Prediction of Geometric Transformation on Cardiac MRI via Convolutional Neural Network

TL;DR

This paper introduces a self-supervised convolutional neural network approach to predict geometric transformations in cardiac MRI images, enabling effective feature learning without manual annotations.

Contribution

It proposes a novel self-supervised learning method for medical images by recognizing geometric transformations, including a generalization to 3D data.

Findings

Achieved over 96% accuracy on various cardiac MRI modalities

Demonstrated effective unsupervised feature learning in medical imaging

Provided a publicly available code and model for the community

Abstract

In the field of medical image, deep convolutional neural networks(ConvNets) have achieved great success in the classification, segmentation, and registration tasks thanks to their unparalleled capacity to learn image features. However, these tasks often require large amounts of manually annotated data and are labor-intensive. Therefore, it is of significant importance for us to study unsupervised semantic feature learning tasks. In our work, we propose to learn features in medical images by training ConvNets to recognize the geometric transformation applied to images and present a simple self-supervised task that can easily predict the geometric transformation. We precisely define a set of geometric transformations in mathematical terms and generalize this model to 3D, taking into account the distinction between spatial and time dimensions. We evaluated our self-supervised method on CMR images of different modalities (bSSFP, T2, LGE) and achieved accuracies of 96.4%, 97.5%, and 96.4%, respectively. The code and models of our paper will be published on: https://github.com/gaoxin492/Geometric_Transformation_CMR