A combined deep-learning and deformable-model approach to fully automatic segmentation of the left ventricle in cardiac MRI

By M. Avendi, Arash Kheradvar, Hamid Jafarkhani. Medical Image Anal., 2015

590 citations recorded by the source corpus.

Segmentation of the left ventricle (LV) from cardiac magnetic resonance imaging (MRI) datasets is an essential step for calculation of clinical indices such as ventricular volume and ejection fraction. In this work, we employ deep learning algorithms combined with deformable models to develop and evaluate a fully automatic LV segmentation tool from short-axis cardiac MRI datasets. The method employs deep learning algorithms to learn the segmentation task from the ground true data. Convolutional networks are employed to automatically detect the LV chamber in MRI dataset. Stacked autoencoders are used to infer the LV shape. The inferred shape is incorporated into deformable models to improve the accuracy and robustness of the segmentation. We validated our method using 45 cardiac MR datasets from the MICCAI 2009 LV segmentation challenge and showed that it outperforms the state-of-the art methods. Excellent agreement with the ground truth was achieved. Validation metrics, percentage of good contours, Dice metric, average perpendicular distance and conformity, were computed as 96.69%, 0.94, 1.81 mm and 0.86, versus those of 79.2-95.62%, 0.87-0.9, 1.76-2.97 mm and 0.67-0.78, obtained by other methods, respectively.

Subfields: Cardiology and Cardiovascular Medicine, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/83531af06fac06374fd2e362059a850931399e8e

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 Computer Vision and Pattern Recognition

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

The rise of deep learning in drug discovery. (2018, methodology): “Besides the popular application of the image segmentation [106,107] and classiﬁcations [104,105], its utilities have also been shown in content-based image retrieval [109] and it was reported that DL methods outperformed the popular ISOMAP and Elastic Net methods.”
State-of-the-art review on deep learning in medical imaging. (2019, background): “(2008) [43] MRI (45) LV Segmentation CNN Autoencoder + Deformable model DM: 0.”
Semi-supervised Learning for Network-Based Cardiac MR Image Segmentation (2017, unknown): “For cardiac MR image segmentation, FCN and other network architectures have also been explored [1,9,11,16,17].”
Fully automatic acute ischemic lesion segmentation in DWI using convolutional neural networks (2017, unknown): “In cardiac imaging, a left ventricle segmentation approach for MR images has been proposed that combines deep CNNs and deformable models [1].”
Deep learning Mr imaging–based attenuation correction for PeT/Mr imaging 1 (2017, background): “…to medical imaging (4), with successful implementations showing promising results segmenting brain structures (5), brain tumors (6), cardiac structures (7), and bone and In this study, the deep MRAC framework was implemented in a hybrid computing environment involving Python, MATLAB, and C/C++.”
Automatic Skin Lesion Segmentation Using Deep Fully Convolutional Networks With Jaccard Distance (2017, methodology): “Specifically for medical image segmentation, CNNs have been applied to segment brain tumor on MR images [23], urinary bladder on CT urolography [24] left ventricle on cardiac MRI [25], and skin lesion from nondermoscopic images [26] among others.”
Medical Image Computing and Computer-Assisted Intervention − MICCAI 2017: 20th International Conference, Quebec City, QC, Canada, September 11-13, 2017, Proceedings, Part II (2017, unknown): “focussing on cell segmentation [15], detection and counting [8,10,16] or tracking [1,6,7,12,14], but very few deal with LFM data.”
A survey on deep learning in medical image analysis (2017, methodology): “(2015) MRI CNN Left ventricle slice detection; simple CNN indicates if structure is present Avendi et al. (2016) MRI CNN Left ventricle segmentation; AE used to initialize filters because training data set was small Kong et al. (2016) MRI RNN Identification of end-diastole and end-systole frames fro”
Deep Learning for Health Informatics (2017, methodology): “In [66], a deep learning algorithm is employed to encode the parameters of a deformable model and thus facilitate the segmentation of the left ventricle (LV) from short-axis cardiac MRI.”
Deep learning in radiology: an overview of the concepts and a survey of the state of the art with focus on MRI (2018, background): “In radiology, detection is often an important step in the diagnostic process that identifies an abnormality (such as a mass or a nodule), an organ, an anatomical structure, or a region of interest for further classification or segmentation.(73,74) Here we discuss the common architectures used for va”
What the radiologist should know about artificial intelligence – an ESR white paper (2019, methodology): “Avendi et al. developed a deep learning and deformable model for left ventricular (LV) segmentation from cardiac MRI datasets, to obtain an automated calculation of clinical indices such as ventricular volume and ejection fraction [44].”
Deep Learning for Cardiac Image Segmentation: A Review (2019, methodology): “(47) proposed one of the first DL-based methods for LV segmentation in cardiac short-axis MR images.”
Anatomically Constrained Neural Networks (ACNNs): Application to Cardiac Image Enhancement and Segmentation (2017, methodology): “Label map predictions are collected at the output of the decoder and they are compared with the same ground-truth annotations described previously, which was similar to the AE based segmentation method proposed in [2] and [3].”
Deep Learning Techniques for Automatic MRI Cardiac Multi-Structures Segmentation and Diagnosis: Is the Problem Solved? (2018, background): “As opposed to several MRI cardiac segmentation papers which report 2D Hausdorff distances [5], [10], [11], we report the 3D dH , which allows an intrinsic management of the missing segmentation problem on the end slices.”
DRINet for Medical Image Segmentation (2018, background): “clinical applications, including brain segmentation [2], cardiac ventricle segmentation [3], abdominal organ segmentation [4], and cell segmentation in biological images [5].”