Orientation recognition and correction of Cardiac MRI with deep neural network

TL;DR

This paper presents a deep neural network framework for automatic orientation recognition and correction in cardiac MRI images, adaptable across multiple modalities with transfer learning, and integrated into a practical command-line tool.

Contribution

The paper introduces a novel deep learning-based approach for cardiac MRI orientation correction, including a transfer learning strategy for multi-modality application and a usable command-line implementation.

Findings

Effective orientation correction on 2D DICOM images

Successful transfer learning to multi-modality MRI

Open-source code and tools provided

Abstract

In this paper, the problem of orientation correction in cardiac MRI images is investigated and a framework for orientation recognition via deep neural networks is proposed. For multi-modality MRI, we introduce a transfer learning strategy to transfer our proposed model from single modality to multi-modality. We embed the proposed network into the orientation correction command-line tool, which can implement orientation correction on 2D DICOM and 3D NIFTI images. Our source code, network models and tools are available at https://github.com/Jy-stdio/MSCMR_orient/