Automatic exudate extraction for early detection of Diabetic Retinopathy

Sreng, Syna; Maneerat, Noppadol; Isarakorn, Don; Pasaya, Bundit; Takada, Jun‐ichi; Panjaphongse, Ronakorn; Varakulsiripunth, Ruttikorn

doi:10.1109/iciteed.2013.6676206

Cited by 20 publications

(13 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, we employed a maximum entropy thresholding method to extract cell nuclei from CPE images which have non-uniform gray level distribution. Another motivation for using the maximum entropy method to select the optimal threshold in our study was that it has been widely and successfully used in many real applications of medical image analysis [22][23][24] Maximum entropy thresholding is one of the global thresholding methods which is proposed by Shannon in 1948, [25,26]. Similar to the Otsu method, maximum entropy thresholding selects the optimal threshold by maximizing the information measure between objects and their backgrounds.…”

Section: Nuclei Segmentationmentioning

confidence: 99%

Detection and Classification of Overlapping Cell Nuclei in Cytology Effusion Images Using a Double-Strategy Random Forest

et al. 2018

View full text Add to dashboard Cite

Due to the close resemblance between overlapping and cancerous nuclei, the misinterpretation of overlapping nuclei can affect the final decision of cancer cell detection. Thus, it is essential to detect overlapping nuclei and distinguish them from single ones for subsequent quantitative analyses. This paper presents a method for the automated detection and classification of overlapping nuclei from single nuclei appearing in cytology pleural effusion (CPE) images. The proposed system is comprised of three steps: nuclei candidate extraction, dominant feature extraction, and classification of single and overlapping nuclei. A maximum entropy thresholding method complemented by image enhancement and post-processing was employed for nuclei candidate extraction. For feature extraction, a new combination of 16 geometrical and 10 textural features was extracted from each nucleus region. A double-strategy random forest was performed as an ensemble feature selector to select the most relevant features, and an ensemble classifier to differentiate between overlapping nuclei and single ones using selected features. The proposed method was evaluated on 4000 nuclei from CPE images using various performance metrics. The results were 96.6% sensitivity, 98.7% specificity, 92.7% precision, 94.6% F1 score, 98.4% accuracy, 97.6% G-mean, and 99% area under curve. The computation time required to run the entire algorithm was just 5.17 s. The experiment results demonstrate that the proposed algorithm yields a superior performance to previous studies and other classifiers. The proposed algorithm can serve as a new supportive tool in the automated diagnosis of cancer cells from cytology images.

show abstract

Section: Nuclei Segmentationmentioning

confidence: 99%

Detection and Classification of Overlapping Cell Nuclei in Cytology Effusion Images Using a Double-Strategy Random Forest

et al. 2018

View full text Add to dashboard Cite

show abstract

“…Again, to prevent confusion with exudates, Sreng et al (2013) first detected and eliminated the optic disc through image binarization, ROI-based segmentation and morphological reconstruction. Then, the exudates were detected by applying the maximum entropy thresholding to filter out the bright pixels and finally, exudates were extracted via morphological reconstruction.…”

Section: Related Workmentioning

confidence: 99%

Segmentation of Exudates via Color-based K-means Clustering and Statistical-based Thresholding

Ghalwash¹,

Youssif²,

Allam³

2017

Journal of Computer Science

View full text Add to dashboard Cite

This paper provides a novel approach for the problem of detecting the yellowish lesions in the eye fundus images, such as hard and soft exudates, in a fully-automated manner. To solve this problem of segmenting exudates automatically, the fundus image was first converted into the L*a*b* color space to decouple the chromaticity information of the image. Next, the fundus image was partitioned into five disjoint clusters based on this information via the unsupervised kmeans algorithm. Among the clustered images, the one having the brightest average intensity was chosen to be the best cluster containing all the bright yellowish pixels. Using this cluster, a threshold value was estimated via statistic-based metrics and subsequently applied to remove any non-bright clustered pixels and preserve only the relatively bright ones within the image. Finally, the optic disc was eliminated from the thresholded image, leaving out only the bright abnormalities. This approach was evaluated over a total of 1419 images retrieved from three heterogeneous datasets: DIARETDB0, DIARETDB1 and MESSIDOR. The proposed segmentation algorithm was fullyautomated, non-customized, simple and straightforward, regardless of the heterogeneity of the datasets. The proposed system correctly detected the bright abnormalities achieving an average sensitivity and specificity of 85.08% and 56.77%, respectively.

show abstract

“…using optometric equipment in an office versus using a 20 diaptor lens with a smartphone application [5] in a rural clinic in a third-world country, etc). Although detection techniques that adapt from image to image have been attempted using techniques such as maximum entropy thresholding [2], and Otsu thresholding [3] these techniques fall short for accommodating amplitude variations within the image itself or when using the same threshold over a series of images. In fact most classical detection techniques assume that the exudates (i.e.…”

Section: Introductionmentioning

confidence: 99%

Detection of exudates in fundus imagery using a constant false-alarm rate (CFAR) detector

Khanna

Kapoor

2014

SPIE Proceedings

View full text Add to dashboard Cite

Diabetic retinopathy is the leading cause of blindness in adults in the United States. The presence of exudates in fundus imagery is the early sign of diabetic retinopathy so detection of these lesions is essential in preventing further ocular damage. In this paper we present a novel technique to automatically detect exudates in fundus imagery that is robust against spatial and temporal variations of background noise. The detection threshold is adjusted dynamically, based on the local noise statics around the pixel under test in order to maintain a pre-determined, constant false alarm rate (CFAR). The CFAR detector is often used to detect bright targets in radar imagery where the background clutter can vary considerably from scene to scene and with angle to the scene. Similarly, the CFAR detector addresses the challenge of detecting exudate lesions in RGB and multispectral fundus imagery where the background clutter often exhibits variations in brightness and texture. These variations present a challenge to common, global thresholding detection algorithms and other methods. Performance of the CFAR algorithm is tested against a publicly available, annotated, diabetic retinopathy database and preliminary testing suggests that performance of the CFAR detector proves to be superior to techniques such as Otsu thresholding.

show abstract

Automatic exudate extraction for early detection of Diabetic Retinopathy

Cited by 20 publications

References 14 publications

Detection and Classification of Overlapping Cell Nuclei in Cytology Effusion Images Using a Double-Strategy Random Forest

Detection and Classification of Overlapping Cell Nuclei in Cytology Effusion Images Using a Double-Strategy Random Forest

Segmentation of Exudates via Color-based K-means Clustering and Statistical-based Thresholding

Detection of exudates in fundus imagery using a constant false-alarm rate (CFAR) detector

Contact Info

Product

Resources

About