Search PubMed⌕ Search

Biomedical subjects

James Farmer

Publications and source records attributed to James Farmer.

2 recordsLinked to original sources

Conjunctival T-cell lymphoma: a clinicopathologic case report.

OBJECTIVE: To report a patient with conjunctival T-cell lymphoma, an extremely rare entity. DESIGN: Single case report. METHODS: Based on clinical examination, an excisional biopsy and immunostaining were performed on the conjunctival lesion. For management, we excised and performed triple freeze-thaw cryotherapy to the involved area, and we consulted the oncology service. MAIN OUTCOME MEASURES: T-cell and B-cell markers, and clinical examination of the lesion. RESULTS: Both examination and laboratory assessment revealed no evidence of systemic involvement. Conjunctival biopsy showed expansion of the substantia propria with an infiltrate of chronic inflammatory cells (including lymphocytes, plasma cells, and eosinophils), and prominent lymphocyte exocytosis with reactive epithelial changes. The CD-45 RO (T-cell marker) was strongly positive, whereas the CD-20 (B-cell marker) was negative. The T-cell receptor gene rearrangement was positive with beta clonality, confirming the diagnosis of T-cell lymphoma. CONCLUSIONS: T-cell lymphoma is a rare but possible diagnosis of gelatinous conjunctival lesions. The oncology consultants were reluctant to treat the patient with systemic chemotherapy or radiation because extraconjunctival extension could never be documented. The answer to the question of what is the most appropriate treatment for conjunctival T-cell lymphoma remains unknown.

Antigens, CD20↗

An Efficient EM-based Training Algorithm for Feedforward Neural Networks.

A fast training algorithm is developed for two-layer feedforward neural networks based on a probabilistic model for hidden representations and the EM algorithm. The algorithm decomposes training the original two-layer networks into training a set of single neurons. The individual neurons are then trained via a linear weighted regression algorithm. Significant improvement on training speed has been made using this algorithm for several bench-mark problems. Copyright 1997 Elsevier Science Ltd. All Rights Reserved.

Journal Article↗