Automatic segmentation of optic disc in retinal fundus images using semi-supervised deep learning
- PDF / 6,081,014 Bytes
- 26 Pages / 439.642 x 666.49 pts Page_size
- 45 Downloads / 288 Views
Automatic segmentation of optic disc in retinal fundus images using semi-supervised deep learning Shaleen Bengani1 · Angel Arul Jothi J.1
· Vadivel S.1
Received: 12 June 2019 / Revised: 26 August 2020 / Accepted: 28 August 2020 / © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Diseases of the eye require manual segmentation and examination of the optic disc by ophthalmologists. Though, image segmentation using deep learning techniques is achieving remarkable results, it leverages on large-scale labeled datasets. But, in the field of medical imaging, it is challenging to acquire large labeled datasets. Hence, this article proposes a novel deep learning model to automatically segment the optic disc in retinal fundus images by using the concepts of semi-supervised learning and transfer learning. Initially, a convolutional autoencoder (CAE) is trained to automatically learn features from a large number of unlabeled fundus images available from the Kaggle’s diabetic retinopathy (DR) dataset. The autoencoder (AE) learns the features from the unlabeled images by reconstructing the input images and becomes a pre-trained network (model). After this, the pre-trained autoencoder network is converted into a segmentation network. Later, using transfer learning, the segmentation network is trained with retinal fundus images along with their corresponding optic disc ground truth images from the DRISHTI GS1 and RIM-ONE datasets. The trained segmentation network is then tested on retinal fundus images from the test set of DRISHTI GS1 and RIM-ONE datasets. The experimental results show that the proposed method performs on par with the state-of-the-art methods achieving a 0.967 and 0.902 dice score coefficient on the test set of the DRISHTI GS1 and RIM-ONE datasets respectively. The proposed method also shows that transfer learning and semi-supervised learning overcomes the barrier imposed by the large labeled dataset. The proposed segmentation model can be used in automatic retinal image processing systems for diagnosing diseases of the eye. Keywords Deep learning · Autoencoder · Semi-supervised learning · Convolutional neural network · Transfer learning · Segmentation · Optic disc Angel Arul Jothi J.
[email protected] Shaleen Bengani [email protected] Vadivel S. [email protected] 1
Department of Computer Science, Birla Institute of Technology and Science Pilani, Dubai Campus, Dubai, UAE
Multimedia Tools and Applications
1 Introduction Retinal images are used by ophthalmologists for screening, diagnosis and treatment of diseases of the eye like diabetic retinopathy and glaucoma. These diseases are becoming increasingly common and leads to complete vision loss if untreated. Despite being useful in diagnosing eye related diseases, literature has shown that retinal images can also be used as an indicator for assessing other medical conditions like cardiovascular disease, hypertension, stroke and multiple sclerosis. A retinal fundus image is a 2D image of the
Data Loading...
