TumorNET: Lung Nodule Characterization Using Multi-View Convolutional Neural Network with Gaussian Process (ISBI 2017)
Introduction:
Lung cancer accounts for the highest number of mortalities among all cancers in the world. Classification of lung nodules into malignant and benign is one of the most important tasks in this regard. A fast, robust and accurate system to address this challenge would not only save a lot of radiologists’ time and effort, but would also enable the discovery of new discriminative imaging features. Significant successes in terms of improved survival rates for lung cancer patients have been observed due to improvements in CAD (Computer Aided Diagnosis) technologies and development of advanced treatment options. However, lung cancer still has a 5-year survival rate of 17.8% where only 15% of all cases are diagnosed at an early stage.
Method:
In this work, we propose an end-to-end trainable multi-view deep Convolutional Neural Network (CNN) for nodule characterization. First, we use median intensity projection to obtain a 2D patch corresponding to each dimension. The three images are then concatenated to form a tensor, where the images serve as different channels of the input image.
In order to increase the number of training samples, we perform data augmentation by scaling, rotating and adding noise to the input image. The trained network is used to extract features from the input image followed by a Gaussian Process (GP) regression to obtain the malignancy score.
We also empirically establish the significance of different high level nodule attributes such as calcification, sphericity, spiculation, lobulation, texture and margin for malignancy determination. These attributes are found to be complementary to the deep multi-view CNN features and a significant improvement over other methods is obtained.
An overview of the proposed method. First, the median intensity projection is performed across each axis, followed by their concatenation as three channels of an image. A CNN with 5 convolution and 3 fully connected layers is trained from scratch. Finally, the malignancy score is obtained using the Gaussian Process regression.
Results:
Comparison of the proposed approach with Support Vector Regression, Elastic Net and LASSO using accuracy measure and standard error of the mean (SEM).
Qualitative results showing median intensity projected images for correctly (green) and incorrectly (red) scored lung nodules. (a) and (b) show malignant and benign nodules respectively where each row shows different cases and column represents different views (axial, sagittal, coronal).
Poster: [Download]
Related Publication/Reference:
"TumorNET: Lung Nodule Characterization Using Multi-View Convolutional Neural Network with Gaussian Process", Sarfaraz Hussein, Robert Gillies, Kunlin Cao, Qi Song, Ulas Bagci. IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017) [Paper]
BibTeX:
@inproceedings{hussein2017tumornet,
title={TumorNet: Lung Nodule Characterization Using Multi-View Convolutional Neural Network with Gaussian Process},
author={Hussein, Sarfaraz and Gillies, Robert and Cao, Kunlin and Song, Qi and Bagci, Ulas},
booktitle={2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)},
pages={1007--1010},
year={2017},
organization={IEEE}
}
Regression accuracy and standard error (SEM) using the combination of high level attributes and CNN features.