<h4>Background</h4>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.<h4>Methods</h4>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.<h4>Finding</h4>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).<h4>Interpretation</h4>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.<h4>Funding</h4>None.

The spleen plays a dual role of immune response and the filtration of red blood cells (RBC), the latter function being performed within the unique microcirculatory architecture of the red pulp. The red pulp filters and eliminates senescent and pathological RBC and can expell intra-erythrocytic rigid bodies through the so-called pitting mechanism. The loss of splenic function increases the risk of infections, thromboembolism, and hematological malignancies. However, current diagnostic tests such as quantification of Howell-Jolly Bodies and splenic scintigraphy lack sensitivity or are logistically demanding. Although not widely available in medical practice, the quantification of RBC containing vacuoles, i.e., pocked RBC, is a highly sensitive and specific marker for hyposplenism. The peripheral blood of hypo/asplenic individuals contains up to 80% RBC with vacuoles, whereas these pocked RBC account for less than 4% of RBC in healthy subjects. Despite their value as a spleen function test, intraerythrocytic vacuoles have received relatively limited attention so far, and little is known about their origin, content, and clearance. We provide an overview of the current knowledge regarding possible origins and mechanisms of elimination, as well as the potential function of these unique and original organelles observed in otherwise “empty” mature RBC. We highlight the need for further research on pocked RBC, particularly regarding their potential function and specific markers for easy counting and sorting, which are prerequisites for functional studies and wider application in medical practice.