Spleen elastography in patients with Systemic sclerosis

High-resolution musculoskeletal ultrasonography and elastography for eosinophilic fasciitis diagnosis and follow-up: a case-based review

Eosinophilic fasciitis (EF) remains a rare condition without precise diagnostic criteria due to common symptoms with other autoimmune diseases requiring broad differential diagnosis. This paper describes the use of high-resolution musculoskeletal ultrasonography and elastography in the diagnosis and follow-up of eosinophilic fasciitis through the case of a 56-year-old male patient. In addition to laboratory data, instrumental data, and biopsy, musculoskeletal ultrasonography (US) was used both in the diagnostic process and in the follow-up period for an objective assessment of the changes in the patient's condition and response to treatment. The US showed disorganization of the myofibrils adjacent to the superficial fascia, edema, and thickening of the fascia and subcutaneous edema. In addition, the use of shear-wave elastography (SWE) demonstrated significantly reduced skin elasticity. High-frequency musculoskeletal ultrasound in combination with SWE is an effective method both for the diagnosis of EF and for the follow-up of the changes occurring after therapy. Based on the fact that it can easily differentiate the substrate of involvement, such as skin, subcutaneous tissue, or muscle fascia, ultrasound can be used to distinguish EF from other skin and muscle diseases.

Evaluation of a Deep Learning Algorithm for Automated Spleen Segmentation in Patients with Conditions Directly or Indirectly Affecting the Spleen

The aim of this study was to develop a deep learning-based algorithm for fully automated spleen segmentation using CT images and to evaluate the performance in conditions directly or indirectly affecting the spleen (e.g., splenomegaly, ascites). For this, a 3D U-Net was trained on an in-house dataset (n = 61) including diseases with and without splenic involvement (in-house U-Net), and an open-source dataset from the Medical Segmentation Decathlon (open dataset, n = 61) without splenic abnormalities (open U-Net). Both datasets were split into a training (n = 32.52%), a validation (n = 9.15%) and a testing dataset (n = 20.33%). The segmentation performances of the two models were measured using four established metrics, including the Dice Similarity Coefficient (DSC). On the open test dataset, the in-house and open U-Net achieved a mean DSC of 0.906 and 0.897 respectively (p = 0.526). On the in-house test dataset, the in-house U-Net achieved a mean DSC of 0.941, whereas the open U-Net obtained a mean DSC of 0.648 (p < 0.001), showing very poor segmentation results in patients with abnormalities in or surrounding the spleen. Thus, for reliable, fully automated spleen segmentation in clinical routine, the training dataset of a deep learning-based algorithm should include conditions that directly or indirectly affect the spleen.