Detection of Epithelial Giant Cells in Nasal Aspirate Cytological Smears Using Deep Learning and Computer Vision Techniques: an Approach for Early Diagnosis of Measles Disease

Abstract

Measles disease is usually diagnosed through an RT-PCR test, which detects the measles-specific IgM antibody in serum samples. However, this approach is highly expensive and requires a lot of sample preprocessing making it a laborious task. Another approach for measles identification could be a cytological smear test – which is a low-cost, quick, and accurate method for the early detection of measles disease. Due to the lack of experience in interpreting smears, its usage in clinical practice is currently limited. We have designed a MesoSpot, an automatic segmentation method for the first time that can precisely define the region of giant cells in nasal aspirate cytological smears and assist medical experts in the speedy diagnosis of measles disease. MesoSpot was developed by training 500 cytological smear images collected from various web sources. We have used 50 cytological smear images to validate the model and evaluated its performance using various metrics. The main purpose of the proposed study is to detect multinucleated giant cells and estimate their size and number, which aids in assessing the disease's severity. To annotate the giant cells in each cytological smear, we have applied a semantic segmentation approach using APEER software. UNET architecture was used to train the model, and image processing techniques were used to spot giant cells and predict their size. Various performance metrics were employed to assess the model's efficiency. The model's output was also compared to the ground truth image and statistically confirmed.