Granulomatous inflammation is a histologic pattern of tissue reaction which appears following cell injury. Granulomatous inflammation is caused by a variety of conditions including infection, autoimmune, toxic, allergic, drug, and neoplastic conditions. The tissue reaction pattern narrows the pathologic and clinical differential diagnosis and subsequent clinical management. Common reaction patterns include necrotizing granulomas, non necrotizing granulomas, suppurative granulomas, diffuse granulomatous inflammation, and foreign body giant cell reaction. Prototypical examples of necrotizing granulomas are seen with mycobacterial infections and non-necrotizing granulomas with sarcoidosis. However, broad differential diagnoses exist within each category. Using a pattern based algorithmic approach, identification of the etiology becomes apparent when taken with clinical context.The pulmonary system is one of the most commonly affected sites to encounter granulomatous inflammation. Infectious causes of granuloma are most prevalent with mycobacteria and dimorphic fungi leading the differential diagnoses. Unlike the lung, skin can be affected by several routes, including direct inoculation, endogenous sources, and hematogenous spread. This broad basis of involvement introduces a variety of infectious agents, which can present as necrotizing or non-necrotizing granulomatous inflammation. Non-infectious etiologies require a thorough clinicopathologic review to narrow the scope of the pathogenesis which include: foreign body reaction, autoimmune, neoplastic, and drug related etiologies. Granulomatous inflammation of the kidney, often referred to as granulomatous interstitial nephritis (GIN) is unlike organ systems such as the skin or lungs. The differential diagnosis of GIN is more frequently due to drugs and sarcoidosis as compared to infections (fungal and mycobacterial).Herein we discuss the pathogenesis and histologic patterns seen in a variety of organ systems and clinical conditions.

No abstract

Whole-slide images (WSIs) are a rich new source of biomedical imaging data. The use of automated systems to classify and segment WSIs has recently come to forefront of the pathology research community. While digital slides have obvious educational and clinical uses, their most exciting potential lies in the application of quantitative computational tools to automate search tasks, assist in classic diagnostic classification tasks, and improve prognosis and theranostics. An essential step in enabling these advancements is to apply advances in machine learning and artificial intelligence from other fields to previously inaccessible pathology datasets, thereby enabling the application of new technologies to solve persistent diagnostic challenges in pathology. Here, we applied convolutional neural networks to differentiate between two forms of melanocytic lesions (Spitz and conventional). Classification accuracy at the patch level was 99.0%–2% when applied to WSI. Importantly, when the model was trained without careful image curation by a pathologist, the training took significantly longer and had lower overall performance. These results highlight the utility of augmented human intelligence in digital pathology applications, and the critical role pathologists will play in the evolution of computational pathology algorithms.