Search

The World Health Organization (WHO) has clear guidelines regarding the use of Ki67 index in defining the proliferative rate and assigning grade for pancreatic neuroendocrine tumor (NET). WHO mandates the quantification of Ki67 index by counting at least 500 positive tumor cells in a hotspot. Unfortunately, Ki67 antibody may stain both tumor and non-tumor cells as positive depending on the phase of the cell cycle. Likewise, the counter stain labels both tumor and non-tumor as negative. This non-specific nature of Ki67 stain and counter stain therefore hinders the exact quantification of Ki67 index. To address this problem, we present a deep learning method to automatically differentiate between NET and non-tumor regions based on images of Ki67 stained biopsies. Transfer learning was employed to recognize and apply relevant knowledge from previous learning experiences to differentiate between tumor and non-tumor regions. Transfer learning exploits a rich set of features previously used to successfully categorize non-pathology data into 1,000 classes. The method was trained and validated on a set of whole-slide images including 33 NETs subject to Ki67 immunohistochemical staining using a leave-one-out cross-validation. When applied to 30 high power fields (HPF) and assessed against a gold standard (evaluation by two expert pathologists), the method resulted in a high sensitivity of 97.8% and specificity of 88.8%. The deep learning method developed has the potential to reduce pathologists’ workload by directly identifying tumor boundaries on images of Ki67 stained slides. Moreover, it has the potential to replace sophisticated and expensive imaging methods which are recently developed for identification of tumor boundaries in images of Ki67-stained NETs. [ABSTRACT FROM AUTHOR]

Background: Small glomerular IgA deposits have been reported in patients with liver cirrhosis, mainly as an incidental finding in autopsy studies. We recently encountered nine cirrhotic patients who presented with acute proliferative glomerulonephritis with unusually large, exuberant glomerular immune complex deposits, in the absence of systemic lupus erythematosus (SLE) or monoclonal gammopathy-related kidney disease. Deposits were typically IgA dominant/codominant. Our aim was to further elucidate the etiology, diagnostic pitfalls, and clinical outcomes. Methods: We present clinical features and kidney biopsy findings of nine cirrhotic patients with an unusual acute immune complex glomerulonephritis. We also identified native kidney biopsies from all patients with liver cirrhosis at our institution over a 13-year period (January 2004 to December 2016) to evaluate presence of glomerular IgA deposits in them (n = 118). Results: Six of nine cirrhotic patients with the large immune deposits had a recent/concurrent acute bacterial infection, prompting a diagnosis of infection-associated glomerulonephritis and treatment with antibiotics. In the remaining three patients, no infection was identified and corticosteroids were initiated. Three of nine patients recovered kidney function (one recovered kidney function after liver transplant); three patients developed chronic kidney disease but remained off dialysis; two patients became dialysis-dependent and one patient developed sepsis and expired shortly after biopsy. Within the total cohort of 118 patients with cirrhosis, 67 others also showed IgA deposits, albeit small; and 42 patients had no IgA deposits. Conclusions: These cases provide support to the theory that liver dysfunction may compromise clearance of circulating immune complexes, enabling deposition in the kidney. At least in a subset of cirrhotic patients, a superimposed bacterial infection may serve as a “second-hit” and lead to acute glomerulonephritis with exuberant immune complex deposits. Therefore, a trial of antibiotics is recommended and caution is advised before immunosuppressive treatment is offered. Unfortunately, most of these patients have advanced liver failure; therefore both diagnosis and management remain a challenge. [ABSTRACT FROM AUTHOR]