Real time coarse orientation detection in MR scans using multi-planar deep convolutional neural networks

Parmeet S. Bhatia; Fitsum Reda; Martin Harder; Yiqiang Zhan; Xiang Sean Zhou

doi:10.1117/12.2254647

Translator Disclaimer

24 February 2017 Real time coarse orientation detection in MR scans using multi-planar deep convolutional neural networks

Parmeet S. Bhatia, Fitsum Reda, Martin Harder, Yiqiang Zhan, Xiang Sean Zhou

Author Affiliations +

Proceedings Volume 10133, Medical Imaging 2017: Image Processing; 1013303 (2017) https://doi.org/10.1117/12.2254647
Event: SPIE Medical Imaging, 2017, Orlando, Florida, United States

Abstract

Automatically detecting anatomy orientation is an important task in medical image analysis. Specifically, the ability to automatically detect coarse orientation of structures is useful to minimize the effort of fine/accurate orientation detection algorithms, to initialize non-rigid deformable registration algorithms or to align models to target structures in model-based segmentation algorithms. In this work, we present a deep convolution neural network (DCNN)-based method for fast and robust detection of the coarse structure orientation, i.e., the hemi-sphere where the principal axis of a structure lies. That is, our algorithm predicts whether the principal orientation of a structure is in the northern hemisphere or southern hemisphere, which we will refer to as UP and DOWN, respectively, in the remainder of this manuscript. The only assumption of our method is that the entire structure is located within the scan’s field-of-view (FOV). To efficiently solve the problem in 3D space, we formulated it as a multi-planar 2D deep learning problem. In the training stage, a large number coronal-sagittal slice pairs are constructed as 2-channel images to train a DCNN to classify whether a scan is UP or DOWN. During testing, we randomly sample a small number of coronal-sagittal 2-channel images and pass them through our trained network. Finally, coarse structure orientation is determined using majority voting. We tested our method on 114 Elbow MR Scans. Experimental results suggest that only five 2-channel images are sufficient to achieve a high success rate of 97.39%. Our method is also extremely fast and takes approximately 50 milliseconds per 3D MR scan. Our method is insensitive to the location of the structure in the FOV.

Conference Presentation

Citation Download Citation

Parmeet S. Bhatia, Fitsum Reda, Martin Harder, Yiqiang Zhan, and Xiang Sean Zhou "Real time coarse orientation detection in MR scans using multi-planar deep convolutional neural networks", Proc. SPIE 10133, Medical Imaging 2017: Image Processing, 1013303 (24 February 2017); https://doi.org/10.1117/12.2254647

ACCESS THE FULL ARTICLE