Search

Objective Genetic diagnosis of muscular dystrophies (MDs) has classically been guided by clinical presentation, muscle biopsy, and muscle MRI data. Muscle MRI suggests diagnosis based on the pattern of muscle fatty replacement. However, patterns overlap between different disorders and knowledge about disease-specific patterns is limited. Our aim was to develop a software-based tool that can recognize muscle MRI patterns and thus aid diagnosis of MDs. Methods We collected 976 pelvic and lower limbs T1-weighted muscle MRIs from 10 different MDs. Fatty replacement was quantified using Mercuri score and files containing the numeric data were generated. Random forest supervised machine learning was applied to develop a model useful to identify the correct diagnosis. Two thousand different models were generated and the one with highest accuracy was selected. A new set of 20 MRIs was used to test the accuracy of the model, and the results were compared with diagnoses proposed by 4 specialists in the field. Results A total of 976 lower limbs MRIs from 10 different MDs were used. The best model obtained had 95.7% accuracy, with 92.1% sensitivity and 99.4% specificity. When compared with experts on the field, the diagnostic accuracy of the model generated was significantly higher in a new set of 20 MRIs. Conclusion Machine learning can help doctors in the diagnosis of muscle dystrophies by analyzing patterns of muscle fatty replacement in muscle MRI. This tool can be helpful in daily clinics and in the interpretation of the results of next-generation sequencing tests. Classification of evidence This study provides Class II evidence that a muscle MRI-based artificial intelligence tool accurately diagnoses muscular dystrophies.

Background Late-onset Pompe disease (LOPD) is a genetic disorder characterized by progressive degeneration of the skeletal muscles produced by a deficiency of the enzyme acid alpha-glucosidase. Enzymatic replacement therapy with recombinant human alpha-glucosidase seems to reduce the progression of the disease; although at the moment, it is not completely clear to what extent. Quantitative muscle magnetic resonance imaging (qMRI) is a good biomarker for the follow-up of fat replacement in neuromuscular disorders. The aim of this study was to describe the changes observed in fat replacement in skeletal muscles using qMRI in a cohort of LOPD patients followed prospectively. Methods A total of 36 LOPD patients were seen once every year for 4 years. qMRI, several muscle function tests, spirometry, activities of daily living scales, and quality-of-life scales were performed on each visit. Muscle MRI consisted of two-point Dixon studies of the trunk and thigh muscles. Computer analysis of the images provided the percentage of muscle degenerated and replaced by fat in every muscle (known as fat fraction). Longitudinal analysis of the measures was performed using linear mixed models applying the Greenhouse-Geisser test. Results We detected a statistically significant and continuous increase in mean thigh fat fraction both in treated (+5.8% in 3 years) and in pre-symptomatic patients (+2.6% in 3years) (Greenhouse-Geisser p < 0.05). As an average, fat fraction increased by 1.9% per year in treated patients, compared with 0.8% in pre-symptomatic patients. Fat fraction significantly increased in every muscle of the thighs. We observed a significant correlation between changes observed in fat fraction in qMRI and changes observed in the results of the muscle function tests performed. Moreover, we identified that muscle performance and mean thigh fat fraction at baseline visit were independent parameters influencing fat fraction progression over 4 years (analysis of covariance, p < 0.05). Conclusions Our study identifies that skeletal muscle fat fraction continues to increase in patients with LOPD despite the treatment with enzymatic replacement therapy. These results suggest that the process of muscle degeneration is not stopped by the treatment and could impact muscle function over the years. Hereby, we show that fat fraction along with muscle function tests can be considered a good outcome measures for clinical trials in LOPD patients.

Desmoid-type fibromatosis (DTF) is a rare soft tissue tumor with fibroblastic features affecting two to four individuals per million population per year. Despite its bland microscopic appearance, the tumor behaves aggressively. Although unable to metastasize, DTF tends to recur and local recurrences in anatomically critical sites can be fatal. Tumor-associated macrophages (TAM) play an important role in tumor development through the activation of angiogenesis, particularly in cases of epithelial malignancies. The aim of this study is to investigate the prognostic significance of TAMs and the number of microvessels in DTF. Tumor macrophages (CD163), microvessel density (CD31), and beta-catenin were investigated on 69 primary DTF cases with follow-up information. CTNNB1 mutations were also studied. High density of tumor macrophages and high number of microvessels were associated with a significantly worse recurrence-free survival (P=0.03 and P=0.007, respectively). There was a significant correlation between microvessel density and CD163 macrophages (P=0.02). Furthermore, combination of high number of tumor macrophages and high microvessel density greatly improved the statistical significance (P=0.000005). Macrophages and microvessels may play an important role in the biologic behavior of DTF. This finding could help in the clinical management of patients with DTF. © Springer-Verlag 2012.

CT findings of 107 patients with non lymphomatous malignant peritoneal disease were retrospectively evaluated. The most common malignancies encountered were ovarian neoplasms (46%), followed by gastric (14%) and colonic carcinomas (10%). In 12 cases (11%) the primary site was unknown. Peritoneal and extraperitoneal findings were evaluated. Signs most frequently observed were: peritoneal implants (82%), ascites (70%), mesenteric implants (65%) and omental involvement (52%). Appreciation of the spectrum of CT findings in peritoneal carcinomatosis is essential for an accurate evaluation of scans in patients with abdominopelvic malignancies.