Automatic detection of red lesions in digital color fundus photographs

By Meindert Niemeijer, B. van Ginneken, Joes Staal, M. Suttorp-Schulten, Michael David Abràmoff. IEEE Transactions on Medical Imaging, 2005

615 citations recorded by the source corpus.

Subfields: Ophthalmology, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/444deb4d61347150f98d2095192bf0c9a75c99bf

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Ophthalmology

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Retinal Blood Vessel Segmentation Using Line Operators and Support Vector Classification (2007, background): “Conversely, in some applications the vasculature must be excluded from the analysis to ease automatic detection of pathological elements like exudates or microaneurysms [5].”
A New Supervised Method for Blood Vessel Segmentation in Retinal Images by Using Gray-Level and Moment Invariants-Based Features (2011, methodology): “Then, the difference between and is calculated for every pixel (1) To this respect, literature reports shade-correction methods based on the subtraction of the background image from the original image [10], [12], [57] or the division of the latter by the former [58], [59].”
Automatic hemorrhage detection in color fundus images based on gradual removal of vascular branches (2016, methodology): “[3] proposed a hybrid method coupled with the pixel classification.”
Retinal Imaging and Image Analysis (2010, positive): “candidate pixels, to a multifilter filter-bank approach [73], [84].”
DIARETDB 1 diabetic retinopathy database and evaluation protocol (2007, methodology): “[12] used a similar approach for bright abnormal region detection as they used for finding abnormal red regions in [13].”
DREAM: Diabetic Retinopathy Analysis Using Machine Learning (2014, background): “The ﬁrst kind of classiﬁers incur low computational complexity such as kNN [15], and GMM [16] with two multivariate Gaussians, one Gaussian corresponding to class 0 and another to class 1.”
Automated microaneurysm detection using local contrast normalization and local vessel detection (2006, methodology): “A similar approach is also employed in [5] for detection of MAs and larger red lesions known as haemorrhages.”
Automatic detection of diabetic retinopathy exudates from non-dilated retinal images using mathematical morphology methods (2008, background): “This paper investigates and roposes a set of optimally adjusted morphological operators to be used for exudate detection on diabetic retinopathy patients’ non-dilated pupil and ow-contrast images.”
Automated detection and differentiation of drusen, exudates, and cotton-wool spots in digital color fundus photographs for diabetic retinopathy diagnosis. (2007, background): “Microaneurysm, retinal hemorrhage, neovascularization, and other retinal microvascular abnormalities: an algorithm for detecting these red lesions.(10)”
A survey on automated microaneurysm detection in Diabetic Retinopathy retinal images (2013, methodology): “After preprocessing, microaneurysms are extracted using recursive region growing and adaptive intensity thresholding with “moat operator” and edge enhancement operator.”
A Survey on ensemble learning under the era of deep learning (2021, methodology): “TFE32 Volumetric features extracted from fundus images (Niemeijer et al. 2005; SB and Singh 2012; Seoud et al. 2016)”
Multiscale AM-FM Methods for Diabetic Retinopathy Lesion Detection (2010, background): “[10] removed the slow gradients in the background of the green channel of each image resulting in a shade-corrected image.”
Automatic detection of microaneurysms in color fundus images (2007, methodology): “These considerations have lead several authors to the use of KNN classifiers (Walter et al., 2001; Niemeijer et al., 2005), which consist in assigning to a new candidate z the class to which the majority among the K nearest neighbors of z belongs.”
IDRiD: Diabetic Retinopathy - Segmentation and Grading Challenge. (2020, background): “These red lesions (both MAs and HEs) are also frequently detected together us-ing dynamic shape features ( Seoud et al., 2016 ), ﬁlter response and multiple kernel learning ( Srivastava et al., 2017 ) and hybrid feature extraction approach ( Niemeijer et al., 2005 ).”
Optimal Wavelet Transform for the Detection of Microaneurysms in Retina Photographs (2008, methodology): “We also evaluated our lesion detector as a candidate extractor for Niemeijer’s method (NPM), instead of mathematical morphology and pixel classification based candidate extractors.”