RESUMEN
Autoimmune bullous dermatoses (AIBD) are rare diseases that affect human skin and mucous membranes. Clinically, they are characterized by blister formation and/or erosions. Depending on the structures involved and the depth of blister formation, they are grouped into pemphigus diseases, pemphigoid diseases, and dermatitis herpetiformis. Classification of AIBD into their sub-entities is crucial to guide treatment decisions. One of the most sensitive screening methods for initial differentiation of AIBD is the indirect immunofluorescence (IIF) microscopy on tissue sections of monkey esophagus and primate salt-split skin, which are used to detect disease-specific autoantibodies. Interpretation of IIF patterns requires a detailed examination of the image by trained professionals automating this process is a challenging task with these highly complex tissue substrates, but offers the great advantage of an objective result. Here, we present computer-aided classification of esophagus and salt-split skin IIF images. We show how deep networks can be adapted to the specifics and challenges of IIF image analysis by incorporating segmentation of relevant regions into the prediction process, and demonstrate their high accuracy. Using this semi-automatic extension can reduce the workload of professionals when reading tissue sections in IIF testing. Furthermore, these results on highly complex tissue sections show that further integration of semi-automated workflows into the daily workflow of diagnostic laboratories is promising.
Asunto(s)
Enfermedades Autoinmunes , Penfigoide Ampolloso , Pénfigo , Enfermedades Cutáneas Vesiculoampollosas , Animales , Humanos , Técnica del Anticuerpo Fluorescente Indirecta/métodos , Vesícula , Enfermedades Autoinmunes/diagnóstico , Enfermedades Cutáneas Vesiculoampollosas/diagnósticoRESUMEN
Bullous pemphigoid (BP) is an autoimmune blistering skin disease. Autoantibodies to BP180 and BP230 can be detected by indirect immunofluorescence (IIF) on different substrates (oesophagus, salt-split-skin, BP180-antigen dots, BP230-transfected cells) and ELISA. Here, we compared test characteristics of these test systems. We analysed sera from BP patients (n=60) in whom the clinical diagnosis had been confirmed histopathologically. The control cohort comprised sera from patients with other autoimmune-associated (n=22) or inflammatory (n=35) skin diseases. All samples were tested by IIF (EUROIMMUN™ Dermatology Mosaic) and ELISA (EUROIMMUN and MBL). Anti-BP180 is best detected with BP180-antigen dots by IIF (sensitivity: 88%; specificity: 97%). As compared to IIF, the differences with both BP180 ELISA techniques are small though. Likelihood ratios (LRs) for positive and negative test results are >10 and between 0.1 and 0.2, respectively, for all test systems. Detection of anti-BP230 is highly variable (sensitivity range 38-60%; specificity range 83-98%). Only the IIF test reveals a LR for positive test results >10. Since the LRs for a negative test are all ~0.5, negative test results for anti-BP230 antibodies do not help to exclude BP. In conclusion, the multi-parameter IIF test reveals a good diagnostic performance in BP. Since this test simultaneously allows for the detection of anti-Dsg1 and anti-Dsg3 antibodies, involved in pemphigus foliaceus and vulgaris, a single test-incubation may be sufficient to differentiate between the most frequent autoimmune blistering diseases.