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

By O. Bernard, Alain Lalande, Clément Zotti, F. Cervenansky, Xin Yang, P. Heng, Irem Cetin, K. Lekadir, Oscar Camara, M. G. gonzález Ballester and 27 more. IEEE Transactions on Medical Imaging, 2018

2,285 citations recorded by the source corpus.

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.

Subfields: Cardiology and Cardiovascular Medicine, Radiology, Nuclear Medicine and Imaging, Surgery

View Paper: https://www.semanticscholar.org/paper/9406246f6972c03e5bfaac4df4676648dc4ac935

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cardiology and Cardiovascular Medicine

In Radiology, Nuclear Medicine and Imaging

In Surgery

Salman Hameed Khan

Citations in the corpus

Survey on Deep Neural Networks in Speech and Vision Systems (2019, background): “…in deep neural networks have shown tremendous potential in almost all areas of medical imaging such as ophthalmology [215], dental radiography [216], skin cancer imaging [217], brain imaging [218], cardiac imaging [219, 220], urology [221], lung imaging [222], stroke imaging [223], and so on.”
Channel prior convolutional attention for medical image segmentation (2023, methodology): “Subfigure 2 (a) presents the evaluation results for automated cardiac diagnosis (Bernard et al., 2018), and subfigure 2 (b) showcases the outcomes for skin lesion segmentation (Gutman et al., 2016; Barata et al., 2014).”
Segment Anything in Medical Images (2023, background): “, T1, T2, ADC, FLAIR) [24][10][6][41][5][8][29][42], abdomen tumor, COVID-19 infection, gallbladder, head and neck tumor, liver, pancreas, pleural effusion, and stomach segmentation in CT images [34][19][7][33][32][42][4][28][27][12], breast tumor, liver, and vessel segmentation in ultrasound images”
Multi-Scale Self-Guided Attention for Medical Image Segmentation (2019, background): “eure, Montreal, Canada.´ email:jose.dolz@etsmtl.ca. Manuscript received XXX; revised XXX. [1] and have achieved outstanding performance in a broad span of applications, including brain [2] or cardiac [3] imaging, for example, becoming the de facto solution for these problems. In this scenario, fully”
Mamba-UNet: UNet-Like Pure Visual Mamba for Medical Image Segmentation (2024, methodology): “Automated Cardiac Diagnosis Challenge We conducted our experiments using the publicly available ACDC MRI cardiac segmentation dataset from the MICCAI 2017 Challenge [1].”
Medical Image Segmentation Review: The Success of U-Net (2022, methodology): “Bernard et al. [89] analyzed the performance of ten architectures that were involved in the “Automatic Cardiac Diagnosis Challenge (ACDC)” workshop held in conjunction with the 2017 International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI) .”
Transformers in Medical Imaging: A Survey (2022, methodology): “Experiments on Synapse and ACDC [155] dataset demonstrate the effectiveness of the Swin-UNet architectural design.”
nnFormer: Interleaved Transformer for Volumetric Segmentation (2021, methodology): “To fairly compare nnFormer with previous Transformer-based architectures, we conduct experiments on Synapse [14] and Automatic Cardiac Diagnosis Challenge (ACDC) [2] datasets.”
Automated Design of Deep Learning Methods for Biomedical Image Segmentation (2019, methodology): “ scores (i.e. mean between liver and tumor dice for the liver dataset), values for the ablation studies represent the percentage-wise change in Dice score. matic Cardiac Segmentation Challenge (ACDC) [1]: Here, three parts of the heart were to be segmented in cine-MRI images for two dierent time ste”
nnFormer: Volumetric Medical Image Segmentation via a 3D Transformer (2021, methodology): “The default optimizer is SGD where we set the momentum to 0.99.”
Automated cardiovascular magnetic resonance image analysis with fully convolutional networks (2017, methodology): “ network works on two additional datasets, the MICCAI 2009 Left Ventricle Segmentation Challenge (LVSC 2009) dataset [29] and the MICCAI 2017 Automated Cardiac Diagnosis Challenge (ACDC 2017) dataset [30]. These two datasets were acquired using dierent scanners or dierent protocols [15,31] from the ”
nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation (2020, methodology): “At the same semantic segmentation is an essential ingredient in numerous clinical applications 3,4 , including applications of artificial intelligence in diagnostic support systems 5,6 , therapy planning support 7 , intra-operative assistance 2 and tumor growth monitoring 8 .”
Contrastive learning of global and local features for medical image segmentation with limited annotations (2020, methodology): “[I] The ACDC dataset was hosted in MICCAI 2017 ACDC challenge [7, 1].”