Multi-Scale Convolutional Neural Network for Automated AMD Classification using Retinal OCT Images
This work addresses the increasing workload in healthcare for diagnosing AMD, a leading cause of blindness, by providing an automated tool, though it is incremental as it builds on existing deep learning frameworks.
The paper tackled automated classification of age-related macular degeneration (AMD) from retinal OCT images by proposing a multi-scale convolutional neural network based on a feature pyramid network structure, achieving performance improvements of 0.4% to 3.3% over existing methods and boosting accuracy from 87.2% to 93.4% through gradual learning.
Age-related macular degeneration (AMD) is the most common cause of blindness in developed countries, especially in people over 60 years of age. The workload of specialists and the healthcare system in this field has increased in recent years mainly due to the prevalence of population aging worldwide and the chronic nature of AMD. Recent developments in deep learning have provided a unique opportunity to develop fully automated diagnosis frameworks. Considering the presence of AMD-related retinal pathologies in varying sizes in OCT images, our objective was to propose a multi-scale convolutional neural network (CNN) capable of distinguishing pathologies using receptive fields with various sizes. The multi-scale CNN was designed based on the feature pyramid network (FPN) structure and was used to diagnose normal and two common clinical characteristics of dry and wet AMD, namely drusen and choroidal neovascularization (CNV). The proposed method was evaluated on a national dataset gathered at Noor Eye Hospital (NEH) and the UCSD public dataset. Experimental results show the superior performance of our proposed multi-scale structure over several well-known OCT classification frameworks. This feature combination strategy has proved to be effective on all tested backbone models, with improvements ranging from 0.4% to 3.3%. In addition, gradual learning has proven to improve performance in two consecutive stages. In the first stage, the performance was boosted from 87.2%+-2.5% to 92.0%+-1.6% using pre-trained ImageNet weights. In the second stage, another performance boost from 92.0%+-1.6% to 93.4%+-1.4% was observed due to fine-tuning the previous model on the UCSD dataset. Lastly, generating heatmaps provided additional proof for the effectiveness of our multi-scale structure, enabling the detection of retinal pathologies appearing in different sizes.