(1) Background: Kaposi’s sarcoma (KS) is an angioproliferative neoplasm typically appearing as angiomatous patches, plaques, and/or nodules on the skin. Dermoscopy and ultrasonography have been suggested as an aid in the diagnosis of KS, but there is little evidence in the literature, especially regarding its possible differential diagnoses. Our aim is to describe and compare the clinical, dermoscopic, and ultrasonographic features of KS and KS-like lesions. (2) Methods: we conducted a prospective study on 25 consecutive patients who were first referred to our tertiary care center from January to May 2021 for a possible KS. (3) Results: 41 cutaneous lesions were examined by means of dermoscopy, Doppler ultrasonography, and pathology, 32 of which were KS-related, while the remaining 9 were lesions with clinical resemblance to KS. On dermoscopy, a purplish-red pigmentation, scaly surface, and the collarette sign were the most common features among KS lesions (81.3%, 46.9%, and 28.1%, respectively). On US, all 9 KS plaques and 21 KS nodules presented a hypoechoic image. Dermoscopic and Doppler ultrasonographic findings of KS-like lesions, such as cherry angioma, venous lake, glomus tumor, pyogenic granuloma, and angiosarcoma were also analyzed. (4) Conclusions: dermoscopy and Doppler ultrasonography can be useful to better assess the features of KS lesions and in diagnosing equivocal KS-like lesions.

Leprosy is a chronic neglected infectious disease that affects over 200,000 people each year and causes disabilities in more than four million people in Asia, Africa, and Latin America. The disease can appear with a wide spectrum of clinical forms, and therefore the clinical suspicion is often difficult. Refugees and migrants from endemic countries affected by leprosy can remain undiagnosed in Europe due to the unpreparedness of clinicians. We retrospectively describe the characteristics of 55 refugees/migrants with a diagnosis of leprosy established in Italy from 2009 to 2018. Continents of origin were Africa (42%), Asia (40%), and South and Central America (18%). The symptoms reported were skin lesions (91%), neuropathy (71%), edema (7%), eye involvement (6%), fever (6%), arthritis (4%), and lymphadenopathy (4%). Seven patients (13%) had irreversible complications. Overall, 35% were relapses and 66% multibacillary leprosy. Furthermore, we conducted a review of 17 case reports or case series and five nationwide reports, published in the same decade, describing 280 migrant patients with leprosy in Europe. In Europe, leprosy is a rare chronic infectious disease, but it has not completely disappeared. Diagnosis and treatment of leprosy in refugees and migrants from endemic countries are a challenge. European guidelines for this neglected disease in this high-risk population would be beneficial.

Alzheimer's disease (AD) is the most common age-related dementia. Mild cognitive impairment (MCI) is the early stage of cognitive decline before AD. It is crucial to predict the MCI-to-AD conversion for precise management, which remains challenging due to the diversity of patients. Previous evidence shows that the brain network generated from diffusion MRI promises to classify dementia using deep learning. However, the limited availability of diffusion MRI challenges the model training. In this study, we develop a self-supervised contrastive learning approach to generate structural brain networks from routine anatomical MRI under the guidance of diffusion MRI. The generated brain networks are applied to train a learning framework for predicting the MCI-to-AD conversion. Instead of directly modelling the AD brain networks, we train a graph encoder and a variational autoencoder to model the healthy ageing trajectories from brain networks of healthy controls. To predict the MCI-to-AD conversion, we further design a recurrent neural networks based approach to model the longitudinal deviation of patients' brain networks from the healthy ageing trajectory. Numerical results show that the proposed methods outperform the benchmarks in the prediction task. We also visualize the model interpretation to explain the prediction and identify abnormal changes of white matter tracts.