Deep Learning Techniques for Automatic MRI Cardiac Multi-Structures Segmentation and Diagnosis: Is the Problem Solved?

Delineation of the left ventricular cavity, myocardium, and right ventricle from cardiac magnetic resonance images (multi-slice 2-D cine MRI) is a common clinical task to establish diagnosis. The automation of the corresponding tasks has thus been the subject of intense research over the past decades. In this paper, we introduce the “Automatic Cardiac Diagnosis Challenge” dataset (ACDC), the largest publicly available and fully annotated dataset for the purpose of cardiac MRI (CMR) assessment. The dataset contains data from 150 multi-equipments CMRI recordings with reference measurements and classification from two medical experts. The overarching objective of this paper is to measure how far state-of-the-art deep learning methods can go at assessing CMRI, i.e., segmenting the myocardium and the two ventricles as well as classifying pathologies. In the wake of the 2017 MICCAI-ACDC challenge, we report results from deep learning methods provided by nine research groups for the segmentation task and four groups for the classification task. Results show that the best methods faithfully reproduce the expert analysis, leading to a mean value of 0.97 correlation score for the automatic extraction of clinical indices and an accuracy of 0.96 for automatic diagnosis. These results clearly open the door to highly accurate and fully automatic analysis of cardiac CMRI. We also identify scenarios for which deep learning methods are still failing. Both the dataset and detailed results are publicly available online, while the platform will remain open for new submissions.

I. Introduction

Analysis of cardiac function plays an important role in clinical cardiology for patient management, disease diagnosis, risk evaluation, and therapy decision [1]–[3]. Thanks to digital imagery, the assessment of a set of complementary indices computed from different structures of the heart is a routine task for cardiac diagnostics. Because of its well-known capacity for discriminating different types of tissues, Cardiac MRI (CMR) (built from series of parallel short axis slices) is considered as the gold standard of cardiac function analysis through the assessment of the left and right ventricular ejection fractions (EF) and stroke volumes (SV), the left ventricle mass and the myocardium thickness. This requires accurate delineation of the left ventricular endocardium and epicardium, and of the right ventricular endocardium for both end diastolic (ED) and end systolic (ES) phase instances. In clinical practice, semi-automatic segmentation is still a daily practice because of the lack of accuracy of fully-automatic cardiac segmentation methods. This leads to time consuming tasks prone to intra- and inter-observer variability [4].