Renu Ethirajan
SigTuple Technologies Pvt Ltd, India
Title: Study on the performance of an artificial intelligence system for image based analysis of peripheral blood smears
Biography
Biography: Renu Ethirajan
Abstract
In this study, we evaluate SHONIT, a cloud based artificial intelligence (AI) system for automated analysis of images captured from peripheral blood smears. SHONIT’s performance in classification of WBCs was evaluated by comparing SHONIT’s results with hematology analyzers and manual microscopy for manually stained smears. The study was carried out over 100 samples. The cases included both normal and abnormal samples, wherein the abnormal cases were from patients with one or more quantitative or qualitative flagging. All the smears were created using Hemaprep auto-smearer and stained using May Grunwald Geimsa stain. They were scanned and analyzed by SHONIT for WBC differentials under 40X magnification. WBC morphological classification by SHONIT was verified by an experienced hematopathologist. Quantitative parameters were analysed by computing the mean absolute error of the WBC DC values between SHONIT and Sysmex XN3000 and between SHONIT and manual microscopy. The mean absolute error between WBC differential values of manual microscopy and SHONIT were 7.67%, 5.93%, 4.58%, 2.69%, 0.44% for neutrophil, lymphocyte, monocyte, eosinophil and basophil respectively. The mean absolute error between WBC differential values values of Sysmex XN3000 and SHONIT were 8.73%, 5.55%, 3.63%, 2.12%, 0.45% for neutrophil, lymphocyte, monocyte, eosinophil and basophil respectively. SHONIT has proven to be effective in locating and examining WBCs. It saves time, accelerates the turnaround-time and and increases productivity of pathologists. It has helped to overcome the time-consuming effort associated with traditional microscopy.