Diagnosis of Retinal Diseases Based on Bayesian Optimization Deep Learning Network Using Optical Coherence Tomography Images

Table 10

Comparison of proposed models with other deep learning models.

Models	Retinal diseases	Classification accuracy (%)
Models proposed in the literature
OctNET [13]	DME, CNV, and Drusen	99.7
Layer guided CNN [35]	DME, CNV, and Drusen	89.9
GAN [16]	DME, CNV, MH and Drusen	93.9
Deep CNN [36]	DMD and DME	95.7
CenterNet [11]	DR	98.1
AlexNet, ResNet-18, GoogleNet [18]	CSR	99.6
Capsule network [22]	DME, Drusen, and CNV	99.6
CNN [24]	DMD, DME, and CNV	97.0
Deep CNN [23]	CSR	93.8
Proposed pretrained models in this work
VGG16	AMD, CNV, DME, CSE, DR, Drusen, MH
(a) As a feature extractor		79.36
(b) As a fine tuner		95.25
Densenet201
(a) As a feature extractor		93.81
(b) As a fine tuner		99.71
InceptionV3
(a) As a feature extractor		89.73
(b) As a fine tuner		96.78
Xception
(a) As a feature extractor		90.99
(b) As a fine tuner		97.92