AI-Powered Semantic Segmentation and Fluid Volume Calculation of Lung CT images in Covid-19 Patients

TL;DR

This study presents an AI system using transfer learning and DeepLabV3+ architecture to accurately segment lung regions in CT images of COVID-19 patients and calculate infected volume, aiding clinical prioritization.

Contribution

It introduces a novel application of transfer learning with DeepLabV3+ for precise lung and infection segmentation and volume measurement in COVID-19 CT scans.

Findings

Lung mask IoU achieved 99.78%.

Infected region IoU achieved 89.01%.

Effective volume measurement of infected regions.

Abstract

COVID-19 pandemic is a deadly disease spreading very fast. People with the confronted immune system are susceptible to many health conditions. A highly significant condition is pneumonia, which is found to be the cause of death in the majority of patients. The main purpose of this study is to find the volume of GGO and consolidation of a covid-19 patient so that the physicians can prioritize the patients. Here we used transfer learning techniques for segmentation of lung CTs with the latest libraries and techniques which reduces training time and increases the accuracy of the AI Model. This system is trained with DeepLabV3+ network architecture and model Resnet50 with Imagenet weights. We used different augmentation techniques like Gaussian Noise, Horizontal shift, color variation, etc to get to the result. Intersection over Union(IoU) is used as the performance metrics. The IoU of lung masks is predicted as 99.78% and that of infected masks is as 89.01%. Our work effectively measures the volume of infected region by calculating the volume of infected and lung mask region of the patients.