Assessment of whole-body muscle MRI for the early diagnosis of Amyotrophic Lateral Sclerosis.

OBJECTIVES: To evaluate muscle signal abnormalities on whole-body muscle MRI with T2 and diffusion-weighted imaging in early ALS stages. METHODS: 101 muscles were analyzed in newly diagnosed ALS patients and healthy controls on a whole-body MRI protocol including four-point T2-Dixon imaging and diffusion-weighted imaging (b0 and b800). Sensitivity and inter-observer agreement were assessed. RESULTS: 15 patients (mean age, 64 +/- 12 [SD], 9 men) who met the Awaji-Shima criteria for definite, probable or possible ALS and 9 healthy controls were assessed (mean age, 53 +/- 13 [SD], 2 men). 61 % of the muscles assessed in ALS patients (62/101) showed signal hyperintensities on T2-weighted imaging, mainly in the upper and lower extremities (legs, hands and feet). ALS patients had a significantly higher number of involved muscles compared to healthy controls (p = 0,006). Diffusion-weighted imaging allowed for the detection of additional involvement in 22 muscles, thus improving the sensitivity of whole-body MRI from 60 % (using T2-weighted imaging only) up to 80 % (with the combination of T2-weighted and diffusion-weighted imaging). CONCLUSIONS: ALS patients exhibited significant muscle signal abnormalities on T2-weighted and diffusion-weighted imaging in early disease stages. Whole-body MRI could be used for pre-EMG mapping of muscle involvement in order to choose suitable targets, thus improving early diagnosis.

A deep learning tool without muscle-by-muscle grading to differentiate myositis from facio-scapulo-humeral dystrophy using MRI.

PURPOSE: The purpose of this study was to assess the capabilities of a deep learning (DL) tool to discriminate between type 1 facioscapulo-humeral dystrophy (FSHD1) and myositis using whole-body muscle magnetic resonance imaging (MRI) examination without the need for visual grading of muscle signal changes. MATERIALS AND METHODS: A total of 40 patients who underwent whole-body MRI examination that included T1-weighted and STIR sequences were included. There were 19 patients with proven FSHD1 (9 men, 10 women; mean age, 47.7 ± 18.0 [SD] years; age range: 20-72 years) and 21 patients with myositis fulfilling European Neuromuscular Centre criteria and European League Against Rheumatism and American College of Rheumatology criteria (11 men, 10 women; mean age, 59.3 ± 17.0 [SD]; age range: 19-78 years). Based on thigh, calf, and shoulder sections a supervised training of a neural network was performed and its diagnostic performance was studied using a 5-fold cross validation method and compared to the results obtained by two radiologists specialized in musculoskeletal imaging. RESULTS: The DL tool was able to differentiate FSHD1 from myositis with a correct classification percentage respectively of 69 % (95% CI: 39-99), 75% (95% CI: 48-100) and 77% (95% CI: 60-94) when thigh only, thigh and calf or the thigh, calf, and shoulder MR images were analyzed. The percentages of correct classification of the two radiologists for these later MR images were 38/40 (95%) and 35/40 (87.5%), respectively; with no differences with DL tool correct classification (P = 0.41 and P > 0.99, respectively). Among the seven patients who were misclassified by the radiologists, the DL tool correctly classified six of them. CONCLUSION: A DL tool was developed to discriminate between FSHD1 and myositis using whole-body MRI with performances equivalent to those achieved by two radiologists. This study provides a proof of concept of the effectiveness of a DL approach to distinguish between two myopathies using MRI with a small amount of data, and no prior muscle signal changes grading.