Nodular lymphocyte predominant Hodgkin lymphoma (NLPHL) represents approximately 5% of Hodgkin lymphoma and typically affects children and young adults. Although the overall prognosis is favorable, variant growth patterns in NLPHL correlate with disease recurrence and progression to T-cell/histiocyte-rich large B-cell lymphoma or frank diffuse large B-cell lymphoma (DLBCL). The diagnostic boundary between NLPHL and DLBCL can be difficult to discern, especially in the presence of variant histologies. Both diagnoses are established using morphology and immunophenotype and share similarities, including the infrequent large tumor B-cells and the lymphocyte and histiocyte-rich microenvironment. NLPHL also shows overlap with other lymphomas, particularly, classic Hodgkin lymphoma and T-cell lymphomas. Similarly, there is overlap with non-neoplastic conditions, such as the progressive transformation of germinal centers. Given the significant clinical differences among these entities, it is imperative that NLPHL and its variants are carefully separated from other lymphomas and their mimics. In this article, the characteristic features of NLPHL and its diagnostic boundaries and pitfalls are discussed. The current understanding of genetic features and immune microenvironment will be addressed, such that a framework to better understand biological behavior and customize patient care is provided.

Diffuse Large B-Cell Lymphoma (DLBCL) is the most common non-Hodgkin lymphoma. Though histologically DLBCL shows varying morphologies, no morphologic features have been consistently demonstrated to correlate with prognosis. We present a morphologic analysis of histology sections from 209 DLBCL cases with associated clinical and cytogenetic data. Duplicate tissue core sections were arranged in tissue microarrays (TMAs), and replicate sections were stained with H&E and immunohistochemical stains for CD10, BCL6, MUM1, BCL2, and MYC. The TMAs are accompanied by pathologist-annotated regions-of-interest (ROIs) that identify areas of tissue representative of DLBCL. We used a deep learning model to segment all tumor nuclei in the ROIs, and computed several geometric features for each segmented nucleus. We fit a Cox proportional hazards model to demonstrate the utility of these geometric features in predicting survival outcome, and found that it achieved a C-index (95% CI) of 0.635 (0.574,0.691). Our finding suggests that geometric features computed from tumor nuclei are of prognostic importance, and should be validated in prospective studies.

Context.— Myriad forces are changing teaching and learning strategies throughout all stages and types of pathology education. Pathology educators and learners face the challenge of adapting to and adopting new methods and tools. The digital pathology transformation and the associated educational ecosystem are major factors in this setting of change. Objective.— To identify and collect resources, tools, and examples of educational innovations involving digital pathology that are valuable to pathology learners and teachers at each phase of professional development. Data Sources.— Sources were a literature review and the personal experience of authors and educators. Conclusions.— High-quality digital pathology tools and resources have permeated all the major niches within anatomic pathology and are increasingly well applied to clinical pathology for learners at all levels. Coupled with other virtual tools, the training landscape in pathology is highly enriched and much more accessible than in the past. Digital pathology is well suited to the demands of peer-to-peer education, such as in the introduction of new testing, grading, or other standardized practices. We found that digital pathology was well adapted to apply our current understanding of optimal teaching strategies and was effective at the undergraduate, graduate, postgraduate, and peer-to-peer levels. We curated and tabulated many existing resources within some segments of pathology. We identified several best practices for each training or educational stage based on current materials and proposed high-priority areas for potential future development.

Biology has become a prime area for the deployment of deep learning and artificial intelligence (AI), enabled largely by the massive data sets that the field can generate. Key to most AI tasks is the availability of a sufficiently large, labeled data set with which to train AI models. In the context of microscopy, it is easy to generate image data sets containing millions of cells and structures. However, it is challenging to obtain large-scale high-quality annotations for AI models. Here, we present HALS (Human-Augmenting Labeling System), a human-in-the-loop data labeling AI, which begins uninitialized and learns annotations from a human, in real-time. Using a multi-part AI composed of three deep learning models, HALS learns from just a few examples and immediately decreases the workload of the annotator, while increasing the quality of their annotations. Using a highly repetitive use-case—annotating cell types—and running experiments with seven pathologists—experts at the microscopic analysis of biological specimens—we demonstrate a manual work reduction of 90.60%, and an average data-quality boost of 4.34%, measured across four use-cases and two tissue stain types.