Artificial Intelligence-Based Diagnosis of Diabetes Mellitus: Combining Fundus Photography with Traditional Chinese Medicine Diagnostic Methodology

Table 1

Fundus conditions detected using fundus photography. The fundus photography detected the subject’s fundus condition. The photographs were then computer analyzed. The fundus characteristics are listed.

Fundus photography report
	Detection object	Detecting value
Fundus condition	Hemorrhage area (mm^2)	0.0462
	Hemorrhage lesion number	2
	Maximum hemorrhage area (mm^2)	0.0308
	Proportion of hemorrhage area	0.0466
	Exudation area (mm^2)	0.1456
	Exudation lesion number	22
	Maximum exudation area (mm^2)	0.0182
	Proportion of exudation area	0.1468
	Mean vessel diameter (pixels)	11.527
	Microangioma number	0
	Arterial venous ratio	0.7128
	Cup-disc ratio	0.499
	Average density of leopard spot	0.049
	Atrophic arc and optic disc area ratio	0.547
	Average curvature of vessels	0.0086

Proportion of hemorrhage area: the ratio of the hemorrhage area to the total area taken; proportion of exudation area: the ratio of the exudation area to the total area taken; cup-disc ratio: the ratio of the optic cup area to the optic disc area; average density of leopard spot: the ratio of the total area of leopard spots to the total area taken.