Learning Deep Representations of Medical Images using Siamese CNNs with Application to Content-Based Image Retrieval

Abstract

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.

arXiv commentPresented in NIPS 2017 Workshop on Machine Learning for Health (ML4H); add retrieval results; fix typos

References in corpus (3)

• Adam: A Method for Stochastic Optimization
• A Survey on Deep Learning in Medical Image Analysis
• Brain Tumor Segmentation with Deep Neural Networks

Cited by in corpus (8)

• Small Sample Learning in Big Data Era
• Leveraging Siamese Networks for One-Shot Intrusion Detection Model
• Neural ranking models for document retrieval
• Part-aware Prototype Network for Few-shot Semantic Segmentation
• Representation Learning for Electronic Health Records
• Brain Tumor Image Retrieval via Multitask Learning
• Revisiting Cross Modal Retrieval
• Montage based 3D Medical Image Retrieval from Traumatic Brain Injury Cohort using Deep Convolutional Neural Network