Automatic reorientation by deep learning to generate short axis SPECT myocardial perfusion images

TL;DR

This paper presents a deep learning method using CNNs and spatial transformer networks to automatically reorient SPECT myocardial perfusion images into standard short-axis slices, improving clinical workflow.

Contribution

A novel deep learning approach for automatic reorientation of MPI images using CNNs and spatial transformer networks, trained on a large dataset with ground truth annotations.

Findings

High accuracy in predicting transformation parameters.

Effective automatic reorientation demonstrated on test data.

Potential to streamline clinical MPI analysis.

Abstract

Single photon emission computed tomography (SPECT) myocardial perfusion images (MPI) can be displayed both in traditional short-axis (SA) cardiac planes and polar maps for interpretation and quantification. It is essential to reorient the reconstructed transaxial SPECT MPI into standard SA slices. This study is aimed to develop a deep-learning-based approach for automatic reorientation of MPI. Methods: A total of 254 patients were enrolled, including 228 stress SPECT MPIs and 248 rest SPECT MPIs. Five-fold cross-validation with 180 stress and 201 rest MPIs was used for training and internal validation; the remaining images were used for testing. The rigid transformation parameters (translation and rotation) from manual reorientation were annotated by an experienced operator and used as the ground truth. A convolutional neural network (CNN) was designed to predict the transformation parameters. Then, the derived transform was applied to the grid generator and sampler in spatial transformer network (STN) to generate the reoriented image. A loss function containing mean absolute errors for translation and mean square errors for rotation was employed. A three-stage optimization strategy was adopted for model optimization: 1) optimize the translation parameters while fixing the rotation parameters; 2) optimize rotation parameters while fixing the translation parameters; 3) optimize both translation and rotation parameters together.