Effort has been put during this reporting period to enhance the predictive analysis that has commenced since last semester. This has been achieved by including more variables in the analysis and currently, focusing on also including time-invariant information, i.e. measurements of clinical features. Some initial results indicate a decent model fit, particularly for the initial states, however, there is still space for improvement as the figures of model fit below suggest.
During the reporting period, simulations by means of the model of the retinal vascular network were completed. A manuscript on modelling was written and submitted to the Bulletin of Mathematical Biology.
The data obtained during animal experiments last summer was analysed. In February the manuscript was approved and published in Biomedical Optics Express.
Preparations for a new series of experiments were performed. These experiments are designed to study vasomotion in rat retinal vasculature. Results are planned to be submitted to a special issue in the Journal for Modeling in Ophthalmology.
Over the past six months, I have finished data collection from my experiment on early adaptation of arteriolar collaterals in chick chorioallantoic membrane (CAM) which will be presented in my paper that is to be submitted later this month. In general, our work shows that after occlusion, unidirectional flow towards the occlusion site was established. Diameters exhibited a significant immediate decrease, followed by an increase with a time constant of 2.5 ± 0.8h (mean ± SD, P<0.05) leading to a plateau up to 60% above the baseline value without significant vascular tone change. In contrast, WSS exhibited a significant increase immediately post-occlusion, followed by an approximately linear decrease returning to the baseline value after about 12h. Maximal increase in WSS and sustained diameter changes were significantly correlated (see figures below).
After joining the REVAMMAD project, I started a training about machine learning techniques focusing on ensemble methods. Later, in the frame of the data warehouse task, I started to plan an application for data and algorithm sharing together with the Orobix team. In order to best suit the needs of the collaboration, I developed a system that supports both centralized and peer-to-peer exchange of datasets and algorithms, also exploiting the software libraries currently being developed in an open source project (DAT project). Most of the time of this reporting period has been dedicated to the implementation and the deployment of a prototype of this application. More recently, I began to investigate the application of artificial neural networks for segmentation tasks in medical imaging.
This reporting period my main contribution has been my work in tortuosity. We have gone in a different direction than most methods, which rely on a rigid mathematical formulation of curvature, to a feature-based method which relies on enhancing curvature in an image. This allows for a tuneable method that doesn’t require a perfect segmentation or vessel centreline to accurately measure tortuosity in a vessel, and we hope to expand the idea to the image level.
The segmentation module of our fully automated tortuosity estimation system has been improved both in terms of modelling curvilinear structures and learning context filters. Moreover, a novel approach to accelerate convolutional sparse coding filter learning has been developed. This is expected to make filter learning much more discriminative and result in a more robust segmentation module. The tortuosity plane has been proposed as a better tool to quantify and interpret tortuosity (an example of how the tortuosity plane is used to map corneal nerve images in terms of tortuosity is included). Please refer to my webpage for further details. http://staff.computing.dundee.ac.uk/rannunziata/publications.html
In the last six months my work has focused on implementing an alternative method for summarising the retinal vessel calibres in more than one group (healthy, diabetics and DRs), which will yield and estimate the trunk vessel more accurately than the current method in literature. In addition to that, the different areas inside the retina were defined, using as landmarks the optic nerve head and fovea. These areas, that have been found to include the most lesions during the progression of DR, will be used for extracting geometric features in order to see whether any significant changes occur prior to the onset of DR. In collaboration with another ESR, vascular trees were segmented, connected and a series of hemodynamic features were calculated alongside the geometric ones, in order to conduct an overall analysis of the changes and the effect that the diabetes/DR have to the retinal vasculature during the last three years of diabetes until the first year of DR.
The last six months have been mainly dedicated to three different aspects. Firstly, finalising the ongoing publications: one paper on retinal autoregulation is now available online in the Journal for Modeling in Ophthalmology and another paper, more focused on the simplified fluid-structure interaction model used in the autoregulation modeling, has been accepted for publication in Comp. Meth. Appl. Mech. Engng. Secondly, the ROM techniques developed in view of their application on a more golbal model of the eye have been implemented and tested. A publication describing such techniques and their results has been submitted. Thirdly, the collaboration with the University of Strasbourg and in particular with Prof. Giovanna Guidoboni has started. The idea is to develop a more global model of the eye to address medical questions regarding the IntraOcular Pressure (IOP).
Netrins are a family of matrix-binding proteins that function as guidance signals. Netrin-4 displays pathologic roles in tumorigenesis and
neovascularization. To answer the question whether netrin-4 acts either pro- or anti-angiogenic, angiogenesis in the retina was assessed in Ntn-4−/− mice with oxygeninduced retinopathy (OIR) and laser-induced choroidal neovascularization (CNV), mimicking hypoxiamediated neovascularization and inflammatory mediated angiogenesis. The basement membrane protein netrin-4 was found to be localised to mature retinal blood vessels. Netrin-4, but not netrin-1 mRNA expression, increased in response to relative hypoxia and recovered to normal levels at the end of blood vessel formation. No changes in the retina were found in normoxic Ntn-4−/− mice. In OIR, Ntn-4−/− mice initially displayed larger avascular areas which recovered faster to revascularization. Ganzfeld electroretinography showed faster recovery of retinal function in Ntn-4−/− mice. Expression of netrin receptors, Unc5H2 and DCC, was found in Müller cells and astrocytes. Laser-induced neovascularization in Nnt-4−/− mice did not differ to that in the controls. Our results indicate a role for netrin-4 as an angiogenesis modulating factor in O2-dependent vascular homeostasis while being less important during normal retinal developmental angiogenesis or during inflammatory neovascularization.
Our publications for this reporting period have been related to corneal imaging. My colleagues and I have produced methods for the automatic detection of microdots, segmentation of nerves, and building mosaics of images for confocal microscopy. Some of this work can be directly ported to retinal images. Much of the research and hopefully subsequent publications will be related to retinal vessel analysis and image quality. Both are important topics for REVAMMAD. My work on vessel junctions combines local color, edge and gradient information to determine whether the vein or artery crosses on top and analyses the area to determine if knicking is occuring. This work also helps to separate the artery and vein trees in the image.
In the last nine months I have been mainly working on three different topics: smooth muscle models, retinal image analysis and intra ocular pressure (IOP). These topics may seem unrelated, however, retinal imaging tools are fundamental in providing reliable geometries for haemodynamics models. Retinal blood flow is characterized by autoregulation phenomena and smooth muscle cells play an important role in it: contracting and relaxing following bio-chemical stimuli. We have summarized the results of this autoregulation models in a publication that is going through the review process. Finally, IOP plays a major role in several eye diseases (glaucoma, for instance) and we have just started to address the problem of modeling of the eye from a broader point of view coupling the haemodynamics with the intra ocular pressure.
The main goal of my project is to define alternative strategies that can prove to be more efficient and/or cost saving in the detection of diabetic retinopathy. The first step of this process was an extensive literature review in order to gain a comprehensive understanding of the nature of the disease, the risk factors that affect its progression and the different frameworks applied for detection. My knowledge was further reinforced by untertaking the level 3 City and Guilds accreditation for screeners and graders and by participating in respective conferences and seminars.
Currently, I am trying to define the underlying parameters of the National Diabetic Eye Screening Programme and estimate the relative costs especially in the case of inappropriate decisions. This is the starting point of my practical implementation and the accurate definition of the framework of this model is crucial in the further assessment of alternative approaches.
During this reporting period, Carlos continued working on his 3D retinal registration method, obtaining very promising experimental results. Those results lead to the preparation of a paper that will be submitted to Engineering in Medicine and Biology Conference 14. He also worked with ESR 3.2, Sergio Crespo Carcia, in a fruiful collaboration that led to the submission of a paper to the Experimental Eye Research Journal.
- Establishment of protocols on wall thickness measurement of microvessels (diameter>=10 µm) on chick chorioallantoic membrane (CAM)
- Devising of protocols on videomicroscopy using high speed camera which allows pulsatility analysisi of blood flow on CAM
- Semi-automatic segmentation methods established in collaboration with ESR 2.1 Francesco Caliva and Dr. Bashir Al-Diri from University of Lincoln, UK.
The automatic detection of lesions is a fundamental tool for my future research on the progression of diabetic retinopathy. My secondment in Lincoln was aimed at testing and adjusting an existing algorithm available at my partner University. While the algorithm was created to find all types of lesion to automate the diagnosis of referable maculopathy, my future research will need it for the detection of micro-aneurisms.
Testing the algorithm on the pictures from high-risk patients from my previous study showed that more than half of micro-aneurisms were not detected. It was found that many of the lesions were not detected on the candidate-selection stage of the algorithm. A newly developed method, based on the template matching technique, could find 50% more true-lesions candidates.
The combination of the two methods detects approximately 70% of the true lesions among the candidates from funds photographs from high-risk patients.
I am participating actively in several projects that approach neovascularization under pathological conditions in the retina, with the interaction of an inflammatory or hypoxic environment. Projects to mention are:
- Quantification of activated microglia in vivo in laser CNV MacGreen mouse.
- Settling of a model for hypertensive retinopathy: dTGR.
- Settling of a model for diabetic retinopathy in a knock down rat: TetO.
- Analysis in vivo and in vitro of CD11b+ cells under ROP paradigm. .
- The role of Netrin4 under pathological neovascularization.
- In vivo follow-up of macrophages in early stages of STZ MacGreen mouse and comparison with a double model MacGreen-Netrin4-/-.
- Role of PlGF in pathological neovascularization.
- Chronic bilateral cranial hypoperfusion in mice analysis in the retina.
I have been working on the design and development of ad-hoc methods for curvilinear structures segmentation.
This work was motivated by the fact that state-of-the-art approaches tend to fail when dealing with corneal nerve fibres captured via confocal microscopy. Qualitative and quantitative results show that our methods outperform previously reported methods on several dataset.
Automated curvilinear structure detection in images capturing corneal nerve fibres and neuronal trees with various technical challenges such as confounding non-target structures, low contrast, low resolution, non-uniform illumination, high tortuosity level and fragmentation.
During this period, I focused mainly on extracting as many features as possible from the available DR images, based on strict quality criteria (regarding inclusion of observations, power estimations and avoidance of statistical errors). Moreover, a suitable hybrid mixed model was introduced specific for the nature of my analysis which can be used when the independence of observations is violated in simple models where we include correlated data.
The fractality and lacunarity for the complexity of vascular trees has been introduced for which the skeletonised or segmented images are required. Multiple features are being tested for their significance and discriminative ability identifying patterns of changes when the vessels’ structure is changing.
New features include branch retinal equivalent, width-to-angle ratio, sum of squares of widths (which is continuosly differentiable and useful for minimising variance) and can be used in the cross section estimation which in turn is useful for the flow rate function. Centreline length to straight distance ration and the junction exponent calculated by the Branching coefficient and fractal (box-counting/hausdorf) dimention are among the other possible features.
Due to image artefacts, the result of the blood vessels’ segmentation is a set of disconnected short segments. During this three months reporting period, I worked on the problem of connecting them. At this aim, an algorithm was implemented.
Given a group consisting of a certain number of segments, there can be connected together in several ways: two segments can join each other and form a bridge; three segments can generate a bifurcation; or they can just be terminals.
At this stage, the connections rely on the use of implicit cost functions.
Besides, an user friendly Matlab tool was designed. Thanks to this tool, it is possible to adjust the results obtained using the previously mentioned cost functions. The tool includes also a fast altorithm for the segmentation of missing blood vessels.
The tool, which in part was developed with ESR 1.1 during his secondment at the University of Lincoln, is currently being tested by ESR 1.2.
During this reporting period, the mathematical model of the retinal vascular network was improved, and some results for paper were obtained. Work on manuscript, dedicated to mathematical model was started. In addition to modeling part of my work, animal experiments on rats eyes were carried out. Now, these experiments are focused on detection of retinal reaction on flickering-light stimulus. Furthermore, I am involved in experiments on eggs chorioallantoic membrane, which are focused on vascular network remodelling. To get the rat retinal images and images of eggs chorioallantoic membrane we using Laser Speckle Contrast method, that is “full-field” and non invasive technique.
Experimentation, as part of my REVAMMAD project, aims to lay ground for simulation of blood flow and vascular structural adaptation in microvascular network on CAM before and after arteriolar occlusion. Generally, this experimental work includes three consecutive components: 1) Cultivation of ex-ovo chicken embryos; 2) Imaging and recording of microvascular network on ex-ovo CAM assay with and without laser irradiation; 3) Parameter analysis including parameters of vessel morphology, network topology, hemodynamics, metabolism and vascular adaptation.
To approach retinal vascular diseases it is necessary to adopt different strategies to understand the mechanisms of the pathology and transfer that knowledge into practical clinical tools. Vasculature in the retina changes under pathological conditions. However, vessels are not alone and we have to understand the disease as a complex puzzle where every piece has its role. Some other cell types besides the ones that compound vessels might be involved in terms of disease, as it is the case of neurons and microglia. Microglia belongs to the immune system at the retina, but its role in disease it is not clearly understood. Current models of imaging and algorithm analysis are pursuing early diagnosis regarding the dynamics and structure of the vasculature. In our basic medical research, we aim to switch the disease correlation into a new concept that involves vessels inside the neurovascular unit, where microglia might play a role, turning the current analysis model into one more complex and defined status.
Classify in vivo confocal microscopy corneal images by tortuosity is complicated by the presence of variable numbers of fibres of different tortuosity level. Instead of designing a function combining manually selected features into a single coefficient, as done in the literature, we proposed a supervised approach which selects automatically the most relevant combination of shape features from a pre-dened dictionary. To our best knowledge, we are the first to consider features at different spatial scales and show experimentally their relevance in tortuosity modelling. Experimental results using a data set of 90 images provided by our clinical collaborators at the Harvard Medical School and Massachusetts Eye and Ear Infirmary show that our framework yields an accuracy indistinguishable, overall, from that of experts when compared against each other.
During last 6 months I managed to accomplish an important milestone in my project, namely the creation of a prototype of Data Warehouse. Initial architecture decisions proved to be correct and led to an implementation that is robust and flexible at the same time. Existence of a prototype allows me to start incorporating datasets and computations into the system as well as commence testing of all components interacting with each other. Data warehouse is built using innovative technologies and we believe that it has a strong industrial potential because (to the best of our knowledge) there is no similar solution in the market. The existence of Data Warehouse which stores multiple heterogeneous datasets and computations that makes it easy to query them is essential before proceeding to the next part of the project which is extracting similar retinal images. After reviewing scientific literature dealing with similarity learning I decided to use deep learning which excels at learning intermediate representations of highly dimensional data that can be used to learn similarity between medical images. My deep learning research led me to a discovery of a novel approach for retinal vessel segmentation that can compete with the state-of-the-art methods in this field.
Our publications for this reporting period have been related to corneal imaging. My colleagues and I have produced methods for the automatic detection of microdots, segmentation of nerves, and building mosaics of images for confocal microscopy. Some of this work can be directly ported to retinal images. Much of the research and hopefully subsequent publications will be related to retinal vessel analysis and image quality. Both are important topics for REVAMMAD. My work on vessel junctions combines local color, edge and gradient information to determine whether the vein or artery crosses on top and analyses the area to determine if knicking is occurring. This work also helps to separate the artery and vein trees in the image.