Alexey A. Samsonov | Searcharxiv

arXiv2022

Data Adaptive Regularization for Abdominal Quantitative Susceptibility Mapping

Purpose: To improve repeatability and reproducibility across acquisition parameters and reduce bias in quantitative susceptibility mapping (QSM) of the liver, through development of an optimized regularized reconstruction algorithm for abdominal QSM. Theory and Methods: An optimized approach to estimation of magnetic susceptibility distribution is formulated as a constrained reconstruction problem that incorporates estimates of the input data reliability and anatomical priors available from chemical shift-encoded imaging. The proposed data-adaptive method was evaluated with respect to bias, repeatability, and reproducibility in a patient population with a wide range of liver iron concentration (LIC). The proposed method was compared to the state-of-the-art approach in liver QSM for two multi-echo SGRE protocols with different acquisition parameters at 3T. Results: The data-adaptive method produced susceptibility maps with higher subjective quality due to reduced shading artifacts. For both acquisition protocols, higher linear correlation with both $R_2$ and $R_2^*$-based measurements were observed for the data-adaptive method ($r^2=0.74/0.72$ for $R_2$, $0.98/0.99$ for $R_2^*$) than the standard method ($r^2=0.62/0.67$ and $0.84/0.91$). For both protocols, the data-adaptive method enabled better test-retest repeatability (repeatability coefficients 0.14/0.14ppm for the data-adaptive method, 0.26/0.31ppm for the standard method) and reproducibility across protocols (reproducibility coefficient 0.25ppm vs 0.36ppm) than the standard method. Conclusions: The proposed data-adaptive QSM algorithm may enable quantification of liver iron concentration with improved repeatability/reproducibility across different acquisition parameters as 3T.

physics.med-ph↗

arXiv2020

Deep learning-based fully automatic segmentation of wrist cartilage in MR images

The study objective was to investigate the performance of a dedicated convolutional neural network (CNN) optimized for wrist cartilage segmentation from 2D MR images. CNN utilized a planar architecture and patch-based (PB) training approach that ensured optimal performance in the presence of a limited amount of training data. The CNN was trained and validated in twenty multi-slice MRI datasets acquired with two different coils in eleven subjects (healthy volunteers and patients). The validation included a comparison with the alternative state-of-the-art CNN methods for the segmentation of joints from MR images and the ground-truth manual segmentation. When trained on the limited training data, the CNN outperformed significantly image-based and patch-based U-Net networks. Our PB-CNN also demonstrated a good agreement with manual segmentation (Sorensen-Dice similarity coefficient (DSC) = 0.81) in the representative (central coronal) slices with large amount of cartilage tissue. Reduced performance of the network for slices with a very limited amount of cartilage tissue suggests the need for fully 3D convolutional networks to provide uniform performance across the joint. The study also assessed inter- and intra-observer variability of the manual wrist cartilage segmentation (DSC=0.78-0.88 and 0.9, respectively). The proposed deep-learning-based segmentation of the wrist cartilage from MRI could facilitate research of novel imaging markers of wrist osteoarthritis to characterize its progression and response to therapy.

physics.med-ph↗