Recognition and standardization of cardiac MRI orientation via multi-tasking learning and deep neural networks

TL;DR

This paper introduces a deep learning framework that simultaneously recognizes and standardizes cardiac MRI orientations using multi-task learning and transfer learning across multiple modalities, improving MRI image processing.

Contribution

The paper presents a novel multi-task deep neural network for cardiac MRI orientation recognition and a transfer learning strategy for multi-modality adaptation, along with practical tools for clinical use.

Findings

Effective orientation recognition across multiple MRI modalities.

Open-source tools for MRI orientation adjustment and visualization.

Enhanced standardization in cardiac MRI imaging workflows.

Abstract

In this paper, we study the problem of imaging orientation in cardiac MRI, and propose a framework to categorize the orientation for recognition and standardization via deep neural networks. The method uses a new multi-tasking strategy, where both the tasks of cardiac segmentation and orientation recognition are simultaneously achieved. For multiple sequences and modalities of MRI, we propose a transfer learning strategy, which adapts our proposed model from a single modality to multiple modalities. We embed the orientation recognition network in a Cardiac MRI Orientation Adjust Tool, i.e., CMRadjustNet. We implemented two versions of CMRadjustNet, including a user-interface (UI) software, and a command-line tool. The former version supports MRI image visualization, orientation prediction, adjustment, and storage operations; and the latter version enables the batch operations. The source code, neural network models and tools have been released and open via https://zmiclab.github.io/projects.html.