Deep multi-instance heatmap regression for the detection of retinal vessel crossings and bifurcations in eye fundus images. (April 2020)

• Record Type: Journal Article
• Authors: Hervella, Álvaro S.; Rouco, José; Novo, Jorge; Penedo, Manuel G.; Ortega, Marcos
• Is Part Of: Computer methods and programs in biomedicine. Volume 186(2020)
• Publication Date: 2020-04
• Subjects: Deep learning -- Eye fundus -- Blood vessels -- Crossings -- Bifurcations -- Landmark detection; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2019.105201
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: The proposed multi-instance heatmap regression allows to successfully take advantage of modern deep learning algorithms. A deep neural network predicts the vessel crossings and bifurcations likelihood maps from the raw eye fundus images. The presented approach integrates into a single step the detection and distinction of the vascular landmarks. The evaluation on two public datasets shows a satisfactory performance and a significant improvent over previous state-of-the-art methods. Abstract: Background and objectives: The analysis of the retinal vasculature plays an important role in the diagnosis of many ocular and systemic diseases. In this context, the accurate detection of the vessel crossings and bifurcations is an important requirement for the automated extraction of relevant biomarkers. In that regard, we propose a novel approach that addresses the simultaneous detection of vessel crossings and bifurcations in eye fundus images. Method: We propose to formulate the detection of vessel crossings and bifurcations in eye fundus images as a multi-instance heatmap regression. In particular, a deep neural network is trained in the prediction of multi-instance heatmaps that model the likelihood of a pixel being a landmark location. This novel approach allows to make predictions using full images and integrates into a single step the detection and distinction of the vascular landmarks. Results: The proposed method is validated on two public datasets of reference that include detailed annotations for vessel crossings and bifurcations in eye fundus images. The conducted experiments evidence that the proposed method offers a satisfactory performance. In particular, the proposed method achieves 74.23% and 70.90% F-score for the detection of crossings and bifurcations, respectively, in color fundus images. Furthermore, the proposed method outperforms previous works by a significant margin. Conclusions : The proposed multi-instance heatmap regression allows to successfully exploit the potential of modern deep learning algorithms for the simultaneous detection of retinal vessel crossings and bifurcations. Consequently, this results in a significant improvement over previous methods, which will further facilitate the automated analysis of the retinal vasculature in many pathological conditions.