A Deep Learning System for Synthetic Knee Magnetic Resonance Imaging: Is Artificial Intelligence-Based Fat-Suppressed Imaging Feasible?

MATERIALS AND METHODS: This single-center study was approved by the institutional review board. Artificial intelligence-based FS MRI scans were created from non-FS images using a deep learning system with a modified convolutional neural network-based U-Net that used a training set of 25,920 images and validation set of 16,416 images. Three musculoskeletal radiologists reviewed 88 knee MR studies in 2 sessions, the original (proton density [PD] + FSPD) and the synthetic (PD + AFSMRI). Readers recorded AFSMRI quality (diagnostic/nondiagnostic) and the presence or absence of meniscal, ligament, and tendon tears; cartilage defects; and bone marrow abnormalities. Contrast-to-noise rate measurements were made among subcutaneous fat, fluid, bone marrow, cartilage, and muscle. The original MRI sequences were used as the reference standard to determine the diagnostic performance of AFSMRI (combined with the original PD sequence). This is a fully balanced study design, where all readers read all images the same number of times, which allowed the determination of the interchangeability of the original and synthetic protocols. Descriptive statistics, intermethod agreement, interobserver concordance, and interchangeability tests were applied. A P value less than 0.01 was considered statistically significant for the likelihood ratio testing, and P value less than 0.05 for all other statistical analyses. RESULTS: Artificial intelligence-based FS MRI quality was rated as diagnostic (98.9% [87/88] to 100% [88/88], all readers). Diagnostic performance (sensitivity/specificity) of the synthetic protocol was high, for tears of the menisci (91% [71/78], 86% [84/98]), cruciate ligaments (92% [12/13], 98% [160/163]), collateral ligaments (80% [16/20], 100% [156/156]), and tendons (90% [9/10], 100% [166/166]). For cartilage defects and bone marrow abnormalities, the synthetic protocol offered an overall sensitivity/specificity of 77% (170/221)/93% (287/307) and 76% (95/125)/90% (443/491), respectively. Intermethod agreement ranged from moderate to substantial for almost all evaluated structures (menisci, cruciate ligaments, collateral ligaments, and bone marrow abnormalities). No significant difference was observed between methods for all structural abnormalities by all readers (P > 0.05), except for cartilage assessment. Interobserver agreement ranged from moderate to substantial for almost all evaluated structures. Original and synthetic protocols were interchangeable for the diagnosis of all evaluated structures. There was no significant difference for the common exact match proportions for all combinations (P > 0.01). The conspicuity of all tissues assessed through contrast-to-noise rate was higher on AFSMRI than on original FSPD images (P < 0.05). CONCLUSIONS: Artificial intelligence-based FS MRI (3D AFSMRI) is feasible and offers a method for fast imaging, with similar detection rates for structural abnormalities of the knee, compared with original 3D MR sequences.

Spontaneous osteonecrosis of the knee (SONK): The role of MR imaging in predicting clinical outcome.

BACKGROUND/AIM: We try to investigate the association between patterns of imaging findings in patients who had a diagnosis of subchondral fracture around the knee, formerly known as SONK and their clinical outcome. MATERIALS AND METHODS: We retrospectively identified 43 knees of 37 patients (28 males, 15 females) who had diagnosis of subchondral fractures around the knee. The mean age is 56-year-old (range 17-83). Musculoskeletal fellowship trained radiologist evaluated all 43 knee MRI in: 1)location of marrow edema 2)peri-osseous edema; 3) subchondral fracture line; 4) subchondral articular surface contour; 5)meniscal tear and extrusion; 6)adjacent soft tissue edema; 7) joint effusion. Independent clinical chart review was performed for clinical outcome with follow up time average of 13.3 months (range 0-88 months). Bad outcome was defined as worsening on imaging, continued complaint with surgical management and knee replacement or another episode of SONK. Chi-square analysis and Student's T tests were conducted to test the statistical significance of association between MR findings and outcomes. Statistical significance was set at p = 0.05 level. RESULTS: Of 43 knees, 6 patients had another episodes of SONK (14%), 11 patients were not improving or needed injection vs arthroscopy (26%), 4 patients required arthroplasty (9%), 22 patients had no negative outcome (51%). Gender, age, diabetic status, and location of the subchondral fracture show no influence on outcome. Worse outcome group had a significantly higher average BMI (31.7 vs. 28.0, P = 0.02). Positive change of subchondral articular surface contour is the only imaging finding with positive association with worse outcome (80% vs. 39.9%, P = 0.02). Presence of positive findings of above 3), 4), 5) and 6) had higher percentage of bad outcome (77.8%) compared to those with less positive findings (47.2%). CONCLUSION: MR imaging findings may help at identifying SONK patient with potential risk of developing bad outcome.

In vivo evaluation of human patellar tendon microstructure and microcirculation with diffusion MRI.

BACKGROUND: Patellar tendon (PT) microstructure integrity and microcirculation status play a crucial role in the progression of tendinopathy and tendon repair. PURPOSE: To assess the feasibility and robustness of stimulated-echo based diffusion-weighted MRI with readout-segmented echo-planar imaging (ste-RS-EPI) for noninvasive assessment of microstructure and microcirculation of human PT. STUDY TYPE: Prospective. SUBJECTS: Fifteen healthy volunteers. FIELD STRENGTH/SEQUENCE: PT diffusion tensor imaging (DTI) and intravoxel incoherent motion (IVIM) were acquired with an ste-RS-EPI protocol on a 3T MRI scanner. ASSESSMENT: Subjects were positioned with their PT at the magic angle. DTI-derived parameters including axial diffusivity (AD), radial diffusivity (RD), mean diffusivity (MD), and fractional anisotropy (FA) were estimated with b-values of 0 and 800 s/mm2 and 12 diffusion directions. IVIM-derived parameters, f p , D* × f p , V b , and D* × V b were assessed in the central-third and the outer-two thirds of the PT with b-values of 0, 20, 30, 60, 80, 120, 200, 400, and 600 s/mm2 in three orthogonal directions. STATISTICAL TESTS: Paired t-tests were used to evaluate differences in IVIM parameters between the central-third and outer-two thirds regions of the patellar tendon. Paired t-tests and within-subject coefficient of variation were used to assess the intra- and intersession reproducibility of PT DTI and IVIM parameters. RESULTS: DTI parameters for healthy PT were 1.54 ± 0.09 × 10-3 mm2 /s, 1.01 ± 0.05 × 10-3 mm2 /s, 1.18 ± 0.06 × 10-3 mm2 /s, and 0.30 ± 0.04 for AD, RD, MD, and FA, respectively. Significantly higher (P < 0.05) IVIM parameters f p and D* × f p were observed in the outer-two thirds (6.1% ± 2.4% and 95.2 ± 49.6, respectively) compared with the central-third (3.8% ± 2.3% and 48.6 ± 35.2, respectively) of the PT. DATA CONCLUSION: Diffusion MRI of PT with an ste-RS-EPI protocol is clinically feasible. Both DTI- and IVIM-derived parameters of the PT demonstrated good test-retest reproducibility and interrater reliability. LEVEL OF EVIDENCE: 2 Technical Efficacy: Stage 1 J. Magn. Reson. Imaging 2020;51:780-790.

Abbreviated quantitative UTE imaging in anterior cruciate ligament reconstruction.

BACKGROUND: Existing ultrashort echo time magnetic resonance imaging (UTE MRI) methods require prohibitively long acquisition times (~ 20-40 min) to quantitatively assess the clinically relevant fast decay T2* component in ligaments and tendons. The purpose of this study was to evaluate the feasibility and clinical translatability of a novel abbreviated quantitative UTE MRI paradigm for monitoring graft remodeling after anterior cruciate ligament (ACL) reconstruction. METHODS: Eight patients who had Graftlink™ hamstring autograft reconstruction were recruited for this prospective study. A 3D double-echo UTE sequence at 3.0 Tesla was performed at 3- and 6-months post-surgery. An abbreviated UTE MRI paradigm was established based on numerical simulations and in vivo validation from healthy knees. This proposed approach was used to assess the T2* for fast decay component ([Formula: see text]) and bound water signal fraction (fbw) of ACL graft in regions of interest drawn by a radiologist. RESULTS: Compared to the conventional bi-exponential model, the abbreviated UTE MRI paradigm achieved low relative estimation bias for [Formula: see text] and fbw over a range of clinically relevant values for ACL grafts. A decrease in [Formula: see text] of the intra-articular graft was observed in 7 of the 8 ACL reconstruction patients from 3- to 6-months (- 0.11 ± 0.16 ms, P = 0.10). Increases in [Formula: see text] and fbw from 3- to 6-months were observed in the tibial intra-bone graft ([Formula: see text]: 0.19 ± 0.18 ms, P < 0.05; Δfbw: 4% ± 4%, P < 0.05). Lower [Formula: see text] (- 0.09 ± 0.11 ms, P < 0.05) was observed at 3-months when comparing the intra-bone graft to the graft/bone interface in the femoral tunnel. The same comparisons at the 6-months also yielded relatively lower [Formula: see text] (- 0.09 ± 0.12 ms, P < 0.05). CONCLUSION: The proposed abbreviated 3D UTE MRI paradigm is capable of assessing the ACL graft remodeling process in a clinically translatable acquisition time. Longitudinal changes in [Formula: see text] and fbw of the ACL graft were observed.

Intravoxel incoherent motion (IVIM) imaging in human achilles tendon.

BACKGROUND: Limited microcirculation has been implicated in Achilles tendinopathy and may affect healing and disease progression. Existing invasive and noninvasive approaches to evaluate tendon microcirculation lack sensitivity and spatial coverage. PURPOSE: To develop a novel Achilles tendon intravoxel incoherent motion (IVIM) MRI protocol to overcome the limitations from low tendon T2 /T2 * value and low intratendinous blood volume and blood velocity to evaluate tendon microcirculation. STUDY TYPE: Prospective. SUBJECTS: Sixteen healthy male participants (age 31.0 ± 2.1) were recruited. FIELD STRENGTH/SEQUENCE: A stimulated echo readout-segmented echo planar imaging (ste-RS-EPI) IVIM sequence at 3.0T. ASSESSMENT: The feasibility of the proposed ste-RS-EPI IVIM protocol combined with Achilles tendon magic angle effect was evaluated. The sensitivity of the protocol was assessed by an exercise-induced intratendinous hemodynamic response in healthy participants. The vascular origin of the observed IVIM signal was validated by varying the diffusion mixing time and echo time. STATISTICAL TESTS: Two-tailed t-tests were used to evaluate differences (P < 0.05 was considered significant). RESULTS: Consistent with known tendon hypovascularity, the midportion Achilles tendon at baseline showed significantly lower IVIM-derived perfusion fraction (fp ) (3.1 ± 0.9%) compared to the proximal and distal Achilles tendon (6.0 ± 1.8% and 6.1 ± 2.0%, respectively; P < 0.01). Similarly, the midportion Achilles tendon exhibited significantly lower baseline blood flow index (D*×fp ) (40.9 ± 19.2, 18.3 ± 5.3, and 32.0 ± 9.4 in proximal, midportion, and distal Achilles tendon, respectively; P < 0.01). Eccentric heel-raise exercise led to ∼2 times increase of Achilles tendon blood flow in healthy participants. Consistent with its vascular origin, the estimated fp demonstrated a high dependency to IVIM protocol parameters, while the T1 /T2 -corrected absolute intratendinous microvascular blood volume fraction (Vb ) did not vary. DATA CONCLUSION: Achilles tendon ste-RS-EPI IVIM noninvasively assessed baseline values and exercise-induced changes to tendon microcirculation in healthy tendon. LEVEL OF EVIDENCE: 1 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2018;48:1690-1699.

Diffusion tensor imaging of human Achilles tendon by stimulated echo readout-segmented EPI (ste-RS-EPI).

PURPOSE: Healing, regeneration, and remodeling of the injured Achilles tendon are associated with notable changes in tendon architecture. However, assessing Achilles microstructural properties with conventional diffusion tension imaging (DTI) remains a challenge because of very short T2 / T 2 * values of the tendon. Hence, the objective of this study was to develop a novel Achilles tendon DTI protocol for a non-invasive investigation of the changes of microstructural integrity in tendinopathy. METHODS: A novel stimulated echo readout-segmented EPI (ste-RS-EPI) DTI sequence was proposed to achieve a TE of ∼14-20 ms for typical b-values of 400-800 s/mm2 on clinical 3T MRI scanners. To further boost tendon MR signal, the Achilles was positioned at the magic angle (∼55 °) with respect to the scanner B0 field. The sensitivity of the developed protocol was evaluated in 19 healthy participants and 6 patients with clinically confirmed tendinopathy. RESULTS: Compared to spin echo RS-EPI DTI protocol, ste-RS-EPI provided an ∼100-200% increase in Achilles MR signal. Tendinopathic Achilles demonstrated a high degree of microstructural disruption based on DTI tractography analysis, with significantly lower (P < 0.05) axial diffusivity (1.20 ± 0.19 vs. 1.39 ± 0.10 × 10-3 mm2 /s), radial diffusivity (0.72 ± 0.11 vs. 0.81 ± 0.08 × 10-3 mm2 /s), and mean diffusivity (0.87 ± 0.14 vs. 1.00 ± 0.07 × 10-3 mm2 /s), but no significant difference in fractional anisotropy (0.38 ± 0.04 vs. 0.38 ± 0.05; P = 0.86). CONCLUSION: Achilles tendon ste-RS-EPI DTI can non-invasively detect the tendinopathy-induced changes to microstructural integrity, consistent with the disruption of collagen arrangement and increased cellularity. This study demonstrated the robustness and sensitivity of the proposed protocol in Achilles tendinopathy.

SRF phosphorylation by glycogen synthase kinase-3 promotes axon growth in hippocampal neurons.

The growth of axons is an intricately regulated process involving intracellular signaling cascades and gene transcription. We had previously shown that the stimulus-dependent transcription factor, serum response factor (SRF), plays a critical role in regulating axon growth in the mammalian brain. However, the molecular mechanisms underlying SRF-dependent axon growth remains unknown. Here we report that SRF is phosphorylated and activated by GSK-3 to promote axon outgrowth in mouse hippocampal neurons. GSK-3 binds to and directly phosphorylates SRF on a highly conserved serine residue. This serine phosphorylation is necessary for SRF activity and for its interaction with MKL-family cofactors, MKL1 and MKL2, but not with TCF-family cofactor, ELK-1. Axonal growth deficits caused by GSK-3 inhibition could be rescued by expression of a constitutively active SRF. The SRF target gene and actin-binding protein, vinculin, is sufficient to overcome the axonal growth deficits of SRF-deficient and GSK-3-inhibited neurons. Furthermore, short hairpin RNA-mediated knockdown of vinculin also attenuated axonal growth. Thus, our findings reveal a novel phosphorylation and activation of SRF by GSK-3 that is critical for SRF-dependent axon growth in mammalian central neurons.