Topological data analysis of high resolution diabetic retinopathy images

Garside, Kathryn; Henderson, Robin; Makarenko, Irina; Masoller, Cristina

doi:10.1371/journal.pone.0217413

Cited by 37 publications

(29 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our findings are consistent with the results recently reported in [59], where topological data analysis (TDA) was applied to the fundus images of diabetic retinopathy patients and healthy subjects in the HRF and MESSIDOR databases. The TDA features (that characterize connected components and holes in the images) allowed to discriminate between healthy patients and those with diabetic retinopathy in the HRF database but not in the MESSIDOR database, a fact that was interpreted as a due to the much lower resolution of MESSIDOR.…”

Section: Discussionsupporting

confidence: 92%

Network-based features for retinal fundus vessel structure analysis

et al. 2019

Self Cite

View full text Add to dashboard Cite

Retinal fundus imaging is a non-invasive method that allows visualizing the structure of the blood vessels in the retina whose features may indicate the presence of diseases such as diabetic retinopathy (DR) and glaucoma. Here we present a novel method to analyze and quantify changes in the retinal blood vessel structure in patients diagnosed with glaucoma or with DR. First, we use an automatic unsupervised segmentation algorithm to extract a tree-like graph from the retina blood vessel structure. The nodes of the graph represent branching (bifurcation) points and endpoints, while the links represent vessel segments that connect the nodes. Then, we quantify structural differences between the graphs extracted from the groups of healthy and non-healthy patients. We also use fractal analysis to characterize the extracted graphs. Applying these techniques to three retina fundus image databases we find significant differences between the healthy and non-healthy groups (p-values lower than 0.005 or 0.001 depending on the method and on the database). The results are sensitive to the segmentation method (manual or automatic) and to the resolution of the images.

show abstract

Section: Discussionsupporting

confidence: 92%

Network-based features for retinal fundus vessel structure analysis

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…An increase of glial fibrillary acidic protein (GFAP) expression, a feature already described in patients with diabetic retinopathy (Mizutani et al 1998), was also detected in the DMHC pig model (Acharya et al 2017). Vascular complications of DM are the most serious manifestation of the disease in humans (Garside et al 2019;Rask-Madsen and King 2013). Pigs were shown to have a retinal vasculature that closely resembles that of man (Bloodworth et al 1965).…”

Section: Ocular Complicationsmentioning

confidence: 96%

Porcine models for studying complications and organ crosstalk in diabetes mellitus

Renner¹,

Blutke

Clauß

et al. 2020

Cell Tissue Res

View full text Add to dashboard Cite

The worldwide prevalence of diabetes mellitus and obesity is rapidly increasing not only in adults but also in children and adolescents. Diabetes is associated with macrovascular complications increasing the risk for cardiovascular disease and stroke, as well as microvascular complications leading to diabetic nephropathy, retinopathy and neuropathy. Animal models are essential for studying disease mechanisms and for developing and testing diagnostic procedures and therapeutic strategies. Rodent models are most widely used but have limitations in translational research. Porcine models have the potential to bridge the gap between basic studies and clinical trials in human patients. This article provides an overview of concepts for the development of porcine models for diabetes and obesity research, with a focus on genetically engineered models. Diabetes-associated ocular, cardiovascular and renal alterations observed in diabetic pig models are summarized and their similarities with complications in diabetic patients are discussed. Systematic multi-organ biobanking of porcine models of diabetes and obesity and molecular profiling of representative tissue samples on different levels, e.g., on the transcriptome, proteome, or metabolome level, is proposed as a strategy for discovering tissue-specific pathomechanisms and their molecular key drivers using systems biology tools. This is exemplified by a recent study providing multi-omics insights into functional changes of the liver in a transgenic pig model for insulin-deficient diabetes mellitus. Collectively, these approaches will provide a better understanding of organ crosstalk in diabetes mellitus and eventually reveal new molecular targets for the prevention, early diagnosis and treatment of diabetes mellitus and its associated complications.

show abstract

“…For the past decade, persistent homology 1 -the most prominently used and studied tool within the field of Topological Data Analysis (TDA) 2 -has lead to many new applications for image segmentation and classification [3][4][5][6][7][8] . The great potential of TDA for images is due to their grid-like structure.…”

Section: Topological Image Modification For Object Detection and Topomentioning

confidence: 99%

Topological image modification for object detection and topological image processing of skin lesions

Vandaele

Nervo²,

Gevaert

2020

Sci Rep

View full text Add to dashboard Cite

We propose a new method based on Topological Data Analysis (TDA) consisting of Topological Image Modification (TIM) and Topological Image Processing (TIP) for object detection. Through this newly introduced method, we artificially destruct irrelevant objects, and construct new objects with known topological properties in irrelevant regions of an image. This ensures that we are able to identify the important objects in relevant regions of the image. We do this by means of persistent homology, which allows us to simultaneously select appropriate thresholds, as well as the objects corresponding to these thresholds, and separate them from the noisy background of an image. This leads to a new image, processed in a completely unsupervised manner, from which one may more efficiently extract important objects. We demonstrate the usefulness of this proposed method for topological image processing through a case-study of unsupervised segmentation of the ISIC 2018 skin lesion images. Code for this project is available on https://bitbucket.org/ghentdatascience/topimgprocess.

show abstract

Topological data analysis of high resolution diabetic retinopathy images

Cited by 37 publications

References 19 publications

Network-based features for retinal fundus vessel structure analysis

Network-based features for retinal fundus vessel structure analysis

Porcine models for studying complications and organ crosstalk in diabetes mellitus

Topological image modification for object detection and topological image processing of skin lesions

Contact Info

Product

Resources

About