Search

* Context.--Large cell transformation (LCT) of indolent Bcell lymphomas, such as follicular lymphoma (FL) and chronic lymphocytic leukemia (CLL), signals a worse prognosis, at which point aggressive chemotherapy is initiated. Although LCT is relatively straightforward to diagnose in lymph nodes, a marrow biopsy is often obtained first given its ease of procedure, low cost, and low morbidity. However, consensus criteria for LCT in bone marrow have not been established. Objective.--To study the accuracy and reproducibility of a trained convolutional neural network in identifying LCT, in light of promising machine learning tools that may introduce greater objectivity to morphologic analysis. Design.--We retrospectively identified patients who had a diagnosis of FL or CLL who had undergone bone marrow biopsy for the clinical question of LCT. We scored morphologic criteria and correlated results with clinical disease progression. In addition, whole slide scans were annotated into patches to train convolutional neural networks to discriminate between small and large tumor cells and to predict the patient's probability of transformation. Results.--Using morphologic examination, the proportion of large lymphoma cells ([greater than or equal to]10% in FL and [greater than or equal to]30% in CLL), chromatin pattern, distinct nucleoli, and proliferation index were significantly correlated with LCT in FL and CLL. Compared to pathologist-derived estimates, machine-generated quantification demonstrated better reproducibility and stronger correlation with final outcome data. Conclusions.--These histologic findings may serve as indications of LCT in bone marrow biopsies. The pathologist--augmented with machine system appeared to be the most predictive, arguing for greater efforts to validate and implement these tools to further enhance physician practice., Large cell transformation (LCT) from indolent B-cell lymphoma to diffuse large B-cell lymphoma (DLBCL) is a life-threatening complication. Patients with preceding indolent B-cell lymphomas, commonly follicular lymphoma (FL) or chronic [...]

* Context.--Immune checkpoint inhibitor (CPI) therapies are associated with multi-organ immune-related adverse events. Although colonic mucosal changes have been described, inflammatory changes incited by CPIs in the upper gastrointestinal tract have not been well characterized. Objective.--To investigate morphologic and immunologic changes incited by CPI therapy in the upper gastrointestinal tract. Design.--We compared the morphology and immune cell phenotype of gastric and duodenal biopsies from patients treated with anti-cytotoxic T-lymphocyte associated protein 4 (CTLA-4) or anti-programmed death receptor-1/programmed death ligand-1 (PD-1/PD-L1) antibodies with biopsies from patients with Helicobacter pylori gastritis, patients with celiac disease, and normal controls. Results.--Gastric biopsies from patients on CPIs showed chronic gastritis mimicking H pylori gastritis. However, CPI gastritis demonstrated greater numbers of [CD8.sup.+] intraepithelial lymphocytes, less lamina propria inflammation, fewer plasma cells and [CD20.sup.+] B cells, fewer lymphoid aggregates, and reduced CD4:CD8 ratio in both the lamina propria and the epithelial layer. There were no differences between anti-CTLA-4 and anti-PD-1/PD-L1 gastritis, except for more lymphoid aggregates in anti-PD-1/PD-L1 gastritis. Duodenal biopsies from patients on CPIs revealed chronic duodenitis with villous blunting, mimicking celiac disease. Compared with celiac disease, CPI duodenitis demonstrated higher prevalence of neutrophilic infiltrates and erosions, increased lamina propria CD3 and CD8 T cells, and reduced CD4:CD8 ratio. Upper gastrointestinal biopsies were more inflamed than concomitant colonic biopsies in the majority of patients. Conclusions.--The morphologic and immunophenotypic distinctions between CPI-associated upper gastrointestinal injuries and common infectious and autoimmune diseases may provide useful discriminators when clinicians are confronted with gastric and duodenal inflammatory changes in patients receiving CPI therapy. doi: 10.5858/arpa.2019-0700-OA, Immune checkpoint inhibitor (CPI) therapies are increasingly used in the treatment of malignant neoplasms. In the course of normal immune function, checkpoint proteins such as cytotoxic T-lymphocyte associated protein 4 [...]