Condition Generative Adversarial Network Deep Learning Model for Accurate Segmentation and Volumetric Measurement to Detect Mucormycosis from Lung CT Images

Introduction Mucormycosis (black fungal attack) has recently been identified as a significant threat, specifically to patients who have recovered from coronavirus infection. This fungus enters the body through the nose and first infects the lungs but can affect other body parts, such as the eye and brain, resulting in vision loss and death. Early detection through lung CT scans is crucial for reliable treatment planning and management. Methods To combat the above problems, this paper introduces a Condition Generative Adversarial Network Deep Learning Model (CGAN-DLM) to facilitate the automatic lung CT image segmentation process, contributing to accurately identifying Mucormycosis earlier. This deep learning model employed different pre-processing strategies over raw lung CT images for extracting its ground truth values based on potential morphological operations. It adopted CGAN to segment the region of interest used for diagnosing mucormycosis with the pre-processed images and their related truth values. Results It also included a volumetric assessment approach that significantly identified the change in lung nodule size before and after the infection of mucormycosis. Conclusion The extensive experiments of the proposed CGAN-DLM conducted using lung CT images taken from the LIDC-IDRI database confirmed sensitivity of 98.42%, specificity of 98.86% and dice coefficient index of 97.31%, on par with the benchmarked lung CT images-based Mucormycosis detection approaches.