Learning Deep Representations of Medical Images using Siamese CNNs with Application to Content-Based Image Retrieval
This work addresses the need for reduced annotation in medical imaging, offering a domain-specific solution that is incremental in nature.
The authors tackled the problem of learning medical image representations with less supervision by proposing a deep Siamese CNN trained on binary image pairs, achieving results comparable to state-of-the-art supervised CNNs while requiring much less annotated data.
Deep neural networks have been investigated in learning latent representations of medical images, yet most of the studies limit their approach in a single supervised convolutional neural network (CNN), which usually rely heavily on a large scale annotated dataset for training. To learn image representations with less supervision involved, we propose a deep Siamese CNN (SCNN) architecture that can be trained with only binary image pair information. We evaluated the learned image representations on a task of content-based medical image retrieval using a publicly available multiclass diabetic retinopathy fundus image dataset. The experimental results show that our proposed deep SCNN is comparable to the state-of-the-art single supervised CNN, and requires much less supervision for training.