Acute Pyelonephritis and an Incidental Diagnosis.

Gastrointestinal stromal tumors (GISTs) arise from the gastrointestinal tract. In rare cases, extra-gastrointestinal stromal tumors (EGISTs) occur in the omentum, mesentery, et cetera. They are mostly asymptomatic or have unspecific symptoms. Risk stratification classification systems are based on tumor size, mitotic rate, location, and perforation. The gold standard for diagnosis is a computed tomography (CT) scan. Ultrasound/CT-guided percutaneous biopsy allows histopathology and immunochemistry results (most stain positive for CD117 (c-KIT), CD34, and/or DOG1). Mutational analysis (most are in proto-oncogene c-KIT and platelet-derived growth factor receptor A (PDGFRA)) determines appropriate therapy. Surgical resection is the gold standard of treatment, with adjuvant and neoadjuvant molecular-targeted therapies depending on recurrence risk and mutations. This report describes a rare case of GIST (omentum EGIST) with a rare presentation (acute pyelonephritis) in a 67-year-old woman. Abdominal examination showed tenderness and a positive Murphy sign on the left side. Blood analysis presented microcytic hypochromic anemia, aggravated renal function, leukocytosis, and increased C-reactive protein. Abdominal CT revealed a heterogeneous abdominal mass, and a CT-guided biopsy showed epithelioid cells positive for CD117 and DOG1, which is compatible with a GIST. The patient underwent surgery that determined the GIST's origin from the greater omentum. Histology revealed an epithelioid GIST with large dimensions and a high histologic grade. Genetic testing detected a variant in the PDGFRA gene. With a high risk of progression, the patient received a three-year course of imatinib.

Light Field Image Dataset of Skin Lesions.

Light field imaging technology has been attracting increasing interest because it enables capturing enriched visual information and expands the processing capabilities of traditional 2D imaging systems. Dense multiview, accurate depth maps and multiple focus planes are examples of different types of visual information enabled by light fields. This technology is also emerging in medical imaging research, like dermatology, allowing to find new features and improve classification algorithms, namely those based on machine learning approaches. This paper presents a contribution for the research community, in the form of a publicly available light field image dataset of skin lesions (named SKINL2 v1.0). This dataset contains 250 light fields, captured with a focused plenoptic camera and classified into eight clinical categories, according to the type of lesion. Each light field is comprised of 81 different views of the same lesion. The database also includes the dermatoscopic image of each lesion. A representative subset of 17 central view images of the light fields is further characterised in terms of spatial information (SI), colourfulness (CF) and compressibility. This dataset has high potential for advancing medical imaging research and development of new classification algorithms based on light fields, as well as in clinically-oriented dermatology studies.