Myosteatosis and bone marrow adiposity are not associated among postmenopausal women with fragility fractures.

Objectives: Although paravertebral intramuscular fatty infiltration (known as myosteatosis) following a vertebral fracture is well-known, scarce data are available regarding interactions between muscle, bone, and other fat depots. Based on a homogeneous cohort comprising postmenopausal women with or without a history of fragility fracture, we aimed to better depict the interrelationship between myosteatosis and bone marrow adiposity (BMA). Methods: 102 postmenopausal women were included, 56 of whom had a fragility fracture. Mean proton density fat fraction (PDFF) was measured in the psoas (PDFFPsoas) and paravertebral (PDFFParavertebral) muscles at the lumbar level, as well as in the lumbar spine and non-dominant hip using chemical shift encoding-based water-fat imaging. Visceral adipose tissue (VAT) and total body fat (TBF) were assessed using dual X-ray absorptiometry. Statistical models were adjusted for age, weight, height (all comparisons), and bone mineral density (when considering BMA). Results: PDFF in the psoas and paravertebral muscles was higher in the fracture group compared to controls even after adjustment for age, weight, and height (PDFFPsoas = 17.1 ± 6.1% versus 13.5 ± 4.9%, p=0.004; PDFFParavertebral = 34.4 ± 13.6% versus 24.9 ± 8.8%, p=0.002). Higher PDFFParavertebral was associated with lower PDFF at the lumbar spine (ß = -6.80 ± 2.85, p=0.022) among controls but not in the fracture group. In both groups, a significant relationship between higher PDFFPsoas and higher VAT was observed (ß = 20.27 ± 9.62, p=0.040 in the fracture group, and ß = 37.49 ± 8.65, p<0.001 in the control group). Although solely observed among controls, a similar relationship was observed between PDFFParavertebral and TBF (ß = 6.57 ± 1.80, p<0.001). No significant association was observed between BMA and other fat depots. Conclusion: Myosteatosis is not associated with BMA among postmenopausal women with fragility fractures. Whereas myosteatosis was associated with other fat depots, BMA appears uniquely regulated.

Breast nodule classification with two-dimensional ultrasound using Mask-RCNN ensemble aggregation.

PURPOSE: The purpose of this study was to create a deep learning algorithm to infer the benign or malignant nature of breast nodules using two-dimensional B-mode ultrasound data initially marked as BI-RADS 3 and 4. MATERIALS AND METHODS: An ensemble of mask region-based convolutional neural networks (Mask-RCNN) combining nodule segmentation and classification were trained to explicitly localize the nodule and generate a probability of the nodule to be malignant on two-dimensional B-mode ultrasound. These probabilities were aggregated at test time to produce final results. Resulting inferences were assessed using area under the curve (AUC). RESULTS: A total of 460 ultrasound images of breast nodules classified as BI-RADS 3 or 4 were included. There were 295 benign and 165 malignant breast nodules used for training and validation, and another 137 breast nodules images used for testing. As a part of the challenge, the distribution of benign and malignant breast nodules in the test database remained unknown. The obtained AUC was 0.69 (95% CI: 0.57-0.82) on the training set and 0.67 on the test set. CONCLUSION: The proposed deep learning solution helps classify benign and malignant breast nodules based solely on two-dimensional ultrasound images initially marked as BIRADS 3 and 4.

Three artificial intelligence data challenges based on CT and ultrasound.

PURPOSE: The 2020 edition of these Data Challenges was organized by the French Society of Radiology (SFR), from September 28 to September 30, 2020. The goals were to propose innovative artificial intelligence solutions for the current relevant problems in radiology and to build a large database of multimodal medical images of ultrasound and computed tomography (CT) on these subjects from several French radiology centers. MATERIALS AND METHODS: This year the attempt was to create data challenge objectives in line with the clinical routine of radiologists, with less preprocessing of data and annotation, leaving a large part of the preprocessing task to the participating teams. The objectives were proposed by the different organizations depending on their core areas of expertise. A dedicated platform was used to upload the medical image data, to automatically anonymize the uploaded data. RESULTS: Three challenges were proposed including classification of benign or malignant breast nodules on ultrasound examinations, detection and contouring of pathological neck lymph nodes from cervical CT examinations and classification of calcium score on coronary calcifications from thoracic CT examinations. A total of 2076 medical examinations were included in the database for the three challenges, in three months, by 18 different centers, of which 12% were excluded. The 39 participants were divided into six multidisciplinary teams among which the coronary calcification score challenge was solved with a concordance index > 95%, and the other two with scores of 67% (breast nodule classification) and 63% (neck lymph node calcifications).