Optimized clinical segmentation of retinal blood vessels by using combination of adaptive filtering, fuzzy entropy and skeletonization

Rezaee, Khosro; Haddadnia, Javad; Tashk, Ashkan

doi:10.1016/j.asoc.2016.09.033

Cited by 58 publications

(20 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Pada penelitian [6] segmentasi pembuluh darah dibagi menjadi 4 bagian yaitu pembuluh darah utama, medium, tipis, dan bukan pembuluh darah dengan jumlah threshold n-1 level segmen atau kelas. Maka pada penelitian juga membagi kategori pembuluh darah dengan jumlah yang sama dengan nilai input NThreshold = 3.…”

Section: Fuzzy Entropyunclassified

See 1 more Smart Citation

Perbaikan Segmentasi Pembuluh Darah Tipis Pada Citra Retina Menggunakan Fuzzy Entropy

Farosanti

Fatichah

2019

JUTI

View full text Add to dashboard Cite

2) ABSTRAK Diabetic Retinopathy adalah kelainan pembuluh darah retina pada mata yang diakibatkan komplikasi penyakit diabetes. Deteksi lebih dini diperlukan agar kelainan ini dapat ditangani secara cepat dan tepat. Kelainan ini ditandai dengan melemahnya bagian pembuluh darah tipis akibat tersumbatnya aliran darah kemudian menyebabkan bengkak pada mata bahkan kebutaan. Oleh karena itu diperlukan analisis pembuluh darah retina melalui proses segmentasi pembuluh darah terutama pada bagian penting yaitu pembuluh darah tipis. Peneliti mengusulkan penggabungan metode perbaikan pembuluh darah tipis atau Thin Vessel Enhancement dengan Fuzzy Entropy. Thin Vessel Enhancement berfungsi untuk memperbaiki citra agar dapat mengekstrak lebih banyak bagian pembuluh darah khususnya pembuluh darah tipis, sedangkan Fuzzy Entropy dapat menentukan nilai optimal threshold berdasarkan nilai entropy pada suatu level segmen atau kelas. Segmentasi yang dihasilkan dibagi menjadi 3 kategori yaitu pembuluh darah utama, medium, dan tipis. Uji coba dilakukan terhadap metode Thin Vessel Enhancement menggunakan 1 kernel dan Fuzzy Entropy dari nilai threshold ke-1 maka diperoleh nilai accuracy, sensitivity, dan specificity sebesar 94.81%, 66.83%, dan 97.51%.

show abstract

Section: Fuzzy Entropyunclassified

“…Segmentasi pembuluh darah pada penelitian [6] menggunakan metode Adaptive Filtering, Fuzzy Entropy, dan Skeletonization. Fuzzy Entropy dapat menghasilkan nilai optimum threshold berdasarkan nilai entropy pada masing-masing membership function.…”

unclassified

Perbaikan Segmentasi Pembuluh Darah Tipis Pada Citra Retina Menggunakan Fuzzy Entropy

Farosanti

Fatichah

2019

JUTI

View full text Add to dashboard Cite

show abstract

“…These features are calculated for angles of 0, 45, 90, and 135. Many histopatological cell detection methods employ local binary pattern (LBP)-based texture features [32][33][34] which are robust against illumination changes. Therefore to have a robust feature set, LBP-based features have been used in this work in which LBP operator is applied on gray scale image before calculating GLCM features.…”

Section: Feature Extractionmentioning

confidence: 99%

An Automatic and Robust Decision Support System for Accurate Acute Leukemia Diagnosis from Blood Microscopic Images

2018

View full text Add to dashboard Cite

This paper proposes an automatic and robust decision support system for accurate acute leukemia diagnosis from blood microscopic images. It is a challenging issue to segment leukocytes under uneven imaging conditions since features of microscopic leukocyte images change in different laboratories. Therefore, this paper introduces an automatic robust method to segment leukocyte from blood microscopic images. The proposed robust segmentation technique was designed based on the fact that if background and erythrocytes could be removed from the blood microscopic image, the remainder area will indicate leukocyte candidate regions. A new set of features based on hematologist visual criteria for the recognition of malignant leukocytes in blood samples comprising shape, color, and LBP-based texture features are extracted. Two new ensemble classifiers are proposed for healthy and malignant leukocytes classification which each of them is highly effective in different levels of analysis. Experimental results demonstrate that the proposed approach effectively segments leukocytes from various types of blood microscopic images. The proposed method performs better than other available methods in terms of robustness and accuracy. The final accuracy rate achieved by the proposed method is 98.10% in cell level. To the best of our knowledge, the image level test for acute lymphoblastic leukemia (ALL) recognition was performed on the proposed system for the first time that achieves the best accuracy rate of 89.81%.

show abstract

“…In recent years, researches have been used unsupervised methods, supervised methods and other methods, such as: salient region [11][12][13][14][15], referee and fluorescein [16], probabilistic formulation [17], classification [18], transform [19], the feature and ensemble learning [20], saliency filter or adaptive between them [21,22], texture [23], etc. to segment the retinal blood vessels.…”

Section: Introductionmentioning

confidence: 99%

Improving Retinal Vessels Segmentation via Deep Learning in Salient Region

Tuyet

Binh

2020

SN COMPUT. SCI.

View full text Add to dashboard Cite

Retinal vessels segmentation is one of the hard tasks. Because it may cause loss of information in the image. Therefore, the features of retinal vessel must be taken care of properly. Deep learning gives the positive results for features extraction. The retinal vessel segmentation really needs to be based on these features. Information in retina is also vital for the health status of citizen. However, the using deep learning combined with salient region will increase the accuracy of saliency. The number of parameters and size for dividing level in each input images make pixels decrease linking. This paper proposed a new method for retinal vessels segmentation based on deep learning in edge map which is created by salient map. The proposed method has three periods: edges salient map in the retinal vessel image, features extraction by convolutional neural network in salient map and segmentation based on pixel level of Sobel operator in saliency. To evaluate the results of proposed method with the other methods, we use the DRIVE dataset through the Jaccard index value. The experiments show that the JI value of the proposed method is higher than the results in other methods.

show abstract

Optimized clinical segmentation of retinal blood vessels by using combination of adaptive filtering, fuzzy entropy and skeletonization

Cited by 58 publications

References 37 publications

Perbaikan Segmentasi Pembuluh Darah Tipis Pada Citra Retina Menggunakan Fuzzy Entropy

Perbaikan Segmentasi Pembuluh Darah Tipis Pada Citra Retina Menggunakan Fuzzy Entropy

An Automatic and Robust Decision Support System for Accurate Acute Leukemia Diagnosis from Blood Microscopic Images

Improving Retinal Vessels Segmentation via Deep Learning in Salient Region

Contact Info

Product

Resources

About