Indore: The Indian Institute of Technology (IIT), Indore IIT has collaborated with an Indore-based hospital and a medical college in Odisha to develop a Artificial intelligence (AI) based method to read computed tomography of the lungs ground glass opacity with greater than 90 percent accuracy.
IIT-I in association with the Kalinga Institute of Medical SciencesOdisha, and Choithram Hospital and Research Centre, Indore have used deep learning to improve the accuracy of lung CT scan reading which will aid in the early detection of lung involvement in inflammation-mediated disease.
The method developed using deep learning provides the CT scan score in decimal points, improving the accuracy of the reading by more than 90 percent of the researchers claimed. The researchers used a U-Net-based 2D deep learning approach to develop 2D images to segment the lungs and detect ground glass opacity (GGO) in specific lobes.
The research was conducted by Associate Professors Dr. Hem Chandra Jha and Dr. M Tanveer at IIT Indore, Dr. Nirmal Kumar Mohakudteacher of the Kalinga Institute of Medical Sciences and Dr. Suchita Jain of Coithram Hospital and Research Center.
The researchers have studied 380 CT scans of COVID-19 positive patients to carry out the research and claim that the AI-based method will overcome the limitations of manual CT scan reading methods.
Jha said: “The inflammation-mediated disease effect can initially start in the right lobe region of the lungs and subsequently affect the rest of the lungs. Our AI-based method can be useful in early detection of lung involvement and also increase accuracy.”
Jha said samples were collected from more than 1,100 COVID-19 patients for the study. “Study on large geographically diverse populations may help to understand the association of biochemical parameters and GGO pattern in lung lobes with different SARS-CoV-2 variants,” Jha said.
