Retinal Image Classification for the Screening of Age-Related Macular Degeneration

Hijazi, Mohd Hanafi Ahmad; Coenen, Frans; Zheng, Yalin

doi:10.1007/978-0-85729-130-1_25

Cited by 23 publications

(16 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The minimal warping path is computed by summing up the minimal d for each matrix grid point thus giving a distance between T andT . More details of the DTW approach with respect to retinal image classification can be found in [42].…”

Section: Retinal Image Classification Using Cbr and Dtwmentioning

confidence: 99%

Data mining techniques for the screening of age-related macular degeneration

Hijazi

Coenen

Zheng

2012

Knowledge-Based Systems

Self Cite

View full text Add to dashboard Cite

Age related Macular Degeneration (AMD) is the primary cause of adult blindness. Currently AMD cannot be cured, however early detection does allow the progress of the condition to be inhibited. One of the first symptoms of AMD is the presence of fatty deposits, called drusen, on the retina. The presence of drusen may be identified through the manual inspection/screening of retinal images. This task, however, requires recourse to domain experts and is therefore resource intensive. This paper proposes and compares two data mining techniques to support the automated screening for AMD. The first uses spatial-histograms, that maintain both image colour and spatial information, for the image representation; to which a Case Based Reasoning (CBR) classification technique is applied. The second is founded on a hierarchical decomposition of the image set so that a tree representation is generated. A weighted frequent sub-graph mining technique is then applied to this representation to identify sub-trees that frequently occur across the data set. The identified sub-trees are then encoded in the form of feature vectors to which standard classification techniques can be applied.

show abstract

Section: Retinal Image Classification Using Cbr and Dtwmentioning

confidence: 99%

Data mining techniques for the screening of age-related macular degeneration

Hijazi

Coenen

Zheng

2012

Knowledge-Based Systems

Self Cite

View full text Add to dashboard Cite

show abstract

“…1[c]. Initial experiments [13], indicated that the green and saturation channels produced the best results. The green channel was thus selected as the most appropriate for retina representation using the RGB model because of its ability to show the greatest contrast compared to other colour channels, seen as essential for retinal object identification [4,32].…”

Section: Time Series Cbr For Amd Screeningmentioning

confidence: 99%

“…The green channel was thus selected as the most appropriate for retina representation using the RGB model because of its ability to show the greatest contrast compared to other colour channels, seen as essential for retinal object identification [4,32]. The saturation component was selected as this has also been shown to produce good performance in identifying AMD featured retinal images [13]. The technique described here thus considers only the green and saturation channels.…”

Section: Time Series Cbr For Amd Screeningmentioning

confidence: 99%

“…The table gives values for the specif icity, sensitivity, and accuracy recorded for each TCV. Results obtain using the above approach (columns marked CBs) were compared with results obtained using a spatialhistogram approach [15]. From the table it can be seen that the proposed approach, that is advocated in this paper, provides the best results with 80% accuracy, and an average increase of 5% over all evaluation metrics.…”

Section: Amd Screening Evaluationmentioning

confidence: 99%

See 1 more Smart Citation

Time Series Case Based Reasoning for Image Categorisation

Elsayed

Hijazi

Coenen

et al. 2011

Case-Based Reasoning Research and Development

Self Cite

View full text Add to dashboard Cite

Abstract. This paper describes an approach to Case Based Reasoning (CBR) for image categorisation. The technique is founded on a time series analysis mechanism whereby images are represented as time series (curves) and compared using time series similarity techniques. There are a number of ways in which images can be represented as time series, this paper explores two. The first considers the entire image whereby the image is represented as a sequence of histograms. The second considers a particular feature (region of interest) contained across an image collection, which can then be represented as a time series. The proposed techniques then use dynamic time warping to compare image curves contained in a case base with that representing a new image example. The focus for the work described is two medical applications: (i) retinal image screening for Age-related Macular Degeneration (AMD) and (ii) the classification of Magnetic Resonance Imaging (MRI) brain scans according to the nature of the corpus callosum, a particular tissue feature that appears in such images. The proposed technique is described in detail together with a full evaluation in terms of the two applications.

show abstract

“…The minimal warping path is computed by summing up the minimal d for each matrix grid points thus giving a distance between T andT . More details of the DTW approach with respect to retinal image classification can be found in [15].…”

Section: Retinal Image Classification Using Cbr and Dtwmentioning

confidence: 99%

Dynamic Time Warping (DTW)

장민석¹,

공성배²,

고락경³

et al.

SpringerReference

View full text Add to dashboard Cite

Age-related Macular Degeneration (AMD) is the most common cause of blindness in old-age. Early identification of AMD can allow for mitigation (but not cure). One of the fist symptoms of AMD is the presence of fatty deposits, called drusen, on the retina. The presence of drusen may be identified through inspection of retina images. Given the aging global population, the prevalence of AMD is increasing. Many health authorities therefore run screening programmes. The automation, or at least partial automation, of retina image screening is therefore seen as beneficial. This paper describes a Case Based Reasoning (CBR) approach to retina image classification to provide support for AMD screening programmes. In the proposed approach images are represented in the form of spatial-histograms that store both colour and spatial image information. Each retina image is represented using a series of histograms each encapsulated as a time series curve. The Case Base (CB) is populated with a labelled set of such curves. New cases are classified by finding the most similar case (curve) in the CB. Similarity checking is achieved using the Dynamic Time warping (DTW).

show abstract

Retinal Image Classification for the Screening of Age-Related Macular Degeneration

Cited by 23 publications

References 29 publications

Data mining techniques for the screening of age-related macular degeneration

Data mining techniques for the screening of age-related macular degeneration

Time Series Case Based Reasoning for Image Categorisation

Dynamic Time Warping (DTW)

Contact Info

Product

Resources

About