Solitary Fibrous Tumor of Parapharyngeal Space: A Rare Case Report.

Solitary fibrous tumors are rare vascular tumours, earlier referred to as hemangiopericytoma. Their occurrence in parapharyngeal space is very rare. Hence, they should also be considered in the differential diagnosis of parapharyngeal soft tissue tumours. This case is being reported to bring out an extremely rare vascular tumour at rare site and represents a surgical challenge because of difficult access in parapharyngeal space with difficult planes between tumour and rest of parapharyngeal space, approach to it is also difficult.

Aggressive Angioimmunoblastic T Cell Lymphomas (AITL) with Soft Tissue Extranodal Mass Varied Histopathological Patterns with Peripheral Blood, Bone Marrow, and Splenic Involvement and Review of Literature.

Angioimmunoblastic T cell lymphoma (AITL) is a peripheral T cell non-Hodgkin lymphoma with an aggressive fatal course and it has varied clinical presentation with an uncommon presentation when they present as soft tissue masses or when there is spill in the peripheral blood or there are composite lymphomas that are rare presentations. Common presentations include lymphadenopathy, fever and systemic symptoms, hemolytic anemias, skin rashes, and rheumatoid arthritis. The classical histopathology is absence of follicles in lymph nodes with presence of high endothelial venules and the tumor cells of small to medium-sized lymphocytes with pale cytoplasm mixed with reactive T cells. On immunohistochemistry, the cells are positive for CD3, CD4, CD10, BCL2, and CXCL13. In this observational study, the clinicopathologic presentation and the immunohistochemical profile of five cases who initially presented with a soft tissue mass which is an extremely rare presentation of this rare type of non-Hodgkin lymphoma that was diagnosed at our center with peripheral blood and bone marrow involvement and the clinicopathologic presentation, immunohistochemical profile, and response to treatment on follow-up are correlated with the literature review. One case had a fulminant and aggressive course and was fatal within 2 months of diagnosis. The rest of the four cases are on regular chemotherapy and follow-up. Our five cases had presented with soft tissue masses, two in the axillary regio,n two in the hand, and one in the scapular region with an extranodal presentation, and there was associated lymphadenopathy which developed subsequently with classic histomorphology and immunohistochemical findings. The age range was 46-54 years and all five cases were males. Three cases were with anemia (hemoglobin range 6.5-8.0 mg/dl) and all five cases were having peripheral blood plasmacytosis. Histopathology was classic with paracortical involvement with polymorphous population of cells with neoplastic lymphocytes of small and large sizes with numerous arborizing blood vessels which correspond to high endothelial venules. Microscopically, three architectural patterns; pattern I was seen in three cases (60%) and then pattern II and III in one case each (20% each). Immunohistochemistry revealed CD4+, CD8-, CXCL13+, CD10+, BCL6+, CD19, CD20, CD1a, Tdt, CD21, and CD23+ in follicular dendritic cells. AITL is a rare and aggressive non-Hodgkin lymphoma with varied clinical presentation with classic histomorphology with various patterns which may cause diagnostic dilemma and immunophenotypic findings, and prompt and early diagnosis is mandatory for institution of therapy.

Artificial Intelligence in Cytopathology: A Neural Network to Identify Papillary Carcinoma on Thyroid Fine-Needle Aspiration Cytology Smears.

INTRODUCTION: Fine-needle aspiration cytology (FNAC) for identification of papillary carcinoma thyroid is a moderately sensitive and specific modality. The present machine learning tools can correctly classify images into broad categories. Training software for recognition of papillary thyroid carcinoma on FNAC smears will be a decisive step toward automation of cytopathology. AIM: The aim of this study is to develop an artificial neural network (ANN) for the purpose of distinguishing papillary carcinoma thyroid and nonpapillary carcinoma thyroid on microphotographs from thyroid FNAC smears. SUBJECTS AND METHODS: An ANN was developed in the Python programming language. In the training phase, 186 microphotographs from Romanowsky/Pap-stained smears of papillary carcinoma and 184 microphotographs from smears of other thyroid lesions (at ×10 and ×40 magnification) were used for training the ANN. After completion of training, performance was evaluated with a set of 174 microphotographs (66 - nonpapillary carcinoma and 21 - papillary carcinoma, each photographed at two magnifications ×10 and ×40). RESULTS: The performance characteristics and limitations of the neural network were assessed, assuming FNAC diagnosis as gold standard. Combined results from two magnifications showed good sensitivity (90.48%), moderate specificity (83.33%), and a very high negative predictive value (96.49%) and 85.06% diagnostic accuracy. However, vague papillary formations by benign follicular cells identified wrongly as papillary carcinoma remain a drawback. CONCLUSION: With further training with a diverse dataset and in conjunction with automated microscopy, the ANN has the potential to develop into an accurate image classifier for thyroid FNACs.