Demystifying evidential Dempster Shafer-based CNN architecture for fetal plane detection from 2D ultrasound images leveraging fuzzy-contrast enhancement and explainable AI.

Ultrasound imaging is a valuable tool for assessing the development of the fetal during pregnancy. However, interpreting ultrasound images manually can be time-consuming and subject to variability. Automated image categorization using machine learning algorithms can streamline the interpretation process by identifying stages of fetal development present in ultrasound images. In particular, deep learning architectures have shown promise in medical image analysis, enabling accurate automated diagnosis. The objective of this research is to identify fetal planes from ultrasound images with higher precision. To achieve this, we trained several convolutional neural network (CNN) architectures on a dataset of 12400 images. Our study focuses on the impact of enhanced image quality by adopting Histogram Equalization and Fuzzy Logic-based contrast enhancement on fetal plane detection using the Evidential Dempster-Shafer Based CNN Architecture, PReLU-Net, SqueezeNET, and Swin Transformer. The results of each classifier were noteworthy, with PreLUNet achieving an accuracy of 91.03%, SqueezeNET reaching 91.03% accuracy, Swin Transformer reaching an accuracy of 88.90%, and the Evidential classifier achieving an accuracy of 83.54%. We evaluated the results in terms of both training and testing accuracies. Additionally, we used LIME and GradCam to examine the decision-making process of the classifiers, providing explainability for their outputs. Our findings demonstrate the potential for automated image categorization in large-scale retrospective assessments of fetal development using ultrasound imaging.

Neutrophil extracellular traps in patients with sepsis.

BACKGROUND: Release of neutrophil extracellular traps (NETs) has been identified as an important aspect of innate immunity. We examined whether sepsis had any influence on ex vivo generation of NETs by neutrophils. MATERIALS AND METHODS: We isolated neutrophils from consecutive patients with sepsis (n = 17) and without sepsis (n = 18) admitted to the intensive care unit. Neutrophils were activated by incubation with phorbol-12-myristate-13-acetate (PMA) to induce release of NETs, and NET formation was assessed by measuring the extracellular DNA level. Immunolabeling and fluorescence imaging were also performed. Extracellular killing of bacteria by NETs was studied by co-culture of Escherichia coli and neutrophils in the presence of a phagocytosis inhibitor. To assess in vivo NET formation, plasma levels of cell-free DNA and histones were measured. RESULTS: After stimulation with PMA, neutrophils isolated from septic patients released 4.08 ± 1.02% of their total DNA, whereas neutrophils from nonseptic patients released 29.06 ± 2.94% (P = <0.0001). Immunofluorescent staining of released DNA, elastase, and myeloperoxidase also revealed similar results. Neutrophils from nonseptic patients showed effective extracellular killing of E coli through NETs, whereas neutrophils from septic patients did not (P < 0.001). Plasma levels of cell-free DNA and histones were higher in septic patients than nonseptic patients (P < 0.001). CONCLUSIONS: The ex vivo generation of NETs is downregulated in neutrophils isolated from patients with sepsis. However, it is unclear whether in vivo NET formation is also impaired during sepsis, so further investigation is necessary.