An Efficient Fully Automated Detection of Mucormycosis Using Three-Dimensional Deep Learning on Computer Tomography Studies

In recent days, many people die of pulmonary embolism (PE) complications, respiratory problems that form in the deep lung. Covid-19 is the leading cause of preventable hospital death for trauma patients and despite 0.1% of the population receiving a new diagnosis annually. Developing computer-aided detection (CAD) systems would alleviate these concerns; however, current systems classify computed tomography (CT) slices individually and yield many false positives from Covid-19. We have done a retrospective study on a dataset collected from various health central hospitals. There is a continued need for tools that can predict Covid and black fungal in hospitalized patients. It affects an estimated 3000–6000 Individuals just in recent days. This can cause considerable morbidity and mortality. For segmentation and classification, we mortality. For segmentation and classification, we use a 2D Dense-Net. By developing more effective detection algorithms, we hope to ensure a more frequent and accurate diagnosis of covid, thereby reducing its high mortality rate. Reports have shown that black fungus is steadily increasing in India as well as the death toll it causes. It has been called ‘a pandemic within the Covid-19 pandemic’ by medical specialists. Black fungus, or Mucormycosis, is a complication caused by a fungal infection. In India Mucormycosis has been detected in Karnataka, Uttarakhand, Telangana, Madhya Pradesh, Andhra Pradesh, Haryana, and Bihar, Primarily, fungal spores floating in the environment gives people this infection. This spreads through contact. The fungi sticks to a body part and travels inside through the nose, lungs or sinus.