Evaluation of feature sensitivity to training data inaccuracy in detection of retinal lesions

Laaksonen, Lauri; Hannuksela, Antti; Claridge, Ela; Fält, Pauli; Hauta-Kasari, Markku; Uusitalo, Hannu; Lensu, Lasse

doi:10.1109/ipta.2016.7820975

Cited by 2 publications

(4 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Morphological operations, like mean shift, normalized cut, and cannys, have presented better performance in EX extraction [103]. Several machine learning principles have shown better sensitivity results for EX segmentation [104][105][106][107][108][109][110][111]. Fraz et al in [104] applied morphological reconstruction and a Gabor filter for EX candidate extraction using 498 images.…”

Section: Exudate Detection Methodsmentioning

confidence: 99%

“…Ground truth data usually have an inaccuracy problem that directly affects the final classification output of an algorithm. Therefore, in a previous study [109], image features were evaluated for the elimination of inaccuracy in clinical data and the segmentation of exudates. Pereira et al in [110] utilized an ant colony optimization (ACO) technique to extract EX edges using 169 low contrast images.…”

Section: Exudate Detection Methodsmentioning

confidence: 99%

“…Gargeya et al [114] also proposed a deep learning model for the grading of DR and no-DR cases. Their model evaluated the color features of 75,137 images obtained from the MESSIDOR2 and e-OPTHA datasets and achieved an AUC of 0.94 and Despite the highly significant results of the EX detection methods in [96][97][98][99][100][101][102][103][104][105][106][107][108][109][110][111], some weaknesses exist that need to be addressed in the future to provide the best possible EX detection systems: (I) Most methods were evaluated on small datasets, which limit theirs performance ability to detect other pathological features, e.g., dark lesions; (II) only bright lesions, i.e., EXs were detected followed by preprocessing steps, which is expensive in terms of processing; (III) high accuracy was achieved at the cost of a low SE rate; and (IV) it is difficult to detect EXs in low contrast areas.…”

Section: Diabetic Retinopathy Detection Systemsmentioning

confidence: 99%

See 2 more Smart Citations

Recent Development on Detection Methods for the Diagnosis of Diabetic Retinopathy

Qureshi

Abbas

2019

Symmetry

View full text Add to dashboard Cite

Diabetic retinopathy (DR) is a complication of diabetes that exists throughout the world. DR occurs due to a high ratio of glucose in the blood, which causes alterations in the retinal microvasculature. Without preemptive symptoms of DR, it leads to complete vision loss. However, early screening through computer-assisted diagnosis (CAD) tools and proper treatment have the ability to control the prevalence of DR. Manual inspection of morphological changes in retinal anatomic parts are tedious and challenging tasks. Therefore, many CAD systems were developed in the past to assist ophthalmologists for observing inter- and intra-variations. In this paper, a recent review of state-of-the-art CAD systems for diagnosis of DR is presented. We describe all those CAD systems that have been developed by various computational intelligence and image processing techniques. The limitations and future trends of current CAD systems are also described in detail to help researchers. Moreover, potential CAD systems are also compared in terms of statistical parameters to quantitatively evaluate them. The comparison results indicate that there is still a need for accurate development of CAD systems to assist in the clinical diagnosis of diabetic retinopathy.

show abstract

Section: Exudate Detection Methodsmentioning

confidence: 99%

Section: Exudate Detection Methodsmentioning

confidence: 99%

Section: Diabetic Retinopathy Detection Systemsmentioning

confidence: 99%

See 1 more Smart Citation

Recent Development on Detection Methods for the Diagnosis of Diabetic Retinopathy

Qureshi

Abbas

2019

Symmetry

View full text Add to dashboard Cite

show abstract

“…The system RetCam 3 is primarily intended for the retinopathy diagnostic of the prematurely born infants because it is possible to do screening after two weeks from born (Laaksonen et al, 2016;Xiao et al, 2017). A high risk of the ROP is on newborn with a weight under 1,000 g. By the international standards, each child with a lower weight than 1,500 g should be examined on this disease (Nugroho et al, 2016).…”

Section: Introductionmentioning

confidence: 99%

Modelling and time evaluation of optical disc and retinal lesions

Kubíček¹,

Timkovič²,

Penhaker³

et al. 2018

IJDET

View full text Add to dashboard Cite

In the clinical ophthalmology, the retinal image analysis is a routine procedure with a target of the time considering the retinal lesions over the time. Unfortunately, there is an absence of the clinical software instruments providing a precise tracking the retinal lesions from the image records. Thus, the retinal image analysis is carried out by skilled physicians, but without any objective software feedback. We aim to propose a procedure having ambitions to an automatic and autonomous extraction of the retinal lesion from the retinal images, and its time evaluation. The retinal lesions are considered on a base of the optical disc which is simultaneously segmented from the retinal images. It is clinically supposed that the optical disc has stable geometrical features over the time contrarily geometrical features of the retinal lesions are timedeveloped. The proposed methodology for a time modelling of the retinal lesions comprises three essential procedures. The optical disc and the retinal lesions segmentation on a base of the time evolving curves ensure indication areas of these retinal objects. Consequently, the binary classification is used with a target of an extraction of a respective model of the optical disc and the retinal lesions.

show abstract

Evaluation of feature sensitivity to training data inaccuracy in detection of retinal lesions

Cited by 2 publications

References 19 publications

Recent Development on Detection Methods for the Diagnosis of Diabetic Retinopathy

Recent Development on Detection Methods for the Diagnosis of Diabetic Retinopathy

Modelling and time evaluation of optical disc and retinal lesions

Contact Info

Product

Resources

About