) A scheduling algorithm that harnesses application knowledge and virtualization-related benefits to provide strong scheduling performance and quality of service guarantees. In the process of addressing these pertinent issues for our target user base (i.e. medical professionals and researchers), we provide insight that benefits a large community of scientific application users in industry and academia. Our execution time prediction and scheduling methodologies are implemented and evaluated on a real system running popular scientific applications. We find that we are able to predict the execution time of a number of these applications with an average error of 15%. Our scheduling methodology, which is tested with medical image processing workloads, is compared to that of two baseline scheduling solutions and we find that it outperforms them in terms of both the number of jobs processed and resource utilization by 20–30%, without violating any deadlines. We conclude that our solution is a viable approach to supporting the computational needs of medical users, even if the cloud computing paradigm is not widely adopted in its current form.

Improving minimum rate predictors algorithm for compression of volumetric medical images

Medical imaging technologies are experiencing a growth in terms of usage and image resolution, namely in diagnostics systems that require a large set of images, like CT or MRI. Furthermore, legal restrictions impose that these scans must be archived for several years. These facts led to the increase of storage costs in medical image databases and institutions. Thus, a demand for more efficient compression tools, used for archiving and communication, is arising. Currently, the DICOM standard, that makes recommendations for medical communications and imaging compression, recommends lossless encoders such as JPEG, RLE, JPEG-LS and JPEG2000. However, none of these encoders include inter-slice prediction in their algorithms. This dissertation presents the research work on medical image compression, using the MRP encoder. MRP is one of the most efficient lossless image compression algorithm. Several processing techniques are proposed to adapt the input medical images to the encoder characteristics. Two of these techniques, namely changing the alignment of slices for compression and a pixel-wise difference predictor, increased the compression efficiency of MRP, by up to 27.9%. Inter-slice prediction support was also added to MRP, using uni and bi-directional techniques. Also, the pixel-wise difference predictor was added to the algorithm. Overall, the compression efficiency of MRP was improved by 46.1%. Thus, these techniques allow for compression ratio savings of 57.1%, compared to DICOM encoders, and 33.2%, compared to HEVC RExt Random Access. This makes MRP the most efficient of the encoders under study.

Proposing the deep dynamic Bayesian network as a future computer based medical system

The development of new learning models has been of great importance throughout recent years, with a focus on creating advances in the area of deep learning. Deep learning was first noted in 2006, and has since become a major area of research in a number of disciplines. This paper will delve into the area of deep learning to present its current limitations and provide a new idea for a fully integrated deep and dynamic probabilistic system. The new model will be applicable to a vast number of areas initially focusing on applications into medical image analysis with an overall goal of utilising this approach for prediction purposes in computer based medical systems.

Leveraging Multiple Features for Image Retrieval and Matching

The goal of image retrieval and matching is to find and locate object instances in images from a large-scale image database. While visual features are abundant, how to combine them to improve performance by individual features remains a challenging task. In this work, we focus on leveraging multiple features for accurate and efficient image retrieval and matching. We first propose two graph-based approaches to rerank initially retrieved images for generic image retrieval. In the graph, vertices are images while edges are similarities between image pairs. Our first approach employs a mixture Markov model based on a random walk model on multiple graphs to fuse graphs. We introduce a probabilistic model to compute the importance of each feature for graph fusion under a naive Bayesian formulation, which requires statistics of similarities from a manually labeled dataset containing irrelevant images. To reduce human labeling, we further propose a fully unsupervised reranking algorithm based on a submodular objective function that can be efficiently optimized by greedy algorithm. By maximizing an information gain term over the graph, our submodular function favors a subset of database images that are similar to query images and resemble each other. The function also exploits the rank relationships of images from multiple ranked lists obtained by different features. We then study a more well-defined application, person re-identification, where the database contains labeled images of human bodies captured by multiple cameras. Re-identifications from multiple cameras are regarded as related tasks to exploit shared information. We apply a novel multi-task learning algorithm using both low level features and attributes. A low rank attribute embedding is joint learned within the multi-task learning formulation to embed original binary attributes to a continuous attribute space, where incorrect and incomplete attributes are rectified and recovered. To locate objects in images, we design an object detector based on object proposals and deep convolutional neural networks (CNN) in view of the emergence of deep networks. We improve a Fast RCNN framework and investigate two new strategies to detect objects accurately and efficiently: scale-dependent pooling (SDP) and cascaded rejection classifiers (CRC). The SDP improves detection accuracy by exploiting appropriate convolutional features depending on the scale of input object proposals. The CRC effectively utilizes convolutional features and greatly eliminates negative proposals in a cascaded manner, while maintaining a high recall for true objects. The two strategies together improve the detection accuracy and reduce the computational cost.

Automatic Glaucoma Detection Based on Optic Disc Segmentation and Texture Feature Extraction

The use of digital image processing techniques is prominent in medical settings for the automatic diagnosis of diseases. Glaucoma is the second leading cause of blindness in the world and it has no cure. Currently, there are treatments to prevent vision loss, but the disease must be detected in the early stages. Thus, the objective of this work is to develop an automatic detection method of Glaucoma in retinal images. The methodology used in the study were: acquisition of image database, Optic Disc segmentation, texture feature extraction in different color models and classification of images in glaucomatous or not. We obtained results of 93% accuracy

Variational and learning models for image and time series inverse problems

Inverse problems are at the core of many challenging applications. Variational and learning models provide estimated solutions of inverse problems as the outcome of specific reconstruction maps. In the variational approach, the result of the reconstruction map is the solution of a regularized minimization problem encoding information on the acquisition process and prior knowledge on the solution. In the learning approach, the reconstruction map is a parametric function whose parameters are identified by solving a minimization problem depending on a large set of data. In this thesis, we go beyond this apparent dichotomy between variational and learning models and we show they can be harmoniously merged in unified hybrid frameworks preserving their main advantages. We develop several highly efficient methods based on both these model-driven and data-driven strategies, for which we provide a detailed convergence analysis. The arising algorithms are applied to solve inverse problems involving images and time series. For each task, we show the proposed schemes improve the performances of many other existing methods in terms of both computational burden and quality of the solution. In the first part, we focus on gradient-based regularized variational models which are shown to be effective for segmentation purposes and thermal and medical image enhancement. We consider gradient sparsity-promoting regularized models for which we develop different strategies to estimate the regularization strength. Furthermore, we introduce a novel gradient-based Plug-and-Play convergent scheme considering a deep learning based denoiser trained on the gradient domain. In the second part, we address the tasks of natural image deblurring, image and video super resolution microscopy and positioning time series prediction, through deep learning based methods. We boost the performances of supervised, such as trained convolutional and recurrent networks, and unsupervised deep learning strategies, such as Deep Image Prior, by penalizing the losses with handcrafted regularization terms.

Regularization meets GreenAI: a new framework for image reconstruction in life sciences applications

Ill-conditioned inverse problems frequently arise in life sciences, particularly in the context of image deblurring and medical image reconstruction. These problems have been addressed through iterative variational algorithms, which regularize the reconstruction by adding prior knowledge about the problem's solution. Despite the theoretical reliability of these methods, their practical utility is constrained by the time required to converge. Recently, the advent of neural networks allowed the development of reconstruction algorithms that can compute highly accurate solutions with minimal time demands. Regrettably, it is well-known that neural networks are sensitive to unexpected noise, and the quality of their reconstructions quickly deteriorates when the input is slightly perturbed. Modern efforts to address this challenge have led to the creation of massive neural network architectures, but this approach is unsustainable from both ecological and economic standpoints. The recently introduced GreenAI paradigm argues that developing sustainable neural network models is essential for practical applications. In this thesis, we aim to bridge the gap between theory and practice by introducing a novel framework that combines the reliability of model-based iterative algorithms with the speed and accuracy of end-to-end neural networks. Additionally, we demonstrate that our framework yields results comparable to state-of-the-art methods while using relatively small, sustainable models. In the first part of this thesis, we discuss the proposed framework from a theoretical perspective. We provide an extension of classical regularization theory, applicable in scenarios where neural networks are employed to solve inverse problems, and we show there exists a trade-off between accuracy and stability. Furthermore, we demonstrate the effectiveness of our methods in common life science-related scenarios. In the second part of the thesis, we initiate an exploration extending the proposed method into the probabilistic domain. We analyze some properties of deep generative models, revealing their potential applicability in addressing ill-posed inverse problems.

Longitudinal Analysis Of Hippocampal T2 Relaxometry In Fmtle.

To investigate the degree of T2 relaxometry changes over time in groups of patients with familial mesial temporal lobe epilepsy (FMTLE) and asymptomatic relatives. We conducted both cross-sectional and longitudinal analyses of T2 relaxometry with Aftervoxel, an in-house software for medical image visualization. The cross-sectional study included 35 subjects (26 with FMTLE and 9 asymptomatic relatives) and 40 controls; the longitudinal study was composed of 30 subjects (21 with FMTLE and 9 asymptomatic relatives; the mean time interval of MRIs was 4.4 ± 1.5 years) and 16 controls. To increase the size of our groups of patients and relatives, we combined data acquired in 2 scanners (2T and 3T) and obtained z-scores using their respective controls. General linear model on SPSS21® was used for statistical analysis. In the cross-sectional analysis, elevated T2 relaxometry was identified for subjects with seizures and intermediate values for asymptomatic relatives compared to controls. Subjects with MRI signs of hippocampal sclerosis presented elevated T2 relaxometry in the ipsilateral hippocampus, while patients and asymptomatic relatives with normal MRI presented elevated T2 values in the right hippocampus. The longitudinal analysis revealed a significant increase in T2 relaxometry for the ipsilateral hippocampus exclusively in patients with seizures. The longitudinal increase of T2 signal in patients with seizures suggests the existence of an interaction between ongoing seizures and the underlying pathology, causing progressive damage to the hippocampus. The identification of elevated T2 relaxometry in asymptomatic relatives and in patients with normal MRI suggests that genetic factors may be involved in the development of some mild hippocampal abnormalities in FMTLE.

Providing Integrity and Authenticity in DICOM Images: A Novel Approach

The increasing adoption of information systems in healthcare has led to a scenario where patient information security is more and more being regarded as a critical issue. Allowing patient information to be in jeopardy may lead to irreparable damage, physically, morally, and socially to the patient, potentially shaking the credibility of the healthcare institution. Medical images play a crucial role in such context, given their importance in diagnosis, treatment, and research. Therefore, it is vital to take measures in order to prevent tampering and determine their provenance. This demands adoption of security mechanisms to assure information integrity and authenticity. There are a number of works done in this field, based on two major approaches: use of metadata and use of watermarking. However, there still are limitations for both approaches that must be properly addressed. This paper presents a new method using cryptographic means to improve trustworthiness of medical images, providing a stronger link between the image and the information on its integrity and authenticity, without compromising image quality to the end user. Use of Digital Imaging and Communications in Medicine structures is also an advantage for ease of development and deployment.

A decision support system to facilitate management of patients with acute gastrointestinal bleeding

Objective: To develop a model to predict the bleeding source and identify the cohort amongst patients with acute gastrointestinal bleeding (GIB) who require urgent intervention, including endoscopy. Patients with acute GIB, an unpredictable event, are most commonly evaluated and managed by non-gastroenterologists. Rapid and consistently reliable risk stratification of patients with acute GIB for urgent endoscopy may potentially improve outcomes amongst such patients by targeting scarce health-care resources to those who need it the most. Design and methods: Using ICD-9 codes for acute GIB, 189 patients with acute GIB and all. available data variables required to develop and test models were identified from a hospital medical records database. Data on 122 patients was utilized for development of the model and on 67 patients utilized to perform comparative analysis of the models. Clinical data such as presenting signs and symptoms, demographic data, presence of co-morbidities, laboratory data and corresponding endoscopic diagnosis and outcomes were collected. Clinical data and endoscopic diagnosis collected for each patient was utilized to retrospectively ascertain optimal management for each patient. Clinical presentations and corresponding treatment was utilized as training examples. Eight mathematical models including artificial neural network (ANN), support vector machine (SVM), k-nearest neighbor, linear discriminant analysis (LDA), shrunken centroid (SC), random forest (RF), logistic regression, and boosting were trained and tested. The performance of these models was compared using standard statistical analysis and ROC curves. Results: Overall the random forest model best predicted the source, need for resuscitation, and disposition with accuracies of approximately 80% or higher (accuracy for endoscopy was greater than 75%). The area under ROC curve for RF was greater than 0.85, indicating excellent performance by the random forest model Conclusion: While most mathematical models are effective as a decision support system for evaluation and management of patients with acute GIB, in our testing, the RF model consistently demonstrated the best performance. Amongst patients presenting with acute GIB, mathematical models may facilitate the identification of the source of GIB, need for intervention and allow optimization of care and healthcare resource allocation; these however require further validation. (c) 2007 Elsevier B.V. All rights reserved.

Shape alterations in the striatum in chorea-acanthocytosis

Chorea-acanthocytosis (ChAc) is an uncommon autosomal recessive disorder due to mutations of the VPS13A gene, which encodes for the membrane protein chorein. ChAc presents with progressive limb and orobuccal chorea, but there is often a marked dysexecutive syndrome. ChAc may first present with neuropsychiatric disturbance such as obsessive-compulsive disorder (OCD), suggesting a particular role for disruption to striatal structures involved in non-motor frontostriatal loops, such as the head of the caudate nucleus. Two previous studies have suggested a marked reduction in volume in the caudate nucleus and putamen, but did not examine morphometric change. We investigated morphometric change in 13 patients with genetically or biochemically confirmed ChAc and 26 age- and gender-matched controls. Subjects underwent magnetic resonance imaging and manual segmentation of the caudate nucleus and putamen, and shape analysis using a non-parametric spherical harmonic technique. Both structures showed significant and marked reductions in volume compared with controls, with reduction greatest in the caudate nucleus. Both structures showed significant shape differences, particularly in the head of the caudate nucleus. No significant correlation was shown between duration of illness and striatal volume or shape, suggesting that much structural change may have already taken place at the time of symptom onset. Our results suggest that striatal neuron loss may occur early in the disease process, and follows a dorsal-ventral gradient that may correlate with early neuropsychiatric and cognitive presentations of the disease. (C) 2010 Elsevier Ireland Ltd. All rights reserved.

Real-time 3D interactive segmentation of echocardiographic data through user-based deformation of B-spline explicit active surfaces

Image segmentation is an ubiquitous task in medical image analysis, which is required to estimate morphological or functional properties of given anatomical targets. While automatic processing is highly desirable, image segmentation remains to date a supervised process in daily clinical practice. Indeed, challenging data often requires user interaction to capture the required level of anatomical detail. To optimize the analysis of 3D images, the user should be able to efficiently interact with the result of any segmentation algorithm to correct any possible disagreement. Building on a previously developed real-time 3D segmentation algorithm, we propose in the present work an extension towards an interactive application where user information can be used online to steer the segmentation result. This enables a synergistic collaboration between the operator and the underlying segmentation algorithm, thus contributing to higher segmentation accuracy, while keeping total analysis time competitive. To this end, we formalize the user interaction paradigm using a geometrical approach, where the user input is mapped to a non-cartesian space while this information is used to drive the boundary towards the position provided by the user. Additionally, we propose a shape regularization term which improves the interaction with the segmented surface, thereby making the interactive segmentation process less cumbersome. The resulting algorithm offers competitive performance both in terms of segmentation accuracy, as well as in terms of total analysis time. This contributes to a more efficient use of the existing segmentation tools in daily clinical practice. Furthermore, it compares favorably to state-of-the-art interactive segmentation software based on a 3D livewire-based algorithm.