Objective To compare mono- and bi-exponential T₂* analysis in healthy and degenerated Achilles tendons using a recently introduced magnetic resonance variable-echo-time sequence (vTE) for T₂* mapping. Methods Ten volunteers and ten patients were included in the study. A variable-echo-time sequence was used with 20 echo times. Images were post-processed with both techniques, mono- and bi-exponential [T₂*_m, short T₂* component (T₂*_s) and long T₂* component (T₂*_l)]. The number of mono- and bi-exponentially decaying pixels in each region of interest was expressed as a ratio (B/M). Patients were clinically assessed with the Achilles Tendon Rupture Score (ATRS), and these values were correlated with the T₂* values. Results The means for both T₂*_m and T₂*_s were statistically significantly different between patients and volunteers; however, for T₂*_s, the P value was lower. In patients, the Pearson correlation coefficient between ATRS and T₂*s was −0.816 (P = 0.007). Conclusion The proposed variable-echo-time sequence can be successfully used as an alternative method to UTE sequences with some added benefits, such as a short imaging time along with relatively high resolution and minimised blurring artefacts, and minimised susceptibility artefacts and chemical shift artefacts. Bi-exponential T₂* calculation is superior to mono-exponential in terms of statistical significance for the diagnosis of Achilles tendinopathy. Key Points • Magnetic resonance imaging offers new insight into healthy and diseased Achilles tendons • Bi-exponential T2* calculation in Achilles tendons is more beneficial than mono-exponential • A short T2* component correlates strongly with clinical score • Variable echo time sequences successfully used instead of ultrashort echo time sequences

Objective: In this study we address the automatic segmentation of selected muscles of the thigh and leg through a supervised deep learning approach. Material and methods: The application of quantitative imaging in neuromuscular diseases requires the availability of regions of interest (ROI) drawn on muscles to extract quantitative parameters. Up to now, manual drawing of ROIs has been considered the gold standard in clinical studies, with no clear and universally accepted standardized procedure for segmentation. Several automatic methods, based mainly on machine learning and deep learning algorithms, have recently been proposed to discriminate between skeletal muscle, bone, subcutaneous and intermuscular adipose tissue. We develop a supervised deep learning approach based on a unified framework for ROI segmentation. Results: The proposed network generates segmentation maps with high accuracy, consisting in Dice Scores ranging from 0.89 to 0.95, with respect to “ground truth” manually segmented labelled images, also showing high average performance in both mild and severe cases of disease involvement (i.e. entity of fatty replacement). Discussion: The presented results are promising and potentially translatable to different skeletal muscle groups and other MRI sequences with different contrast and resolution.

Purpose: The feasibility of imaging musculoskeletal fibrous tissue components, such as menisci, ligaments, and tendons, with a conventional spoiled gradient echo technique is explored in vivo at 3 T and 7 T.Methods: To this end, the echo time (TE₁) of a conventional Fourier‐encoded multicontrast three‐dimensional SGPR sequence is minimized by using nonselective excitation pulses, highly asymmetric readouts, and a variable TE₁ along the phase and slice encoding direction. In addition, a fully sampled second echo image (with TE₂ >> TE₁) can be used to highlight components with short transverse relaxation times in a difference image with positive contrast.Results: Fourier‐encoded spoiled gradient echo sequences are able to provide sub‐millisecond TE₁ of about 800 μs for typical in‐plane resolutions of about 0.5 x 0.5 mm². As a result, high‐resolution positive contrast images of fibrous tissues can be generated within clinically feasible scan‐time of about 2–7 minutes.Conclusion: After optimization, Fourier‐encoded spoiled gradient echo provides a highly robust and flexible imaging technique for high‐resolution positive contrast imaging of fibrous tissue that can readily be used in the clinical routine. Magn Reson Med 70:1434–1439, 2013.

Dafne is a free and open-source software suite that implements the principles of continuous and decentralized deep learning to assist users in medical image segmentation, serving as a potential alternative to traditional centralized learning approaches.