Enhanced framework for COVID-19 prediction with computed tomography scan images using dense convolutional neural network and novel loss function

•Proposes a Dense-CNN with novel loss function based on cross-entropy for efficient convergence.•Effective diagnosis with fewer 'false-negatives' to prevent further spread of the disease.•Loss function effectively smooth's the sharp minima with False-Negative of 6.5% for better optimization.•Prompt and effective diagnosis of COVID-19 disease to reduce the incidence of disease.