Wyniki wyszukiwania - Biblioteka Nauki

Nowa wersja platformy, zawierająca wyłącznie zasoby pełnotekstowe, jest już dostępna.
Przejdź na https://bibliotekanauki.pl

Ograniczanie wyników

2 Biocybernetics and Biomedical Engineering

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: hard exudates

Sortuj według:

Ogranicz wyniki do:

Detection of hard exudates using mean shift and normalized cut method

100%

Banerjee S. , Kayal D.

Biocybernetics and Biomedical Engineering

2016

tom Vol. 36, no. 4

679--685

As diabetic retinopathy (DR) is one of the main causes of loss of vision among diabetic patients, an early detection using automated detection techniques can prevent blindness among diabetic patients. Hard exudates constitute one of the early symptoms of DR and this paper describes a method for its detection using fundus images of retina, employing a combination of morphological operations, mean shift (MS), normalized cut (NC) and Canny's operation. This combined technique avoids over segmentation and at the same time reduces the time complexity while clearly delineating the exudates. Output of the proposed method is evaluated using public databases and produces sensitivity, specificity and accuracy as 98.80%, 98.25% and 98.65%, respectively. The ROC curve gives 0.984 as area under curve. The sensitivity, specificity, accuracy and area under curve of ROC indicate the effectiveness of the method.

Modified U-Net architecture for semantic segmentation of diabetic retinopathy images

100%

Sambyal N. , Saini P. , Syal R. , Gupta V.

Biocybernetics and Biomedical Engineering

2020

tom Vol. 40, no. 3

1094--1109

Segmentation of lesions from fundus images is an essential prerequisite for accurate severity assessment of diabetic retinopathy. Due to variation in morphologies, number and size of lesions, the manual grading process becomes extremely challenging and time-consuming. This necessitates the need of an automatic segmentation system that can precisely define the region of interest boundaries and assist ophthalmologists in speedy diagnosis along with diabetic retinopathy severity grading. The paper presents a modified U-Net architecture based on residual network and employs periodic shuffling with sub-pixel convolution initialized to convolution nearest neighbour resize. The proposed architecture has been trained and validated for microaneurysm and hard exudate segmentation on two publicly available datasets namely IDRiD and e-ophtha. For IDRiD dataset, the network obtains 99.88% accuracy, 99.85% sensitivity, 99.95% specificity and dice score of 0.9998 for both microaneurysm and exudate segmentation. Further, when trained on e-ophtha and validated on IDRiD dataset, the network shows 99.98% accuracy, 99.88% sensitivity, 99.89% specificity and dice score of 0.9998 for microaneurysm segmentation. For exudates segmen-tation, the model obtained 99.98% accuracy, 99.88% sensitivity, 99.89% specificity and dice score of 0.9999, when trained on e-ophtha and validated on IDRiD dataset. In comparison to existing literature, the proposed model provides state-of-the-art results for retinal lesion segmentation.