ANALYSIS of TRANSFER LEARNING for SELECT RETINAL DISEASE CLASSIFICATION

Purpose: To analyze the effect of transfer learning for classification of diabetic retinopathy (DR) by fundus photography and select retinal diseases by spectral domain optical coherence tomography (SD-OCT). Methods: Five widely used open-source deep neural networks and four customized simpler and smaller networks, termed the CBR family, were trained and evaluated on two tasks: 1) classification of DR using fundus photography and 2) classification of drusen, choroidal neovascularization, and diabetic macular edema using SD-OCT. For DR classification, the quadratic weighted Kappa coefficient was used to measure the level of agreement between each network and ground truth–labeled test cases. For SD-OCT–based classification, accuracy was calculated for each network. Kappa and accuracy were compared between iterations with and without use of transfer learning for each network to assess for its effect. Results: For DR classification, Kappa increased with transfer learning for all networks (range of increase 0.152–0.556). For SD-OCT–based classification, accuracy increased for four of five open-source deep neural networks (range of increase 1.8%–3.5%), slightly decreased for the remaining deep neural network (20.6%), decreased slightly for three of four CBR networks (range of decrease 0.9%–1.8%), and decreased by 9.6% for the remaining CBR network. Conclusion: Transfer learning improved performance, as measured by Kappa, for DR classification for all networks, although the effect ranged from small to substantial. Transfer learning had minimal effect on accuracy for SD-OCT–based classification for eight of the nine networks analyzed. These results imply that transfer learning may substantially increase performance for DR classification but may have minimal effect for SD-OCT–based classification.