Machine learning-based radiomics to differentiate immune-mediated necrotizing myopathy from limb-girdle muscular dystrophy R2 using MRI.

Objectives: This study aimed to assess the feasibility of a machine learning-based radiomics tools to discriminate between Limb-girdle muscular dystrophy R2 (LGMDR2) and immune-mediated necrotizing myopathy (IMNM) using lower-limb muscle magnetic resonance imaging (MRI) examination. Methods: After institutional review board approval, 30 patients with genetically proven LGMDR2 (12 females; age, 34.0 ± 11.3) and 45 patients with IMNM (28 females; age, 49.2 ± 16.6) who underwent lower-limb MRI examination including T1-weighted and interactive decomposition water and fat with echos asymmetric and least-squares estimation (IDEAL) sequences between July 2014 and August 2022 were included. Radiomics features of muscles were obtained, and four machine learning algorithms were conducted to select the optimal radiomics classifier for differential diagnosis. This selected algorithm was performed to construct the T1-weighted (TM), water-only (WM), or the combined model (CM) for calf-only, thigh-only, or the calf and thigh MR images, respectively. And their diagnostic performance was studied using area under the curve (AUC) and compared to the semi-quantitative model constructed by the modified Mercuri scale of calf and thigh muscles scored by two radiologists specialized in musculoskeletal imaging. Results: The logistic regression (LR) model was the optimal radiomics model. The performance of the WM and CM for thigh-only images (AUC 0.893, 0.913) was better than those for calf-only images (AUC 0.846, 0.880) except the TM. For "calf + thigh" images, the TM, WM, and CM models always performed best (AUC 0.953, 0.907, 0.953) with excellent accuracy (92.0, 84.0, 88.0%). The AUCs of the Mercuri model of the calf, thigh, and "calf + thigh" images were 0.847, 0.900, and 0.953 with accuracy (84.0, 84.0, 88.0%). Conclusion: Machine learning-based radiomics models can differentiate LGMDR2 from IMNM, performing better than visual assessment. The model built by combining calf and thigh images presents excellent diagnostic efficiency.

Evaluation of Intravoxel Incoherent Motion Diffusion-Weighted Magnetic Resonance Imaging for Detection of Bowel Inflammation in Patients With Crohn Disease.

OBJECTIVES: This study aimed to evaluate the feasibility of intravoxel incoherent motion diffusion-weighted magnetic resonance imaging (DW-MRI) in detecting bowel inflammation in patients with Crohn disease (CD). METHODS: Sixteen patients who underwent intravoxel incoherent motion DW-MRI for CD and colonoscopy were recruited. Seventy-nine bowel segments were selected, and their mean D, D*, f, and apparent diffusion coefficient (ADC) values were measured. The receiver operating characteristic curve was performed to distinguish inflamed from normal bowel. RESULTS: The mean D, D*, f, and ADC values of inflamed bowel were significantly lower than those of normal bowel (P < 0.05). The area under the receiver operating characteristic curve for f (0.906) and ADC values (0.924) was greater than that for D (0.709) or D* values (0.686) for differentiating inflamed bowel from normal bowel (P < 0.05). CONCLUSIONS: Intravoxel incoherent motion DW-MRI is a feasible technique for detecting inflammation in CD patients. The ADC and f values have more potential than the D and D* values.

Fatty infiltration evaluation and selective pattern characterization of lower limbs in limb-girdle muscular dystrophy type 2A by muscle magnetic resonance imaging.

INTRODUCTION: Limb-girdle muscular dystrophy type 2A (LGMD2A) is characterized by progressive wasting of muscles for which the disease-monitoring tools are still deficient. METHODS: We performed muscle MRI of the lower limbs in 32 LGMD2A patients and 21 controls. The modified Mercuri scale was employed to evaluate the degree of fatty infiltration. RESULTS: Severe fatty infiltration in the long head of biceps femoris (modified Mercuri scale 3.99) and sparing of extensor digitorum longus (modified Mercuri scale 0.17) were observed. The sensitivity and specificity of this pattern in diagnostic testing was 76.00% and 90.48%, respectively. A comprehensive clinical and MRI evaluation revealed that progressive fatty infiltration in the upper leg correlated well with disease progression, but neither calf involvement nor muscle strength deterioration showed a good correlation. DISCUSSION: The selective involvement pattern is potentially useful for LGMD2A diagnosis. Upper leg muscle MRI is a sensitive evaluation method for monitoring disease progression. Muscle Nerve 58: 536-541, 2018.