Abstract:
Deep neural networks have been investigated in learning latent representations of
medical images, yet most of the studies limit their approach using 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 clustering algorithm for learning latent representations of medical
images. In this work, we present Deep clustering method that jointly learns the
parameters of a neural network and the cluster assignments of the resulting features.
We iteratively groups the features with a standard clustering algorithm, k-means
and uses the subsequent assignments as a supervision to update the weights of the
network. We evaluated the learned image representations on a task of classi cation
using a publicly available diabetic retinopathy fundus image dataset. The experimental
results show that our proposed method is close to the state-of-the-art supervised
ensemble CNN.