In-Depth Evaluation of Saliency Maps for Interpreting Convolutional Neural Network Decisions in the Diagnosis of Glaucoma Based on Fundus Imaging.

Glaucoma, a leading cause of blindness, damages the optic nerve, making early diagnosis challenging due to no initial symptoms. Fundus eye images taken with a non-mydriatic retinograph help diagnose glaucoma by revealing structural changes, including the optic disc and cup. This research aims to thoroughly analyze saliency maps in interpreting convolutional neural network decisions for diagnosing glaucoma from fundus images. These maps highlight the most influential image regions guiding the network's decisions. Various network architectures were trained and tested on 739 optic nerve head images, with nine saliency methods used. Some other popular datasets were also used for further validation. The results reveal disparities among saliency maps, with some consensus between the folds corresponding to the same architecture. Concerning the significance of optic disc sectors, there is generally a lack of agreement with standard medical criteria. The background, nasal, and temporal sectors emerge as particularly influential for neural network decisions, showing a likelihood of being the most relevant ranging from 14.55% to 28.16% on average across all evaluated datasets. We can conclude that saliency maps are usually difficult to interpret and even the areas indicated as the most relevant can be very unintuitive. Therefore, its usefulness as an explanatory tool may be compromised, at least in problems such as the one addressed in this study, where the features defining the model prediction are generally not consistently reflected in relevant regions of the saliency maps, and they even cannot always be related to those used as medical standards.

Contrast based circular approximation for accurate and robust optic disc segmentation in retinal images.

A new method for automatic optic disc localization and segmentation is presented. The localization procedure combines vascular and brightness information to provide the best estimate of the optic disc center which is the starting point for the segmentation algorithm. A detection rate of 99.58% and 100% was achieved for the Messidor and ONHSD databases, respectively. A simple circular approximation to the optic disc boundary is proposed based on the maximum average contrast between the inner and outer ring of a circle centered on the estimated location. An average overlap coefficient of 0.890 and 0.865 was achieved for the same datasets, outperforming other state of the art methods. The results obtained confirm the advantages of using a simple circular model under non-ideal conditions as opposed to more complex deformable models.

Diagnostic ability of a new method for measuring haemoglobin levels in the optic nerve head in multiple sclerosis patients.

AIMS: To evaluate a new method for measuring haemoglobin (Hb) levels and quantifying the colour changes in the optic nerve head of multiple sclerosis (MS) patients to detect axonal loss and consequently optic disc atrophy. MATERIAL AND METHODS: 40 MS patients and 40 age and sex-matched healthy subjects were included in this prospective cross-sectional study and underwent a full ophthalmological examination, including three photographs of the optic disc. The Laguna ONhE ('optic nerve hemoglobin'; Insoft SL, Tenerife, Spain) software was used to obtain the Hb analysis in each of the 24 sectors and average Hb of optic disc photographs acquired. Reproducibility of measurements provided by Laguna ONhE program was analysed. RESULTS: MS patients showed significant reduction of optic disc Hb percentages in average Hb (58.99% in MS, 65.39% in healthy subjects; p<0.001) and in almost all analysed sectors with the largest differences in temporal sectors. Laguna ONhE program showed good reproducibility measuring Hb percentages in MS patients and healthy subjects. CONCLUSIONS: Measurements of optic disc Hb levels obtained with Laguna ONhE software had good ability detecting optic atrophy and axonal loss in MS patients. This method had good reliability and is easy to implement in routine clinical practice.