skip to main content


Search for: All records

Creators/Authors contains: "Chaudhari, Akshay"

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

  1. null (Ed.)
    Deep neural networks give state-of-the-art accuracy for reconstructing images from few and noisy measurements, a problem arising for example in accelerated magnetic resonance imaging (MRI). However, recent works have raised concerns that deep-learning-based image reconstruction methods are sensitive to perturbations and are less robust than traditional methods: Neural networks (i) may be sensitive to small, yet adversarially-selected perturbations, (ii) may perform poorly under distribution shifts, and (iii) may fail to recover small but important features in an image. In order to understand the sensitivity to such perturbations, in this work, we measure the robustness of different approaches for image reconstruction including trained and un-trained neural networks as well as traditional sparsity-based methods. We find, contrary to prior works, that both trained and un-trained methods are vulnerable to adversarial perturbations. Moreover, both trained and un-trained methods tuned for a particular dataset suffer very similarly from distribution shifts. Finally, we demonstrate that an image reconstruction method that achieves higher reconstruction quality, also performs better in terms of accurately recovering fine details. Our results indicate that the state-of-the-art deep-learning-based image reconstruction methods provide improved performance than traditional methods without compromising robustness. 
    more » « less
  2. Background

    Deep learning (DL)‐based automatic segmentation models can expedite manual segmentation yet require resource‐intensive fine‐tuning before deployment on new datasets. The generalizability of DL methods to new datasets without fine‐tuning is not well characterized.

    Purpose

    Evaluate the generalizability of DL‐based models by deploying pretrained models on independent datasets varying by MR scanner, acquisition parameters, and subject population.

    Study Type

    Retrospective based on prospectively acquired data.

    Population

    Overall test dataset: 59 subjects (26 females); Study 1: 5 healthy subjects (zero females), Study 2: 8 healthy subjects (eight females), Study 3: 10 subjects with osteoarthritis (eight females), Study 4: 36 subjects with various knee pathology (10 females).

    Field Strength/Sequence

    A 3‐T, quantitative double‐echo steady state (qDESS).

    Assessment

    Four annotators manually segmented knee cartilage. Each reader segmented one of four qDESS datasets in the test dataset. Two DL models, one trained on qDESS data and another on Osteoarthritis Initiative (OAI)‐DESS data, were assessed. Manual and automatic segmentations were compared by quantifying variations in segmentation accuracy, volume, and T2 relaxation times for superficial and deep cartilage.

    Statistical Tests

    Dice similarity coefficient (DSC) for segmentation accuracy. Lin's concordance correlation coefficient (CCC), Wilcoxon rank‐sum tests, root‐mean‐squared error‐coefficient‐of‐variation to quantify manual vs. automatic T2 and volume variations. Bland–Altman plots for manual vs. automatic T2 agreement. APvalue < 0.05 was considered statistically significant.

    Results

    DSCs for the qDESS‐trained model, 0.79–0.93, were higher than those for the OAI‐DESS‐trained model, 0.59–0.79. T2 and volume CCCs for the qDESS‐trained model, 0.75–0.98 and 0.47–0.95, were higher than respective CCCs for the OAI‐DESS‐trained model, 0.35–0.90 and 0.13–0.84. Bland–Altman 95% limits of agreement for superficial and deep cartilage T2 were lower for the qDESS‐trained model, ±2.4 msec and ±4.0 msec, than the OAI‐DESS‐trained model, ±4.4 msec and ±5.2 msec.

    Data Conclusion

    The qDESS‐trained model may generalize well to independent qDESS datasets regardless of MR scanner, acquisition parameters, and subject population.

    Evidence Level

    1

    Technical Efficacy

    Stage 1

     
    more » « less
  3. Purpose

    To develop a radial, double‐echo steady‐state (DESS) sequence with ultra‐short echo‐time (UTE) capabilities for T2measurement of short‐T2tissues along with simultaneous rapid, signal‐to‐noise ratio (SNR)‐efficient, and high‐isotropic‐resolution morphological knee imaging.

    Methods

    THe 3D radial UTE readouts were incorporated into DESS, termed UTEDESS. Multiple‐echo‐time UTEDESS was used for performing T2relaxometry for short‐T2tendons, ligaments, and menisci; and for Dixon water‐fat imaging. In vivo T2estimate repeatability and SNR efficiency for UTEDESS and Cartesian DESS were compared. The impact of coil combination methods on short‐T2measurements was evaluated by means of simulations. UTEDESS T2measurements were compared with T2measurements from Cartesian DESS, multi‐echo spin‐echo (MESE), and fast spin‐echo (FSE).

    Results

    UTEDESS produced isotropic resolution images with high SNR efficiency in all short‐T2tissues. Simulations and experiments demonstrated that sum‐of‐squares coil combinations overestimated short‐T2measurements. UTEDESS measurements of meniscal T2were comparable to DESS, MESE, and FSE measurements while the tendon and ligament measurements were less biased than those from Cartesian DESS. Average UTEDESS T2repeatability variation was under 10% in all tissues.

    Conclusion

    The T2measurements of short‐T2tissues and high‐resolution morphological imaging provided by UTEDESS makes it promising for studying the whole knee, both in routine clinical examinations and longitudinal studies. Magn Reson Med 78:2136–2148, 2017. © 2017 International Society for Magnetic Resonance in Medicine.

     
    more » « less