Deep Bayesian baseline for segmenting diabetic retinopathy lesions: Advances and challenges. (September 2021)

• Record Type: Journal Article
• Authors: Garifullin, Azat; Lensu, Lasse; Uusitalo, Hannu
• Is Part Of: Computers in biology and medicine. Volume 136(2021)
• Publication Date: 2021-09
• Subjects: Bayesian deep learning -- Diabetic retinopathy -- Lesion segmentation -- Microaneurysm -- Hard exudate -- Soft exudate -- Haemorrhage; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2021.104725
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Early diagnosis of retinopathy is essential for preventing retinal complications and visual impairment due to diabetes. For the detection of retinopathy lesions from retinal images, several automatic approaches based on deep neural networks have been developed in the recent years. Most of the proposed methods produce point estimates of pixels belonging to the lesion areas and give no or little information on the uncertainty of method predictions. However, the latter can be essential in the examination of the medical condition of the patient when the goal is early detection of abnormalities. This work extends the recent research with a Bayesian framework by considering the parameters of a convolutional neural network as random variables and utilizing stochastic variational dropout based approximation for uncertainty quantification. The framework includes an extended validation procedure and it allows analyzing lesion segmentation distributions, model calibration and prediction uncertainties. Also the challenges related to the deep probabilistic model and uncertainty quantification are presented. The proposed method achieves area under precision-recall curve of 0.84 for hard exudates, 0.641 for soft exudates, 0.593 for haemorrhages, and 0.484 for microaneurysms on IDRiD dataset. Highlights: A novel Bayesian baseline for segmenting diabetic retinopathy lesions. An assessment and analysis of model calibration and prediction uncertainties. The presentation of an extended validation procedure for DR lesion segmentation taskbeyond the point estimates.