Anatomy-specific classification of medical images using deep convolutional nets

TL;DR

This paper develops a deep convolutional neural network approach for accurate, anatomy-specific classification of CT images, achieving high accuracy and AUC, facilitating improved computer-aided diagnosis systems.

Contribution

The study introduces a ConvNet-based method for organ-specific classification of medical images, utilizing data augmentation to enhance performance, with high accuracy and AUC.

Findings

Classification error of 5.9%

Average AUC of 0.998

Effective data augmentation improves results

Abstract

Automated classification of human anatomy is an important prerequisite for many computer-aided diagnosis systems. The spatial complexity and variability of anatomy throughout the human body makes classification difficult. "Deep learning" methods such as convolutional networks (ConvNets) outperform other state-of-the-art methods in image classification tasks. In this work, we present a method for organ- or body-part-specific anatomical classification of medical images acquired using computed tomography (CT) with ConvNets. We train a ConvNet, using 4,298 separate axial 2D key-images to learn 5 anatomical classes. Key-images were mined from a hospital PACS archive, using a set of 1,675 patients. We show that a data augmentation approach can help to enrich the data set and improve classification performance. Using ConvNets and data augmentation, we achieve anatomy-specific classification error of 5.9 % and area-under-the-curve (AUC) values of an average of 0.998 in testing. We demonstrate that deep learning can be used to train very reliable and accurate classifiers that could initialize further computer-aided diagnosis.