End-to-End Diagnosis and Segmentation Learning from Cardiac Magnetic Resonance Imaging

TL;DR

This paper introduces an end-to-end deep learning approach for cardiac MRI diagnosis and segmentation that performs well even with small datasets, improving accuracy and convergence speed.

Contribution

It presents a multi-task learning method that jointly trains for segmentation and diagnosis, demonstrating improved results over baseline models on limited data.

Findings

Reduced diagnosis error from 32% to 22%.

Faster convergence compared to non-segmentation models.

Achieved best results for end-to-end CMR diagnosis and segmentation.

Abstract

Cardiac magnetic resonance (CMR) is used extensively in the diagnosis and management of cardiovascular disease. Deep learning methods have proven to deliver segmentation results comparable to human experts in CMR imaging, but there have been no convincing results for the problem of end-to-end segmentation and diagnosis from CMR. This is in part due to a lack of sufficiently large datasets required to train robust diagnosis models. In this paper, we propose a learning method to train diagnosis models, where our approach is designed to work with relatively small datasets. In particular, the optimisation loss is based on multi-task learning that jointly trains for the tasks of segmentation and diagnosis classification. We hypothesize that segmentation has a regularizing effect on the learning of features relevant for diagnosis. Using the 100 training and 50 testing samples available from the Automated Cardiac Diagnosis Challenge (ACDC) dataset, which has a balanced distribution of 5 cardiac diagnoses, we observe a reduction of the classification error from 32% to 22%, and a faster convergence compared to a baseline without segmentation. To the best of our knowledge, this is the best diagnosis results from CMR using an end-to-end diagnosis and segmentation learning method.