Convolutional Sparse Kernel Network for Unsupervised Medical Image Analysis

Abstract

The availability of large-scale annotated image datasets and recent advances in supervised deep learning methods enable the end-to-end derivation of representative image features that can impact a variety of image analysis problems. Such supervised approaches, however, are difficult to implement in the medical domain where large volumes of labelled data are difficult to obtain due to the complexity of manual annotation and inter- and intra-observer variability in label assignment. We propose a new convolutional sparse kernel network (CSKN), which is a hierarchical unsupervised feature learning framework that addresses the challenge of learning representative visual features in medical image analysis domains where there is a lack of annotated training data. Our framework has three contributions: (i) We extend kernel learning to identify and represent invariant features across image sub-patches in an unsupervised manner. (ii) We initialise our kernel learning with a layer-wise pre-training scheme that leverages the sparsity inherent in medical images to extract initial discriminative features. (iii) We adapt a multi-scale spatial pyramid pooling (SPP) framework to capture subtle geometric differences between learned visual features. We evaluated our framework in medical image retrieval and classification on three public datasets. Our results show that our CSKN had better accuracy when compared to other conventional unsupervised methods and comparable accuracy to methods that used state-of-the-art supervised convolutional neural networks (CNNs). Our findings indicate that our unsupervised CSKN provides an opportunity to leverage unannotated big data in medical imaging repositories.

arXiv commentAccepted by Medical Image Analysis (with a new title 'Convolutional Sparse Kernel Network for Unsupervised Medical Image Analysis'). The manuscript is available from following link (https://doi.org/10.1016/j.media.2019.06.005)

References in corpus (16)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• A Survey on Deep Learning in Medical Image Analysis
• Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?
• Proceedings of the 29th International Conference on Machine Learning (ICML-12)
• Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks
• Unsupervised Deep Feature Extraction for Remote Sensing Image Classification
• Submanifold Sparse Convolutional Networks
• No More Pesky Learning Rates
• All you need is a good init
• Automatic Skin Lesion Analysis using Large-scale Dermoscopy Images and Deep Residual Networks
• Convolutional Kernel Networks
• Image Classification of Melanoma, Nevus and Seborrheic Keratosis by Deep Neural Network Ensemble
• Multiple Kernel Sparse Representations for Supervised and Unsupervised Learning
• Efficient Sparse-Winograd Convolutional Neural Networks
• Transfer Learning for Melanoma Detection: Participation in ISIC 2017 Skin Lesion Classification Challenge
• Araguaia Medical Vision Lab at ISIC 2017 Skin Lesion Classification Challenge

Cited by in corpus (5)

• Learning to segment images with classification labels
• Unsupervised Feature Learning with K-means and An Ensemble of Deep Convolutional Neural Networks for Medical Image Classification
• A Spatial Guided Self-supervised Clustering Network for Medical Image Segmentation
• Unsupervised Local Discrimination for Medical Images
• Deep Multi-Scale Resemblance Network for the Sub-class Differentiation of Adrenal Masses on Computed Tomography Images