Schroedinger Eigenmaps for the Analysis of Biomedical Data

Czaja, Wojciech; Ehler, Martin

doi:10.1109/tpami.2012.270

Cited by 66 publications

(29 citation statements)

References 36 publications

(38 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An alternative to using only a single band is to apply a dimension reduction technique to the entire multispectral image, in order to combine the individual bands into a single representative image. Possible techniques for this are linear methods, such as PCA, and nonlinear methods, such as Laplacian eigenmaps [46] and related graph-kernel methods [47]. Taking as the input image the first principal component in the case of PCA, or the first eigenvector in the case of Laplacian eigenmaps, and then registering this to the reference image using our algorithm, is one approach to extending our method to full multispectral and hyperspectral images.…”

Section: Multispectral-to-panchromatic Registration Experimentsmentioning

confidence: 99%

Automatic Image Registration of Multimodal Remotely Sensed Data With Global Shearlet Features

Murphy

Moigne

Harding

2016

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Automatic image registration is the process of aligning two or more images of approximately the same scene with minimal human assistance. Wavelet-based automatic registration methods are standard, but sometimes are not robust to the choice of initial conditions. That is, if the images to be registered are too far apart relative to the initial guess of the algorithm, the registration algorithm does not converge or has poor accuracy, and is thus not robust. These problems occur because wavelet techniques primarily identify isotropic textural features and are less effective at identifying linear and curvilinear edge features. We integrate the recently developed mathematical construction of shearlets, which is more effective at identifying sparse anisotropic edges, with an existing automatic wavelet-based registration algorithm. Our shearlet features algorithm produces more distinct features than wavelet features algorithms; the separation of edges from textures is even stronger than with wavelets.Our algorithm computes shearlet and wavelet features for the images to be registered, then performs least squares minimization on these features to compute a registration transformation. Our algorithm is two-staged and multiresolution in nature. First, a cascade of shearlet features is used to provide a robust, though approximate, registration. This is then refined by registering with a cascade of wavelet features. Experiments across a variety of image classes show an improved robustness to initial conditions, when compared to wavelet features alone.

show abstract

Section: Multispectral-to-panchromatic Registration Experimentsmentioning

confidence: 99%

Automatic Image Registration of Multimodal Remotely Sensed Data With Global Shearlet Features

Murphy

Moigne

Harding

2016

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Applications of MSI have shown promising results in different areas of biomedical image analysis ranging from human forearm imaging to skin chromophore mapping, [34][35][36][37][38] with several applied to retinal image analysis. [39][40][41][42] A recent study on retinal vein occlusion demonstrated that MSI was able to define vascular abnormalities at a comparable performance as fundus photography, fundus fluorescein angiography, and optical coherence tomography. 43 In MSI, image data are captured at specific nonoverlapping frequency bands.…”

Section: Resultsmentioning

confidence: 99%

Automated microaneurysm detection in diabetic retinopathy using curvelet transform

et al. 2016

View full text Add to dashboard Cite

Abstract. Microaneurysms (MAs) are known to be the early signs of diabetic retinopathy (DR). An automated MA detection system based on curvelet transform is proposed for color fundus image analysis. Candidates of MA were extracted in two parallel steps. In step one, blood vessels were removed from preprocessed green band image and preliminary MA candidates were selected by local thresholding technique. In step two, based on statistical features, the image background was estimated. The results from the two steps allowed us to identify preliminary MA candidates which were also present in the image foreground. A collection set of features was fed to a rule-based classifier to divide the candidates into MAs and non-MAs. The proposed system was tested with Retinopathy Online Challenge database. The automated system detected 162 MAs out of 336, thus achieved a sensitivity of 48.21% with 65 false positives per image. Counting MA is a means to measure the progression of DR. Hence, the proposed system may be deployed to monitor the progression of DR at early stage in population studies. © The Authors. Published by SPIE under a Creative Commons Attribution 3.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.

show abstract

“…Deep learning models have several drawbacks, such as the need for huge amounts of training data, high training time, large memory usage, and the complicated design of a suitable network. A semi-supervised technique was developed by Zheng et al 4 (see also Chen et al, 5 Xu et al, 6 and Wilkins et al; 7 for general learning techniques, we refer to Grady, 8 Czaja and Ehler, 9 Schölkopf and Smola, 10 and Roweis and Saul 11 ). Here we shall provide an efficient method with a fast learning part and low memory needs based on dimension reduction techniques.…”

Section: Introductionmentioning

confidence: 99%

Supervised learning and dimension reduction techniques for quantification of retinal fluid in optical coherence tomography images

Breger

Ehler

Bogunović

et al. 2017

Eye

View full text Add to dashboard Cite

PurposeThe purpose of the present study is to develop fast automated quantification of retinal fluid in optical coherence tomography (OCT) image sets.MethodsWe developed an image analysis pipeline tailored towards OCT images that consists of five steps for binary retinal fluid segmentation. The method is based on feature extraction, pre-segmention, dimension reduction procedures, and supervised learning tools.ResultsFluid identification using our pipeline was tested on two separate patient groups: one associated to neovascular age-related macular degeneration, the other showing diabetic macular edema. For training and evaluation purposes, retinal fluid was annotated manually in each cross-section by human expert graders of the Vienna Reading Center. Compared with the manual annotations, our pipeline yields good quantification, visually and in numbers.ConclusionsBy demonstrating good automated retinal fluid quantification, our pipeline appears useful to expert graders within their current grading processes. Owing to dimension reduction, the actual learning part is fast and requires only few training samples. Hence, it is well-suited for integration into actual manufacturer's devices, further improving segmentation by its use in daily clinical life.

show abstract

Schroedinger Eigenmaps for the Analysis of Biomedical Data

Cited by 66 publications

References 36 publications

Automatic Image Registration of Multimodal Remotely Sensed Data With Global Shearlet Features

Automatic Image Registration of Multimodal Remotely Sensed Data With Global Shearlet Features

Automated microaneurysm detection in diabetic retinopathy using curvelet transform

Supervised learning and dimension reduction techniques for quantification of retinal fluid in optical coherence tomography images

Contact Info

Product

Resources

About