Retinal Vessel Segmentation using Deep Neural Networks

Melinščak, Martina; Prentašić, Pavle; Lončarić, Sven

doi:10.5220/0005313005770582

Cited by 128 publications

(60 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here, CNNs have been used to detect bone [11]. Recently, segmentation of blood vessels has been introduced as another application of using CNNs on retinal photographs [12]. This shows that CNNs are finding increasing use in biomedical image processing applications.…”

mentioning

confidence: 99%

Using Convolutional Neural Network for edge detection in musculoskeletal ultrasound images

Jabbar

Day

Heinz

et al. 2016

2016 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

Fast and accurate segmentation of musculoskeletal ultrasound images is an on-going challenge. Two principal factors make this task difficult: firstly, the presence of speckle noise arising from the interference that accompanies all coherent imaging approaches; secondly, the sometimes subtle interaction between musculoskeletal components that leads to non-uniformity of the image intensity. Our work presents an investigation of the potential of Convolutional Neural Networks (CNNs) to address both of these problems. CNNs are an effective tool that has previously been used in image processing of several biomedical imaging modalities. However, there is little published material addressing the processing of musculoskeletal ultrasound images, particularly using a panoramic technique. In our work we explore the effectiveness of CNNs when trained to act as a pre-segmentation pixel classifier that determines whether a pixel is an edge or non-edge pixel. Our CNNs are trained using two different ground truth interpretations. The first one uses an automatic Canny edge detector to provide the ground truth image; in the second interpretation, the ground truth was obtained using the same image marked-up by an expert anatomist. In this initial study the CNNs have been trained using half of the prepared data from one image, using the other half for testing; validation was also carried out using three unseen ultrasound images. CNN performance was assessed using Mathew's Correlation Coefficient, Sensitivity, Specificity and Accuracy. The results show that CNN performance when using expert ground truth image is better than in the case of using Canny ground truth image. Our technique is promising and has the potential to speed-up the image processing pipeline using appropriately trained CNNs.

show abstract

mentioning

confidence: 99%

Using Convolutional Neural Network for edge detection in musculoskeletal ultrasound images

Jabbar

Day

Heinz

et al. 2016

2016 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

show abstract

“…Acc AUC Sens Spec Melinščak [4] 0.9466 0.9749 --Fu [5] 0.9523 -0.7603 -Li [7] 0.9527 0.9738 0.7569 0.9816 Dasgupta [8] 0.9533 0.9744 0.7691 0.9801 Yan [9] 0.9542 0.9752 0.7653 0.9818 Liskowski [10] 0.9251 0.9738 0.9160 0.9241 CapsNet [11] 0.9292 0.9638 0.7614 0.9731 Proposed 0.9547 0.9750 0.7651 0.9818 on the training images and combined the test predictions of each fold in an ensemble. We evaluated our model using the following metrics: Accuracy (Acc), Area under the curve (AUC), Sensitivity (Sens), and Specificity (Spec).…”

Section: Methodsmentioning

confidence: 99%

“…These methods outperform classical approaches based on handcrafted features and exceed human-level performance (e.g., for image classification [3]). Most methods use a CNN architecture and image patches to classify the central pixel as either vessel or background (e.g., Melinščak et al [4]). Fu et al [5] reformulated the problem of vessel segmentation as a boundary detection task using a CNN in combination with a conditional random field (CRF) to classify image patches.…”

Section: Introductionmentioning

confidence: 99%

Inception Capsule Network for Retinal Blood Vessel Segmentation and Centerline Extraction

Kromm

Rohr

2019

Preprint

View full text Add to dashboard Cite

Automatic segmentation and centerline extraction of retinal blood vessels from fundus image data is crucial for early detection of retinal diseases. We have developed a novel deep learning method for segmentation and centerline extraction of retinal blood vessels which is based on the Capsule network in combination with the Inception architecture. Compared to state-of-the-art deep convolutional neural networks, our method has much fewer parameters due to its shallow architecture and generalizes well without using data augmentation. We performed a quantitative evaluation using the DRIVE dataset for both vessel segmentation and centerline extraction. Our method achieved state-of-the-art performance for vessel segmentation and outperformed existing methods for centerline extraction.

show abstract

“…Convolutional neural networks (CNNs) are widely used approaches in deep learning and are applicable in diverse image processing problems. Works of [22][23][24][25] are recent researches using deep neural networks for segmentation of medical images. In [22] and [23] CNN is used for segmentation of vessels in fundus images and X-ray angiogram.…”

mentioning

confidence: 99%

“…Works of [22][23][24][25] are recent researches using deep neural networks for segmentation of medical images. In [22] and [23] CNN is used for segmentation of vessels in fundus images and X-ray angiogram. Works of [24] and [25] have used CNNs for segmentation of brain tumors.…”

mentioning

confidence: 99%

Extraction of skin lesions from non-dermoscopic images for surgical excision of melanoma

et al. 2017

View full text Add to dashboard Cite

Abstract-Melanoma is amongst most aggressive types of cancer. However, it is highly curable if detected in its early stages. Prescreening of suspicious moles and lesions for malignancy is of great importance. Detection can be done by images captured by standard cameras, which are more preferable due to low cost and availability. One important step in computerized evaluation of skin lesions is accurate detection of lesion's region, i.e. segmentation of an image into two regions as lesion and normal skin. Accurate segmentation can be challenging due to burdens such as illumination variation and low contrast between lesion and healthy skin. In this paper, a method based on deep neural networks is proposed for accurate extraction of a lesion region. The input image is preprocessed and then its patches are fed to a convolutional neural network (CNN). Local texture and global structure of the patches are processed in order to assign pixels to lesion or normal classes. A method for effective selection of training patches is used for more accurate detection of a lesion's border. The output segmentation mask is refined by some post processing operations. The experimental results of qualitative and quantitative evaluations demonstrate that our method can outperform other state-of-the-art algorithms exist in the literature.Index Terms-Convolutional neural network, deep learning, medical image segmentation, melanoma, skin cancer.

show abstract

Retinal Vessel Segmentation using Deep Neural Networks

Cited by 128 publications

References 21 publications

Using Convolutional Neural Network for edge detection in musculoskeletal ultrasound images

Using Convolutional Neural Network for edge detection in musculoskeletal ultrasound images

Inception Capsule Network for Retinal Blood Vessel Segmentation and Centerline Extraction

Extraction of skin lesions from non-dermoscopic images for surgical excision of melanoma

Contact Info

Product

Resources

About