Quantifying fat replacement of muscle by quantitative MRI in muscular dystrophy

Abstract

The muscular dystrophies are rare orphan diseases, characterized by progressive muscle weakness: the most common and well known is Duchenne muscular dystrophy which affects young boys and progresses quickly during childhood. However, over 70 distinct variants have been identified to date, with different rates of progression, implications for morbidity, mortality, and quality of life. There are presently no curative therapies for these diseases, but a range of potential therapies are presently reaching the stage of multi-centre, multi-national first-in-man clinical trials. There is a need for sensitive, objective end-points to assess the efficacy of the proposed therapies. Present clinical measurements are often too dependent on patient effort or motivation, and lack sensitivity to small changes, or are invasive. Quantitative MRI to measure the fat replacement of skeletal muscle by either chemical shift imaging methods (Dixon or IDEAL) or spectroscopy has been demonstrated to provide such a sensitive, objective end-point in a number of studies. This review considers the importance of the outcome measures, discusses the considerations required to make robust measurements and appropriate quality assurance measures, and draws together the existing literature for cross-sectional and longitudinal cohort studies using these methods in muscular dystrophy.

Keywords: Clinical trial; Duchenne; MRI; Muscle; Muscular dystrophy; Quantitative.

Fig. 1

T1-weighted image of dystrophic thigh muscle. The widely varying signal intensity in the uniform subcutaneous fat demonstrates the B₁ inhomogeneity across the leg at 3.0 T which inhibits the ability of T1-weighted images to monitor disease progression

Fig. 2

Cross-section through healthy lower leg muscle with a gradient echo sequence using (left) out of phase (TE = 3.45 ms), (middle) in phase (TE = 4.6 ms), and (right) out of phase (TE = 5.75 ms) echo times. The top row shows the magnitude signal, while the bottom shows the phase. Note the cancellation of the magnitude signal at water–fat boundaries in the out of phase images

Fig. 3

Use of a mathematical model enables the signal from the water components and the fat components to be separated, though these images still contain B₁ inhomogeneity

Fig. 4

If we calculate the percentage of fat signal in the total MR signal, then the background inhomogeneity disappears and we are left with a map of fat fraction from 0 to 100% which is comparable between scan sessions and individuals

Fig. 5

Typical water–fat spectrum based on ref 68. Fat signal is often modelled on one off-resonant frequency (1.3 ppm); however, this is not accurate, since up to 30% of fat signal may lie at different locations. For true quantitative measurements, the entire fat spectrum should be accounted for

Fig. 6

Example of using PDFF maps to assess progression at baseline (left) and 12 months later (right) in the lower leg of a patient with limb girdle muscular dystrophy 2I (bottom) and Duchenne muscular dystrophy (top). Progression in 1 year is generally much more rapid in DMD compared to LGMD2I: fat fraction changes measured included the soleus (21–28% in DMD, 8–13% in LGMD2I), tibialis anterior (12–16% in DMD, no change at 6% in LGMD2I), lateral gastrocnemius (21–29% in DMD, 20–24% in LGMD2I), medial gastrocnemius (15–20% in DMD, 29–49% in LGMD2I), and the peroneus (28–36% in DMD, 18–26% in LGMD2I)