Gene/Protein Disease Symptom Drug Enzyme Compound
Pivot Concepts:   Target Concepts:
Query: UMLS:C0003615 (appendicitis)
 4,439 document(s) hit in 31,850,051 MEDLINE articles (0.00 seconds)

We report on the histopathologic and immunohistologic findings of two cases of suppurative granulomatous appendicitis of Yersinia enterocolitica (Y. ent.). Using formalin-fixed, paraffin-embedded materials, polymerase chain reaction revealed Y. ent. in both cases. Histologically, the epithelioid cell granulomas (EPGs) were transmural in both cases. The EPGs were predominantly nonsuppurative, and were surrounded by a lymphoid cuff composed of small lymphocytes. A portion of EPGs contained suppuration of the centers of the granulomas (central microabscesses). The EPGs were composed of numerous histiocytes with or without epithelioid cell features, along with scattered small T-lymphocytes and plasmacytoid monocytes. None of the EPGs contained monocytoid B-cells. Immunohistochemical study demonstrated that EPGs were usually surrounded by surface IgM/D+ small mantle zone lymphocytes. Moreover, CNA.42 immunostaining occasionally demonstrated residual follicular dendritic cells in the center of the EPGs. The overall histomorphologic and immunohistochemical findings demonstrated that the EPGs with Y. ent. are of the B-cell negative hypersensitivity type and occur in reactive germinal centers. In one case, regional lymph nodes contained EPGs showing the same histologic and immunohistologic findings as those of the appendix. The present study indicates that among abscesses forming epithelioid granulomatous lesions, EPGs with Y. ent. were B-cell negative granulomas, and it demonstrates histopathologic and immunohistochemical findings different from those of cat scratch disease and lymphogranuloma venerum, which contain numerous monocytoid B-cells.
 ...
PMID:Immunohistological findings of suppurative granulomas of Yersinia enterocolitica appendicitis: a report of two cases. 1718 75

The development of deep learning algorithms for complex tasks in digital medicine has relied on the availability of large labeled training datasets, usually containing hundreds of thousands of examples. The purpose of this study was to develop a 3D deep learning model, AppendiXNet, to detect appendicitis, one of the most common life-threatening abdominal emergencies, using a small training dataset of less than 500 training CT exams. We explored whether pretraining the model on a large collection of natural videos would improve the performance of the model over training the model from scratch. AppendiXNet was pretrained on a large collection of YouTube videos called Kinetics, consisting of approximately 500,000 video clips and annotated for one of 600 human action classes, and then fine-tuned on a small dataset of 438 CT scans annotated for appendicitis. We found that pretraining the 3D model on natural videos significantly improved the performance of the model from an AUC of 0.724 (95% CI 0.625, 0.823) to 0.810 (95% CI 0.725, 0.895). The application of deep learning to detect abnormalities on CT examinations using video pretraining could generalize effectively to other challenging cross-sectional medical imaging tasks when training data is limited.
 ...
PMID:AppendiXNet: Deep Learning for Diagnosis of Appendicitis from A Small Dataset of CT Exams Using Video Pretraining. 3212 25