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

Olivier Bernard 1 Alain Lalande 2 Clement Zotti 3 Frederic Cervenansky 1 Xin Yang 4 Pheng-Ann Heng 4 Irem Cetin 5 Karim Lekadir 5 Oscar Camara 5 Miguel Angel Gonzalez Ballester 6 Gerard Sanroma 5 Sandy Napel 7 Steffen Petersen 8 Georgios Tziritas 9 Elias Grinias 9 Mahendra Khened 10 Varghese Alex Kollerathu 10 Ganapathy Krishnamurthi 10 Marc-Michel Rohé 11, 12 Xavier Pennec 11, 12 Maxime Sermesant 11, 12 Fabian Isensee 13 Paul Jager 13 Klaus Maier-Hein 13 Peter Full 14 Ivo Wolf 15 Sandy Engelhardt 15 Chrisitan Baumgartner 16 Lisa Koch 17 Jelmer Wolterink 18 Ivana Isgum 18 Yeonggul Jang 19 Yoonmi Hong 19 Jay Patravali 20 Shubham Jain 20 Olivier Humbert 21 Pierre-Marc Jodoin 3
Abstract : 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 classificationtask. 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.
Type de document :
Article dans une revue
IEEE Transactions on Medical Imaging, Institute of Electrical and Electronics Engineers, 2018, 37 (11), pp.2514-2525. 〈10.1109/TMI.2018.2837502〉
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01803621
Contributeur : Ivan Porcherot <>
Soumis le : mercredi 30 mai 2018 - 15:52:58
Dernière modification le : mercredi 9 janvier 2019 - 18:26:10

Identifiants

Citation

Olivier Bernard, Alain Lalande, Clement Zotti, Frederic Cervenansky, Xin Yang, et al.. Deep Learning Techniques for Automatic MRI Cardiac Multi-structures Segmentation and Diagnosis: Is the Problem Solved?. IEEE Transactions on Medical Imaging, Institute of Electrical and Electronics Engineers, 2018, 37 (11), pp.2514-2525. 〈10.1109/TMI.2018.2837502〉. 〈hal-01803621〉

Partager

Métriques

Consultations de la notice

336