Combining imaging flow cytometry and machine learning for high-throughput schistocyte quantification: A SVM classifier development and external validation cohort.

BACKGROUND: Schistocyte counts are a cornerstone of the diagnosis of thrombotic microangiopathy syndrome (TMA). Their manual quantification is complex and alternative automated methods suffer from pitfalls that limit their use. We report a method combining imaging flow cytometry (IFC) and artificial intelligence for the direct label-free and operator-independent quantification of schistocytes in whole blood. METHODS: We used 135,045 IFC images from blood acquisition among 14 patients to extract 188 features with IDEAS® software and 128 features from a convolutional neural network (CNN) with Keras framework in order to train a support vector machine (SVM) blood elements' classifier used for schistocytes quantification. FINDING: Keras features showed better accuracy (94.03%, CI: 93.75-94.31%) than ideas features (91.54%, CI: 91.21-91.87%) in recognising whole-blood elements, and together they showed the best accuracy (95.64%, CI: 95.39-95.88%). We obtained an excellent correlation (0.93, CI: 0.90-0.96) between three haematologists and our method on a cohort of 102 patient samples. All patients with schistocytosis (>1% schistocytes) were detected with excellent specificity (91.3%, CI: 82.0-96.7%) and sensitivity (100%, CI: 89.4-100.0%). We confirmed these results with a similar specificity (91.1%, CI: 78.8-97.5%) and sensitivity (100%, CI: 88.1-100.0%) on a validation cohort (n=74) analysed in an independent healthcare centre. Simultaneous analysis of 16 samples in both study centres showed a very good correlation between the 2 imaging flow cytometers (Y=1.001x). INTERPRETATION: We demonstrate that IFC can represent a reliable tool for operator-independent schistocyte quantification with no pre-analytical processing which is of most importance in emergency situations such as TMA. FUNDING: None.

Accurate classification of plasma cell dyscrasias is achieved by combining artificial intelligence and flow cytometry.

Monoclonal gammopathy of unknown significance (MGUS), smouldering multiple myeloma (SMM), and multiple myeloma (MM) are very common neoplasms. However, it is often difficult to distinguish between these entities. In the present study, we aimed to classify the most powerful markers that could improve diagnosis by multiparametric flow cytometry (MFC). The present study included 348 patients based on two independent cohorts. We first assessed how representative the data were in the discovery cohort (123 MM, 97 MGUS) and then analysed their respective plasma cell (PC) phenotype in order to obtain a set of correlations with a hypersphere visualisation. Cluster of differentiation (CD)27 and CD38 were differentially expressed in MGUS and MM (P < 0·001). We found by a gradient boosting machine method that the percentage of abnormal PCs and the ratio PC/CD117 positive precursors were the most influential parameters at diagnosis to distinguish MGUS and MM. Finally, we designed a decisional algorithm allowing a predictive classification ≥95% when PC dyscrasias were suspected, without any misclassification between MGUS and SMM. We validated this algorithm in an independent cohort of PC dyscrasias (n = 87 MM, n = 41 MGUS). This artificial intelligence model is freely available online as a diagnostic tool application website for all MFC centers worldwide (https://aihematology.shinyapps.io/PCdyscrasiasToolDg/).

Platelet Counting: Ugly Traps and Good Advice. Proposals from the French-Speaking Cellular Hematology Group (GFHC).

Despite the ongoing development of automated hematology analyzers to optimize complete blood count results, platelet count still suffers from pre-analytical or analytical pitfalls, including EDTA-induced pseudothrombocytopenia. Although most of these interferences are widely known, laboratory practices remain highly heterogeneous. In order to harmonize and standardize cellular hematology practices, the French-speaking Cellular Hematology Group (GFHC) wants to focus on interferences that could affect the platelet count and to detail the verification steps with minimal recommendations, taking into account the different technologies employed nowadays. The conclusions of the GFHC presented here met with a "strong professional agreement" and are explained with their rationale to define the course of actions, in case thrombocytopenia or thrombocytosis is detected. They are proposed as minimum recommendations to be used by each specialist in laboratory medicine who remains free to use more restrictive guidelines based on the patient's condition.

Pan-HDAC Inhibitors Restore PRDM1 Response to IL21 in CREBBP-Mutated Follicular Lymphoma.

PURPOSE: Follicular lymphoma arises from a germinal center B-cell proliferation supported by a bidirectional crosstalk with tumor microenvironment, in particular with follicular helper T cells (Tfh). We explored the relation that exists between the differentiation arrest of follicular lymphoma cells and loss-of-function of CREBBP acetyltransferase.Experimental Design: The study used human primary cells obtained from either follicular lymphoma tumors characterized for somatic mutations, or inflamed tonsils for normal germinal center B cells. Transcriptome and functional analyses were done to decipher the B- and T-cell crosstalk. Responses were assessed by flow cytometry and molecular biology including ChIP-qPCR approaches. RESULTS: Conversely to normal B cells, follicular lymphoma cells are unable to upregulate the transcription repressor, PRDM1, required for plasma cell differentiation. This defect occurs although the follicular lymphoma microenvironment is enriched in the potent inducer of PRDM1 and IL21, highly produced by Tfhs. In follicular lymphoma carrying CREBBP loss-of-function mutations, we found a lack of IL21-mediated PRDM1 response associated with an abnormal increased enrichment of the BCL6 protein repressor in PRDM1 gene. Moreover, in these follicular lymphoma cells, pan-HDAC inhibitor, vorinostat, restored their PRDM1 response to IL21 by lowering BCL6 bound to PRDM1. This finding was reinforced by our exploration of patients with follicular lymphoma treated with another pan-HDAC inhibitor. Patients showed an increase of plasma cell identity genes, mainly PRDM1 and XBP1, which underline the progression of follicular lymphoma B cells in the differentiation process. CONCLUSIONS: Our data uncover a new mechanism by which pan-HDAC inhibitors may act positively to treat patients with follicular lymphoma through the induction of the expression of plasma cell genes.