Automating Pitted Red Blood Cell Counts Using Deep Neural Network Analysis: A New Method for Measuring Splenic Function in Sickle Cell Anaemia.

The spleen plays an important role in the body's defence against bacterial infections. Measuring splenic function is of interest in multiple conditions, including sickle cell anaemia (SCA), where spleen injury occurs early in life. Unfortunately, there is no direct and simple way of measuring splenic function, and it is rarely assessed in clinical or research settings. Manual counts of pitted red blood cells (RBCs) observed with differential interference contrast (DIC) microscopy is a well-validated surrogate biomarker of splenic function. The method, however, is both user-dependent and laborious. In this study, we propose a new automated workflow for counting pitted RBCs using deep neural network analysis. Secondly, we assess the durability of fixed RBCs for pitted RBC counts over time. We included samples from 48 children with SCA and 10 healthy controls. Cells were fixed in paraformaldehyde and examined using an oil-immersion objective, and microscopy images were recorded with a DIC setup. Manual pitted RBC counts were performed by examining a minimum of 500 RBCs for pits, expressing the proportion of pitted RBCs as a percentage (%PIT). Automated pitted RBC counts were generated by first segmenting DIC images using a Zeiss Intellesis deep learning model, recognising and segmenting cells and pits from background. Subsequently, segmented images were analysed using a small ImageJ macro language script. Selected samples were stored for 24 months, and manual pitted RBC counts performed at various time points. When comparing manual and automated pitted RBC counts, we found the two methods to yield comparable results. Although variability between the measurements increased with higher %PIT, this did not change the diagnosis of asplenia. Furthermore, we found no significant changes in %PIT after storing samples for up to 24 months and under varying temperatures and light exposures. We have shown that automated pitted RBC counts, produced using deep neural network analysis, are comparable to manual counts, and that fixed samples can be stored for long periods of time without affecting the %PIT. Automating pitted RBC counts makes the method less time consuming and results comparable across laboratories.

Mechanisms in fluid retention - towards a mutual concept.

Fluid retention is a common and challenging condition in daily clinical practice. The normal fluid homoeostasis in the human body is based on accurately counter-balanced physiological mechanisms. When compromised fluid retention occurs and is seen in pathophysiologically different conditions such as liver cirrhosis, heart and kidney failure, and in preeclampsia. These conditions may share pathophysiological mechanisms such as functional arterial underfilling, which seems to be a mutual element in cirrhosis, cardiac failure, cardiorenal and hepatorenal syndromes, and in pregnancy. However, there are also distinct differences and it is still unclear whether kidney dysfunction or arterial underfilling is the initiating factor of fluid retention or if they happen simultaneously. This review focuses on similarities and differences in water retaining conditions and points to areas where important knowledge is still needed.

Changes in ventilatory capacity and pulmonary gas exchange during systemic and pulmonary inflammation in humans.

The exact mechanism linking the systemic inflammatory response associated with sepsis to changes in lung function remains to be determined. In a human experimental model of inflammation, we investigated how acute systemic and local pulmonary inflammation affects ventilatory capacity and pulmonary gas exchange. Fifteen volunteers received Escherichia coli lipopolysaccharide (LPS) intravenously or endobronchially on two different study days. Blood samples were obtained hourly (t = 0-8 h) and spirometry was performed at baseline and after 8 h. Both interventions decreased ventilatory capacity compared to baseline (p < 0.01), and this was more pronounced after intravenous (forced expiratory volume in 1-s, FEV1 ; 0.6 L/12% reduction) compared to endobronchial (FEV1 ; 0.32 L/7% reduction) administration (p < 0.05). Furthermore, the alveolar-arterial oxygen difference increased after intravenous but not after endobronchial endotoxin. These findings indicate that pulmonary gas exchange is impaired to a greater extent during endotoxin-induced systemic inflammation than during endotoxin-induced local pulmonary inflammation.