scholarly journals Convolutional neural network‐based approach for segmentation of left ventricle myocardial scar from 3D late gadolinium enhancement MR images

2019 ◽  
Vol 46 (4) ◽  
pp. 1740-1751 ◽  
Author(s):  
Fatemeh Zabihollahy ◽  
James A. White ◽  
Eranga Ukwatta
Keyword(s):  
Neural Network ◽  
Late Gadolinium Enhancement ◽  
Left Ventricle ◽  
Convolutional Neural Network ◽  
Myocardial Scar ◽  
Mr Images ◽  
Gadolinium Enhancement

scholarly journals Evaluation of state-of-the-art segmentation algorithms for left ventricle infarct from late Gadolinium enhancement MR images

2016 ◽  
Vol 30 ◽  
pp. 95-107 ◽  
Author(s):  
Rashed Karim ◽  
Pranav Bhagirath ◽  
Piet Claus ◽  
R. James Housden ◽  
Zhong Chen ◽  
...  
Keyword(s):  
Late Gadolinium Enhancement ◽  
Left Ventricle ◽  
State Of The Art ◽  
Mr Images ◽  
Gadolinium Enhancement ◽  
Segmentation Algorithms

Multi-Scale Feature Fusion Convolutional Neural Network for Concurrent Segmentation of Left Ventricle and Myocardium in Cardiac MR Images

2020 ◽  
Vol 10 (5) ◽  
pp. 1023-1032
Author(s):  
Lin Qi ◽  
Haoran Zhang ◽  
Xuehao Cao ◽  
Xuyang Lyu ◽  
Lisheng Xu ◽  
...  
Keyword(s):  
Neural Network ◽  
Left Ventricle ◽  
Convolutional Neural Network ◽  
Feature Fusion ◽  
Left Ventricular ◽  
Mr Images ◽  
Feature Maps ◽  
Scale Feature ◽  
Multi Scale ◽  
Cine Mr

Accurate segmentation of the blood pool of left ventricle (LV) and myocardium (or left ventricular epicardium, MYO) from cardiac magnetic resonance (MR) can help doctors to quantify LV ejection fraction and myocardial deformation. To reduce doctor’s burden of manual segmentation, in this study, we propose an automated and concurrent segmentation method of the LV and MYO. First, we employ a convolutional neural network (CNN) architecture to extract the region of interest (ROI) from short-axis cardiac cine MR images as a preprocessing step. Next, we present a multi-scale feature fusion (MSFF) CNN with a new weighted Dice index (WDI) loss function to get the concurrent segmentation of the LV and MYO. We use MSFF modules with three scales to extract different features, and then concatenate feature maps by the short and long skip connections in the encoder and decoder path to capture more complete context information and geometry structure for better segmentation. Finally, we compare the proposed method with Fully Convolutional Networks (FCN) and U-Net on the combined cardiac datasets from MICCAI 2009 and ACDC 2017. Experimental results demonstrate that the proposed method could perform effectively on LV and MYOs segmentation in the combined datasets, indicating its potential for clinical application.

scholarly journals Distinct non-ischemic myocardial late gadolinium enhancement lesions in patients with type 2 diabetes

2020 ◽  
Vol 19 (1) ◽  
Author(s):  
Annemie Stege Bojer ◽  
Martin Heyn Sørensen ◽  
Niels Vejlstrup ◽  
Jens P. Goetze ◽  
Peter Gæde ◽  
...  
Keyword(s):  
Type 2 Diabetes ◽  
Late Gadolinium Enhancement ◽  
Left Ventricle ◽  
Stress Perfusion ◽  
Gadolinium Enhancement ◽  
Unique Identifier ◽  
Maximal Volume ◽  
Ischemic Lesion ◽  
Control Subjects

Abstract Background Cardiovascular magnetic resonance imaging (CMR) have described localised non-ischemic late gadolinium enhancement (LGE) lesions of prognostic importance in various non-ischemic cardiomyopathies. Ischemic LGE lesions are prevalent in diabetes (DM), but non-ischemic LGE lesions have not previously been described or systematically studied in DM. Methods 296 patients with type 2 DM (T2DM) and 25 sex-matched control subjects underwent echocardiography and CMR including adenosine-stress perfusion, T1-mapping and LGE. Results 264 patients and all control subjects completed the CMR protocol. 78.4% of patients with T2DM had no LGE lesions; 11.0% had ischemic LGE lesions only; 9.5% had non-ischemic LGE lesions only; and 1.1% had both one ischemic and one non-ischemic lesion. The non-ischemic LGE lesions were situated mid-myocardial in the basal lateral or the basal inferolateral part of the left ventricle and the affected segments showed normal to high wall thickness and normal contraction. Patients with non-ischemic LGE lesions in comparison with patients without LGE lesions had increased myocardial mass (150 ± 34 vs. 133 ± 33 g, P = 0.02), average E/e’(9.9 IQR8.7–12.6 vs. 8.8 IQR7.4–10.7, P = 0.04), left atrial maximal volume (102 IQR84.6–115.2 vs. 91 IQR75.2–100.0 mL, P = 0.049), NT-proBNP (8.9 IQR5.9–19.7 vs. 5.9 IQR5.9–10.1 µmol/L, P = 0.02) and high-sensitive troponin (15.6 IQR13.0–26.1 vs. 13.0 IQR13.0–14.6 ng/L, P = 0.007) and a higher prevalence of retinopathy (48 vs. 25%, P = 0.009) and autonomic neuropathy (52 vs. 30.5%, P = 0.005). Conclusion A specific LGE pattern with lesions in the basal lateral or the basal inferolateral part of the left ventricle was found in patients with type 2 diabetes. Trial registrationhttps://www.clinicaltrials.gov. Unique identifier: NCT02684331.

Whole Tumor Segmentation from Brain MR images using Multi-view 2D Convolutional Neural Network

2021 ◽  
Author(s):  
Ritu Lahoti ◽  
Sunil Kumar Vengalil ◽  
Punith B Venkategowda ◽  
Neelam Sinha ◽  
Vinod Veera Reddy
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Tumor Segmentation ◽  
Mr Images ◽  
Brain Mr Images

scholarly journals Reduction of respiratory motion artifacts in gadoxetate-enhanced MR with a deep learning–based filter using convolutional neural network

2020 ◽  
Vol 30 (11) ◽  
pp. 5923-5932
Author(s):  
M.-L. Kromrey ◽  
D. Tamada ◽  
H. Johno ◽  
S. Funayama ◽  
N. Nagata ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Motion Artifact ◽  
Motion Artifacts ◽  
Arterial Phase ◽  
Artifact Reduction ◽  
Gadoxetate Disodium ◽  
Mr Images ◽  
Liver Mri ◽  
Lesion Conspicuity

Abstract Objectives To reveal the utility of motion artifact reduction with convolutional neural network (MARC) in gadoxetate disodium–enhanced multi-arterial phase MRI of the liver. Methods This retrospective study included 192 patients (131 men, 68.7 ± 10.3 years) receiving gadoxetate disodium–enhanced liver MRI in 2017. Datasets were submitted to a newly developed filter (MARC), consisting of 7 convolutional layers, and trained on 14,190 cropped images generated from abdominal MR images. Motion artifact for training was simulated by adding periodic k-space domain noise to the images. Original and filtered images of pre-contrast and 6 arterial phases (7 image sets per patient resulting in 1344 sets in total) were evaluated regarding motion artifacts on a 4-point scale. Lesion conspicuity in original and filtered images was ranked by side-by-side comparison. Results Of the 1344 original image sets, motion artifact score was 2 in 597, 3 in 165, and 4 in 54 sets. MARC significantly improved image quality over all phases showing an average motion artifact score of 1.97 ± 0.72 compared to 2.53 ± 0.71 in original MR images (p < 0.001). MARC improved motion scores from 2 to 1 in 177/596 (29.65%), from 3 to 2 in 119/165 (72.12%), and from 4 to 3 in 34/54 sets (62.96%). Lesion conspicuity was significantly improved (p < 0.001) without removing anatomical details. Conclusions Motion artifacts and lesion conspicuity of gadoxetate disodium–enhanced arterial phase liver MRI were significantly improved by the MARC filter, especially in cases with substantial artifacts. This method can be of high clinical value in subjects with failing breath-hold in the scan. Key Points • This study presents a newly developed deep learning–based filter for artifact reduction using convolutional neural network (motion artifact reduction with convolutional neural network, MARC). • MARC significantly improved MR image quality after gadoxetate disodium administration by reducing motion artifacts, especially in cases with severely degraded images. • Postprocessing with MARC led to better lesion conspicuity without removing anatomical details.

scholarly journals Free‐breathing 3D late gadolinium enhancement imaging of the left ventricle using a stack of spirals at 3T

2014 ◽  
Vol 41 (4) ◽  
pp. 1030-1037 ◽  
Author(s):  
Iain T. Pierce ◽  
Jennifer Keegan ◽  
Peter Drivas ◽  
Peter D. Gatehouse ◽  
David N. Firmin
Keyword(s):  
Late Gadolinium Enhancement ◽  
Left Ventricle ◽  
Free Breathing ◽  
Late Gadolinium Enhancement Imaging ◽  
Gadolinium Enhancement

scholarly journals Prediction of IDH and TERT promoter mutations in low-grade glioma from magnetic resonance images using a convolutional neural network

2019 ◽  
Vol 9 (1) ◽  
Author(s):  
Ryohei Fukuma ◽  
Takufumi Yanagisawa ◽  
Manabu Kinoshita ◽  
Takashi Shinozaki ◽  
Hideyuki Arita ◽  
...  
Keyword(s):  
Neural Network ◽  
Magnetic Resonance ◽  
Convolutional Neural Network ◽  
Texture Features ◽  
Wild Type ◽  
Mr Images ◽  
Patient Age ◽  
Tert Promoter ◽  
Patient Âgé ◽  
Grade Ii

AbstractIdentification of genotypes is crucial for treatment of glioma. Here, we developed a method to predict tumor genotypes using a pretrained convolutional neural network (CNN) from magnetic resonance (MR) images and compared the accuracy to that of a diagnosis based on conventional radiomic features and patient age. Multisite preoperative MR images of 164 patients with grade II/III glioma were grouped by IDH and TERT promoter (pTERT) mutations as follows: (1) IDH wild type, (2) IDH and pTERT co-mutations, (3) IDH mutant and pTERT wild type. We applied a CNN (AlexNet) to four types of MR sequence and obtained the CNN texture features to classify the groups with a linear support vector machine. The classification was also performed using conventional radiomic features and/or patient age. Using all features, we succeeded in classifying patients with an accuracy of 63.1%, which was significantly higher than the accuracy obtained from using either the radiomic features or patient age alone. In particular, prediction of the pTERT mutation was significantly improved by the CNN texture features. In conclusion, the pretrained CNN texture features capture the information of IDH and TERT genotypes in grade II/III gliomas better than the conventional radiomic features.

Sign in / Sign up

Export Citation Format

Share Document