Microaneurysms detection in color fundus images using machine learning based on directional local contrast

Table 3 Comparison of sensitivity at different FPI values for different MA detection methods on e-ophtha MA database

Methods	Highlights	Sensitivity under different FPI values							Scores
Methods	Highlights	\(\frac{{1}}{{8}}\)	\(\frac{{1}}{{4}}\)	\(\frac{{1}}{{2}}\)	1	2	4	8	Scores
Eftekhari [8]	2-step CNN	0.091	0.258	0.401	0.534	0.579	0.667	0.771	0.471
Veiga [39]	Laws texture masks, SVM	0.110	0.152	0.222	0.307	0.383	0.494	0.629	0.328
Orlando [42]	CNN-based features, RF	0.14	0.20	0.23	0.37	0.45	0.52	0.62	0.361
Wu [23]	Profile features, KNN	0.063	0.117	0.172	0.245	0.323	0.417	0.573	0.273
Proposed method	DLC feature, NB	0.075	0.154	0.267	0.358	0.472	0.594	0.699	0.374

ISSN: 1475-925X