Abstract
The tortuosity assessment of vessels and nerve fibres in ophthalmic images has drawn substantial attention, for its potentials in assisting various medical diagnoses. Numerous morphological tortuosity measures have been leveraged to quantify tortuosity from various perspectives, which warrants the simultaneous use of multiple measures with an aim to produce a robust and accurate assessment. This paper proposes an approach for the automated assessment of curvilinear structures’ tortuosity. Starting with the generation of clusters of tortuosity density for each individual measure, labelled fuzzy sets are then extracted that enhances the readability of subsequent operations. Finally, results from multiple measures are aggregated by a nearest neighbour guided approach where weights are generated in a data-driven manner to explain the derived aggregations. Experimental results on both ophthalmic vessel and nerve images demonstrate the superior performance of the proposed method over those where measurements are used independently or aggregated using conventional averaging operators.
Highlights
The variations of retinal vessels and corneal nerves in ophthalmic images that may indicate several eye diseases and complications are commonly assessed for clinical decision support
This paper proposes an automated pipeline for the ranking and grading of ophthalmic images based on the tortuosity of curvilinear structures, whereby multiple morphological measurements are aggregated to form a robust overall assessment
Many tortuosity measures involve the use of curvature K, which is a metric for the directional change of a unit tangent vector along the investigated curve such as the corneal nerve and retinal vessel
Summary
The variations of retinal vessels and corneal nerves in ophthalmic images that may indicate several eye diseases and complications are commonly assessed for clinical decision support. The concurrent use of multiple measures may avoid bias arising from that of any particular tortuosity measure Inspired by this observation, this paper proposes an automated pipeline for the ranking and grading of ophthalmic images based on the tortuosity of curvilinear structures, whereby multiple morphological measurements are aggregated to form a robust overall assessment. The resultant fuzzy sets of multiple tortuosity measures are aggregated through the k Nearest Neighbours-guided Dependent Ordered Weighted Averaging (kNN-DOWA) operator Experimental results on both in-house and public data sets show that the proposed aggregation process can improve the accuracy and robustness of tortuosity assessment while the weights of different measures can be harnessed to explain the significance of individual measures, which in turn facilitate clinical decision support.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
