Partner: Yajun Ma

University of California (US)

Recent publications
1.Byra M., Wu M., Zhang X., Jang H., Ma Y-J., Chang E.Y., Shah S., Du J., Knee menisci segmentation and relaxometry of 3D ultrashort echo time cones MR imaging using attention U‐Net with transfer learning, Magnetic Resonance in Medicine, ISSN: 1522-2594, DOI: 10.1002/mrm.27969, pp.1-14, 2019
Abstract:

Jiang Du, Department of Radiology, University of California, San Diego, CA 92103‐8226. Email: jiangdu@ucsd.edu Funding information The authors acknowledge grant support from GE Healthcare, NIH (1R01 AR062581, 1R01 AR068987 and 1R01 NS092650), and the VA Clinical Science Research & Development Service (1I01CX001388, I21RX002367). Purpose: To develop a deep learning‐based method for knee menisci segmentation in 3D ultrashort echo time (UTE) cones MR imaging, and to automatically determine MR relaxation times, namely the T1, T1ρ, and T∗ 2 parameters, which can be used to assess knee osteoarthritis (OA). Methods: Whole knee joint imaging was performed using 3D UTE cones sequences to collect data from 61 human subjects. Regions of interest (ROIs) were outlined by 2 experienced radiologists based on subtracted T1ρ‐weighted MR images. Transfer learning was applied to develop 2D attention U‐Net convolutional neural networks for the menisci segmentation based on each radiologist’s ROIs separately. Dice scores were calculated to assess segmentation performance. Next, the T1, T1ρ, T∗ 2 relaxations, and ROI areas were determined for the manual and automatic segmentations, then compared. Results: The models developed using ROIs provided by 2 radiologists achieved high Dice scores of 0.860 and 0.833, while the radiologists’ manual segmentations achieved a Dice score of 0.820. Linear correlation coefficients for the T1, T1ρ, and T∗ 2 relaxations calculated using the automatic and manual segmentations ranged between 0.90 and 0.97, and there were no associated differences between the estimated average meniscal relaxation parameters. The deep learning models achieved segmentation performance equivalent to the inter‐observer variability of 2 radiologists. Conclusion: The proposed deep learning‐based approach can be used to efficiently generate automatic segmentations and determine meniscal relaxations times. The method has the potential to help radiologists with the assessment of meniscal diseases, such as OA.

Keywords:

deep learning, menisci, osteoarthritis, quantitative MR, segmentation

Affiliations:
Byra M.-IPPT PAN
Wu M.-University of California (US)
Zhang X.-University of California (US)
Jang H.-University of California (US)
Ma Y-J.-University of California (US)
Chang E.Y.-University of California (US)
Shah S.-University of California (US)
Du J.-University of California (US)
2.Guo T., Ma Y-J., High R.A., Tang Q., Wong J.H., Byra M., Searleman A.C., To S.C., Wan L., Le N., Du J., Chang E., Assessment of an in vitro model of rotator cuff degeneration using quantitative magnetic resonance and ultrasound imaging with biochemical and histological correlation, European Journal of Radiology, ISSN: 0720-048X, DOI: 10.1016/j.ejrad.2019.108706, Vol.121, pp.1-10, 2019
Abstract:

Purpose Quantitative imaging methods could improve diagnosis of rotator cuff degeneration, but the capability of quantitative MR and US imaging parameters to detect alterations in collagen is unknown. The goal of this study was to assess quantitative MR and US imaging measures for detecting abnormalities in collagen using an in vitro model of tendinosis with biochemical and histological correlation. Method 36 pieces of supraspinatus tendons from 6 cadaveric donors were equally distributed into 3 groups (2 subjected to different concentrations of collagenase and a control group). Ultrashort echo time MR and US imaging measures were performed to assess changes at baseline and after 24 h of enzymatic digestion. Biochemical and histological measures, including brightfield, fluorescence, and polarized microscopy, were used to verify the validity of the model and were compared with quantitative imaging parameters. Correlations between the imaging parameters and biochemically measured digestion were analyzed. Results Among the imaging parameters, macromolecular fraction (MMF), adiabatic T1ρ, T2*, and backscatter coefficient (BSC) were useful in differentiating between the extent of degeneration among the 3 groups. MMF strongly correlated with collagen loss (r=-0.81; 95% confidence interval [CI]: -0.90,-0.66), while the adiabatic T1ρ (r = 0.66; CI: 0.42,0.81), T2* (r = 0.58; CI: 0.31,0.76), and BSC (r = 0.51; CI: 0.22,0.72) moderately correlated with collagen loss. Conclusions MMF, adiabatic T1ρ, and T2* measured and US BSC can detect alterations in collagen. Of the quantitative MR and US imaging measures evaluated, MMF showed the highest correlation with collagen loss and can be used to assess rotator cuff degeneration.

Keywords:

Rotator cuff tendon, Tendinopathy, Quantitative MRI, UTE, Quantitative ultrasound

Affiliations:
Guo T.-University of California (US)
Ma Y-J.-University of California (US)
Du J.-University of California (US)
Chang E.-University of California (US)
High R.A.-University of California (US)
Tang Q.-University of California (US)
Wong J.H.-University of California (US)
Byra M.-IPPT PAN
Searleman A.C.-University of California (US)
To S.C.-University of California (US)
Wan L.-University of California (US)
Le N.-University of California (US)

Conference abstracts
1.Byra M., Wu M., Zhang X., Jang H., Ma Y., Chang E., Shah S., Du J., Assessing the performance of knee meniscus segmentation with deep convolutional neural networks in 3D ultrashort echo time (UTE) Cones MR imaging, 27th ISMRM Annual Meeting & Exhibition, 2019-05-11/05-16, Montreal (CA), pp.1-5, 2019