Follicular Lymphoma (FL) is the second most common subtype of lymphoma in the Western World. It is alow-grade lymphoma arising from Germinal Centre (GC) B cells. The neoplasm predominantly consists ofback-to-back arrangement of nodules or follicles of transformed GC B cells with the replacement of lymphnode architecture and loss of normal cortex and medullary differentiation, which is preserved in nonneoplasticor reactive lymph node. There is a growing interest in studying different cell subsets inside andon the periphery of the follicles to direct curative therapies and minimize treatment-related complications.To facilitate this analysis, we develop an automated method for follicle detection from images of CD8stained histopathological slides. The proposed method is trained on eight whole digital slides. The methodis inspired by U-net to segment follicles from the whole slide images. The results on an independent datasetresulted in an average Dice similarity coefficient of 85.6% when compared to an expert pathologist’sannotations. We expect that the method will play a considerable role for comparing the ratios of differentsubsets of cells inside and at the periphery of the follicles.
展开▼
