ABSTRACT
The year 2019 brought the once in hundred years’ experience for the whole world. COVID-19 pandemic shaken almost all segments of everyone’s life and scientists all over the world are engaged in saving our existence. As there is a need of capturing microstructural changes like tumor boundary pixel level shifts and/or growth, deep learning can be a very promising to identify the pixel level changes occurred in brain MR images. The multi-layer execution using CNN architecture is possible, but there is a need for fast convolution and de-convolution with lowered strides. Conventional methods can provide acceptable results, but to identify the microstructural changes in (COVID-19 patient) MR image, accuracy and visibility at pixel level need to be very precise. Hence, this paper presents the methodology for analysis of pre- and post-COVID-19 brain tumor microstructures by means of development of novel CNNPostCoV deep learning algorithm. Proposed research uses IIARD-19 and IIARD-20 dataset of COVID-19 patient. Algorithm framed with convolution neural network architecture which provides better performance of dice score, sensitivity, and PPV parameters. Paper also presents the training and validation analysis for HGG, LGG, and combined dataset of multi-modal brain tumors. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.