A review of machine learning methods for retinal blood vessel segmentation and artery/vein classification

Mookiah, Muthu Rama Krishnan; Hogg, Stephen; MacGillivray, Tom; Prathiba, Vijayaraghavan; Pradeepa, Rajendra; Mohan, Viswanathan; Doney, Alex S.F.; Palmer, Colin N.A.; Trucco, Emanuele

doi:10.1016/j.media.2020.101905

Cited by 118 publications

(60 citation statements)

References 201 publications

(123 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…There are many publicly available databases for retinal vessel segmentation [10]. Here we just introduce several main databases.…”

Section: Database and Evaluation Metrics For Retinal Vessel Segmentationmentioning

confidence: 99%

“…Several supervised and unsupervised methods are developed and used to automate the segmentation of retinal vessels. Earlier, unsupervised methods are the most common approach for automatically segmenting the retinal vessels, which do not rely on any annotation for segmentation [9,10]. These methods are roughly divided into matching filter [11][12][13], vascular tracing based segmentation [14][15][16] and modelbased segmentation methods [17].…”

Section: Introductionmentioning

confidence: 99%

“…Several review articles on retinal blood vessel segmentation have been published [10,[27][28][29][30]. However, Mookiah, et al [10], Khan, et al [28], Badar, et al [29], Li, et al [30] did not focus on deep learning methods for vessel segmentation, whereas the techniques discussed in Soomro, et al [27] are published several years ago. Therefore, in this review article, we discussed publications of recent six years for retinal blood vessel segmentation based on deep learning.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Retinal Vessel Segmentation Using Deep Learning: A Review

et al. 2021

View full text Add to dashboard Cite

This paper presents a comprehensive review of retinal blood vessel segmentation based on deep learning. The geometric characteristics of retinal vessels reflect the health status of patients and help to diagnose some diseases such as diabetes and hypertension. The accurate diagnosis and timing treatment of these diseases can prevent global blindness of patients. Recently, deep learning algorithms have been rapidly applied to retinal vessel segmentation due to their higher efficiency and accuracy, when compared with manual segmentation and other computer-aided diagnosis techniques. In this work, we reviewed recent publications for retinal vessel segmentation based on deep learning. We surveyed these proposed methods especially the network architectures and figured out the trend of models. We summarized obstacles and key aspects for applying deep learning to retinal vessel segmentation and indicated future research directions. This article will help researchers to construct more advanced and robust models.INDEX TERMS Retinal vessel segmentation, fundus images, deep learning, convolutional neural network.

show abstract

“…There are many publicly available databases for retinal vessel segmentation [10]. Here we just introduce several main databases.…”

Section: Database and Evaluation Metrics For Retinal Vessel Segmentationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Retinal Vessel Segmentation Using Deep Learning: A Review

et al. 2021

View full text Add to dashboard Cite

show abstract

“…However, the monitoring of DR is executed manually which is time consuming. The automated screening of DR can overcome the manual screening that can filter out healthy obvious samples and indicates only suspected cases to ophthalmologists [ 7 , 8 ].…”

Section: Introductionmentioning

confidence: 99%

Hemorrhage Detection Based on 3D CNN Deep Learning Framework and Feature Fusion for Evaluating Retinal Abnormality in Diabetic Patients

Maqsood

Damaševičius

Maskeliūnas

2021

Sensors

View full text Add to dashboard Cite

Diabetic retinopathy (DR) is the main cause of blindness in diabetic patients. Early and accurate diagnosis can improve the analysis and prognosis of the disease. One of the earliest symptoms of DR are the hemorrhages in the retina. Therefore, we propose a new method for accurate hemorrhage detection from the retinal fundus images. First, the proposed method uses the modified contrast enhancement method to improve the edge details from the input retinal fundus images. In the second stage, a new convolutional neural network (CNN) architecture is proposed to detect hemorrhages. A modified pre-trained CNN model is used to extract features from the detected hemorrhages. In the third stage, all extracted feature vectors are fused using the convolutional sparse image decomposition method, and finally, the best features are selected by using the multi-logistic regression controlled entropy variance approach. The proposed method is evaluated on 1509 images from HRF, DRIVE, STARE, MESSIDOR, DIARETDB0, and DIARETDB1 databases and achieves the average accuracy of 97.71%, which is superior to the previous works. Moreover, the proposed hemorrhage detection system attains better performance, in terms of visual quality and quantitative analysis with high accuracy, in comparison with the state-of-the-art methods.

show abstract

“…Evrişimli sinir agının çok katmanlı özellik çıkarımı ,görüntü üzerie uygulanan farklı filtreler ile, agın katmanları boyunca taşınan öz niteliklerinden görüntü ile ilgili önemli özelliklerin ortaya çıkarılmasını saglamaktadır. Derin ögrenmedeki bu gelişim, hücre ve damar görüntülerin bölütlenmesine uyarlanmıştır [3], [4]. Genel olarak biyomedikal görüntülerin analizinde, yüksek başarım oranında bölütleme sonucu veren bir derin sinir agı modeli olan U-Net modelinin kullanıldıgı görülmektedir [5], [6].…”

Section: Introductionunclassified

Medical Image Segmentation Using Deep Neural Networks

Aydin¹

2021

2021 29th Signal Processing and Communications Applications Conference (SIU)

View full text Add to dashboard Cite

Özetçe -Medikal görüntülerin otomatik bölütlenmesi, bu görüntüler kullanılarak çeşitli hastalıkların teşhis edilmesinde önemli bir rol oynamaktadır. Görüntü bölütleme, bir çok medikal görüntüye ayrı ayrı uygulanarak farklı analizlerin ve teşhislerin yapılması saglanabilmektedir. Örnegin, bir hücre kültüründeki hücrelerin otomatik bölütlenmesi ile, hücrelerin miktarı, canlılıgı, her bir hücrenin çapı veyaşeklinin ayrı ayrı analiz edilmesi saglanabilmektedir. Ayrıca bir dokudaki kan damarlarının otomatik bölütlenmesi ile, damarların uzunlugu, yogunlugu, her damarın ayrı ayrı yarı çapı gibi analizler yapılabilmektedir. Bu sayede incelen görüntüden, bir hastalıgın erken teşhisi, hastalıgın türü gibi çıkarımlar gerçekleştirilir. Bu çalışmada çeşitli hücre görüntülerinden ve retina görüntülerinden oluşan iki ayrı veri seti kullanılarak, bu veri setindeki görüntüler ayrı ayrı bölütlenmiştir. Otomatik bölütleme için, bir evrişimsel sinir agı modeli olan U-Net kullanılmış ve gerçek referans degerler ile U-Net agı ile bölütlenen çıktılar karşılaştırılmıştır. Her iki veri seti için elde edilen yüzdesel dogruluk degerleri sırası ile; retina veri seti için 95.2, hücre veri seti için 97.25 olarak hesaplanmıştır.

show abstract

A review of machine learning methods for retinal blood vessel segmentation and artery/vein classification

Cited by 118 publications

References 201 publications

Retinal Vessel Segmentation Using Deep Learning: A Review

Retinal Vessel Segmentation Using Deep Learning: A Review

Hemorrhage Detection Based on 3D CNN Deep Learning Framework and Feature Fusion for Evaluating Retinal Abnormality in Diabetic Patients

Medical Image Segmentation Using Deep Neural Networks

Contact Info

Product

Resources

About