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 Characterization of Severe Arterial Phase Respiratory Motion Artifact on Gadoxetate Disodium-Enhanced MRI – Assessment of Interrater Agreement and Reliability

2018 ◽  
Vol 190 (04) ◽  
pp. 341-347 ◽  
Author(s):  
Kristina Ringe ◽  
Julian Luetkens ◽  
Rolf Fimmers ◽  
Renate Hammerstingl ◽  
Günter Layer ◽  
...  
Keyword(s):  
Respiratory Motion ◽  
Intraclass Correlation ◽  
Motion Artifact ◽  
Motion Artifacts ◽  
Interrater Agreement ◽  
Arterial Phase ◽  
Gadoxetate Disodium ◽  
Liver Mri ◽  
Multicenter Studies ◽  
Respiratory Motion Artifact

Purpose To assess the interrater agreement and reliability of experienced abdominal radiologists in the characterization and grading of arterial phase gadoxetate disodium-related respiratory motion artifact on liver MRI. Materials and Methods This prospective multicenter study was initiated by the working group for abdominal imaging within the German Roentgen Society (DRG), and approved by the local IRB of each participating center. 11 board-certified radiologists independently reviewed 40 gadoxetate disodium-enhanced liver MRI datasets. Motion artifacts in the arterial phase were assessed on a 5-point scale. Interrater agreement and reliability were calculated using the intraclass correlation coefficient (ICC) and Kendall coefficient of concordance (W), with p < 0.05 deemed significant. Results The ICC for interrater agreement and reliability were 0.983 (CI 0.973 – 0.990) and 0.985 (CI 0.978 – 0.991), respectively (both p < 0.0001), indicating excellent agreement and reliability. Kendall’s W for interrater agreement was 0.865. A severe motion artifact, defined as a mean motion score ≥ 4 in the arterial phase was observed in 12 patients. In these specific cases, a motion score ≥ 4 was assigned by all readers in 75 % (n = 9/12 cases). Conclusion Differentiation and grading of arterial phase respiratory motion artifact is possible with a high level of inter-/intrarater agreement and interrater reliability, which is crucial for assessing the incidence of this phenomenon in larger multicenter studies. Key Points  Citation Format

scholarly journals Transient Severe Motion Artifact Related to Gadoxetate Disodium-Enhanced Liver MRI: Frequency and Risk Evaluation at a German Institution

2017 ◽  
Vol 189 (07) ◽  
pp. 651-660 ◽  
Author(s):  
Lennart Well ◽  
Vanessa Rausch ◽  
Gerhard Adam ◽  
Frank Henes ◽  
Peter Bannas
Keyword(s):  
United States ◽  
Risk Factors ◽  
Respiratory Motion ◽  
The United States ◽  
Gadobenate Dimeglumine ◽  
Motion Artifacts ◽  
Arterial Phase ◽  
Gadoxetate Disodium ◽  
Liver Mri ◽  
Potential Risk Factors

Purpose Varying frequencies (5 – 18 %) of contrast-related transient severe motion (TSM) imaging artifacts during gadoxetate disodium-enhanced arterial phase liver MRI have been reported. Since previous reports originated from the United States and Japan, we aimed to determine the frequency of TSM at a German institution and to correlate it with potential risk factors and previously published results. Materials and Methods Two age- and sex-matched groups were retrospectively selected (gadoxetate disodium n = 89; gadobenate dimeglumine n = 89) from dynamic contrast-enhanced MRI examinations in a single center. Respiratory motion-related artifacts in non-enhanced and dynamic phases were assessed independently by two readers blinded to contrast agents on a 4-point scale. Scores of ≥ 3 were considered as severe motion artifacts. Severe motion artifacts in arterial phases were considered as TSM if scores in all other phases were < 3. Potential risk factors for TSM were evaluated via logistic regression analysis. Results For gadoxetate disodium, the mean score for respiratory motion artifacts was significantly higher in the arterial phase (2.2 ± 0.9) compared to all other phases (1.6 ± 0.7) (p < 0.05). The frequency of TSM was significantly higher with gadoxetate disodium (n = 19; 21.1 %) than with gadobenate dimeglumine (n = 1; 1.1 %) (p < 0.001). The frequency of TSM at our institution is similar to some, but not all previously published findings. Logistic regression analysis did not show any significant correlation between TSM and risk factors (all p > 0.05). Conclusion We revealed a high frequency of TSM after injection of gadoxetate disodium at a German institution, substantiating the importance of a diagnosis-limiting phenomenon that so far has only been reported from the United States and Japan. In accordance with previous studies, we did not identify associated risk factors for TSM. Key Points:  Citation Format

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 SHARQnet – Sophisticated harmonic artifact reduction in quantitative susceptibility mapping using a deep convolutional neural network

2019 ◽  
Vol 29 (2) ◽  
pp. 139-149 ◽  
Author(s):  
Steffen Bollmann ◽  
Matilde Holm Kristensen ◽  
Morten Skaarup Larsen ◽  
Mathias Vassard Olsen ◽  
Mads Jozwiak Pedersen ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Susceptibility Mapping ◽  
Deep Convolutional Neural Network ◽  
Artifact Reduction ◽  
Quantitative Susceptibility Mapping

scholarly journals Motion Artifact Correction of Multi-Measured Functional Near-Infrared Spectroscopy Signals Based on Signal Reconstruction Using an Artificial Neural Network

Sensors ◽  
2018 ◽  
Vol 18 (9) ◽  
pp. 2957 ◽  
Author(s):  
Gihyoun Lee ◽  
Sang Jin ◽  
Jinung An
Keyword(s):  
Neural Network ◽  
Infrared Spectroscopy ◽  
Near Infrared Spectroscopy ◽  
Near Infrared ◽  
Motion Artifact ◽  
Correction Method ◽  
Motion Artifacts ◽  
Functional Near Infrared Spectroscopy ◽  
Artifact Correction ◽  
Performance Evaluation Index

In this paper, a new motion artifact correction method is proposed based on multi-channel functional near-infrared spectroscopy (fNIRS) signals. Recently, wavelet transform and hemodynamic response function-based algorithms were proposed as methods of denoising and detrending fNIRS signals. However, these techniques cannot achieve impressive performance in the experimental environment with lots of movement such as gait and rehabilitation tasks because hemodynamic responses have features similar to those of motion artifacts. Moreover, it is difficult to correct motion artifacts in multi-measured fNIRS systems, which have multiple channels and different noise features in each channel. Thus, a new motion artifact correction method for multi-measured fNIRS is proposed in this study, which includes a decision algorithm to determine the most contaminated fNIRS channel based on entropy and a reconstruction algorithm to correct motion artifacts by using a wavelet-decomposed back-propagation neural network. The experimental data was achieved from six subjects and the results were analyzed in comparing conventional algorithms such as HRF smoothing, wavelet denoising, and wavelet MDL. The performance of the proposed method was proven experimentally using the graphical results of the corrected fNIRS signal, CNR that is a performance evaluation index, and the brain activation map.

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