Institute of Fundamental Technological Research
Polish Academy of Sciences

Partners

Yajun Ma

University of California (US)

Recent publications
1.  Xue YP., Jang H., Byra M., Cai ZY., Wu M., Chang EY., Ma YJ., Su J., Automated cartilage segmentation and quantification using 3D ultrashort echo time (UTE) cones MR imaging with deep convolutional neural networks, European Radiology, ISSN: 1432-1084, DOI: 10.1007/s00330-021-07853-6, Vol.31, pp.7653-7663, 2021

Abstract:
Objective: To develop a fully automated full-thickness cartilage segmentation and mapping of T1, T1ρ, and T2*, as well as macromolecular fraction (MMF) by combining a series of quantitative 3D ultrashort echo time (UTE) cones MR imaging with a transfer learning–based U-Net convolutional neural networks (CNN) model. Methods: Sixty-five participants (20 normal, 29 doubtful-minimal osteoarthritis (OA), and 16 moderate-severe OA) were scanned using 3D UTE cones T1 (Cones-T1), adiabatic T1ρ (Cones-AdiabT1ρ), T2* (Cones-T2*), and magnetization transfer (Cones-MT) sequences at 3 T. Manual segmentation was performed by two experienced radiologists, and automatic segmentation was completed using the proposed U-Net CNN model. The accuracy of cartilage segmentation was evaluated using the Dice score and volumetric overlap error (VOE). Pearson correlation coefficient and intraclass correlation coefficient (ICC) were calculated to evaluate the consistency of quantitative MR parameters extracted from automatic and manual segmentations. UTE biomarkers were compared among different subject groups using one-way ANOVA. Results: The U-Net CNN model provided reliable cartilage segmentation with a mean Dice score of 0.82 and a mean VOE of 29.86%. The consistency of Cones-T1, Cones-AdiabT1ρ, Cones-T2*, and MMF calculated using automatic and manual segmentations ranged from 0.91 to 0.99 for Pearson correlation coefficients, and from 0.91 to 0.96 for ICCs, respectively. Significant increases in Cones-T1, Cones-AdiabT1ρ, and Cones-T2* (p < 0.05) and a decrease in MMF (p < 0.001) were observed in doubtful-minimal OA and/or moderate-severe OA over normal controls. Conclusion: Quantitative 3D UTE cones MR imaging combined with the proposed U-Net CNN model allows a fully automated comprehensive assessment of articular cartilage.

Keywords:
deep learning, cartilage, biomarkers, osteoarthritis

Affiliations:
Xue YP. - South China Normal Universit (CN)
Jang H. - University of California (US)
Byra M. - IPPT PAN
Cai ZY. - other affiliation
Wu M. - University of California (US)
Chang EY. - University of California (US)
Ma YJ. - University of California (US)
Su J. - other affiliation
2.  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, Vol.83, No.3, pp.1109-1122, 2020

Abstract:
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 T2* 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, T2* 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 T2* 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)
3.  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.108706-1-10, 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 T1p, 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 T1p (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 T1p, 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)
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)
Du J. - University of California (US)
Chang E. - 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

Category A Plus

IPPT PAN

logo ippt            Pawińskiego 5B, 02-106 Warsaw
  +48 22 826 12 81 (central)
  +48 22 826 98 15
 

Find Us

mapka
© Institute of Fundamental Technological Research Polish Academy of Sciences 2024