1 January 2020 in Medical Image Analysis
20 March 2019 in BioMedical Engineering OnLine
Most current algorithms for automatic glaucoma assessment using fundus images rely on handcrafted features based on segmentation, which are affected by the performance of the chosen segmentation method and the extracted features. Among other characteristics, convolutional neural networks (CNNs) are known because of their ability to learn highly discriminative features from raw pixel intensities. In this paper, we employed five different ImageNet-trained models (VGG16, VGG19, InceptionV3, ResNet50 and Xception) for automatic glaucoma assessment using fundus images. Results from an extensive validation using cross-validation and cross-testing strategies were compared with previous works in the literature. Using five public databases (1707 images), an average AUC of 0.9605 with a 95% confidence interval of 95.92–97.07%, an average specificity of 0.8580 and an average sensitivity of 0.9346 were obtained after using the Xception architecture, significantly improving the performance of other state-of-the-art works. Moreover, a new clinical database, ACRIMA, has been made publicly available, containing 705 labelled images. It is composed of 396 glaucomatous images and 309 normal images, which means, the largest public database for glaucoma diagnosis. The high specificity and sensitivity obtained from the proposed approach are supported by an extensive validation using not only the cross-validation strategy but also the cross-testing validation on, to the best of the authors’ knowledge, all publicly available glaucoma-labelled databases. These results suggest that using ImageNet-trained models is a robust alternative for automatic glaucoma screening system. All images, CNN weights and software used to fine-tune and test the five CNNs are publicly available, which could be used as a testbed for further comparisons.
7 March 2019 in IEEE Transactions on Medical Imaging
Recent works show that Generative Adversarial Networks (GANs) can be successfully applied to image synthesis and semi-supervised learning, where, given a small labelled database and a large unlabelled database, the goal is to train a powerful classi?er. In this paper, we trained a retinal image synthesizer and a semi-supervised learning method for automatic glaucoma assessment using an adversarial model on a small glaucoma-labelled and large unlabelled database. Various studies have shown that glaucoma can be monitored by analyzing the optic disc and its surroundings, for that reason the images used in this work were automatically cropped around the optic disc. The novelty of this work is to propose a new retinal image synthesizer and a semi-supervised learning method for glaucoma assessment based on the Deep Convolutional Generative Adversarial Networks (DCGAN). In addition, and to the best of the authors’ knowledge, this system is trained on an unprecedented number of publicly available images (86926 images). This system, hence, is not only able to generate images synthetically but to provide labels automatically. Synthetic images were qualitatively evaluated using t-SNE plots of features associated with the images and their anatomical consistency were estimated by measuring the proportion of pixels corresponding to the anatomical structures around the optic disc. The resulting image synthesizer is able to generate realistic (cropped) retinal images and, subsequently, the glaucoma classi?er is able to classify them into glaucomatous and normal with high accuracy (AUC= 0.9017). The obtained retinal image synthesizer and the glaucoma classi?er could be used then to generate an unlimited number of cropped retinal images with glaucoma labels.
15 May 2024 in Medical Image Analysis
25 January 2022 in Nature Machine Intelligence
14 December 2020 in Progress in Biomedical Engineering