Covid-19 Imaging Tools: How Big Data is Big?

In this paper, considering year 2020 and Covid-19, we analyze medical imaging tools and their performance scores in accordance with the dataset size and their complexity. For this, we mainly consider AI-driven tools that employ two different types of image data, namely chest Computed Tomography (CT) and X-ray. We elaborate on their strengths and weaknesses by taking the following important factors into account: i) dataset size; ii) model fitting criteria (over-fitting and under-fitting); iii) transfer learning in the deep learning era; and iv) data augmentation. Medical imaging tools do not explicitly analyze model fitting. Also, using transfer learning, with fewer data, one could possibly build Covid-19 deep learning model but they are limited to education and training. We observe that, in both image modalities, neither the dataset size nor does data augmentation work well for Covid-19 screening purposes because a large dataset does not guarantee all possible Covid-19 manifestations and data augmentation does not create new Covid-19 cases.

Improved U-Net architecture with VGG-16 for brain tumor segmentation.

Automated assessment and segmentation of Brain MRI images facilitate towards detection of neurological diseases and disorders. In this paper, we propose an improved U-Net with VGG-16 to segment Brain MRI images and identify region-of-interest (tumor cells). We compare results of improved U-Net with a custom-designed U-Net architecture by analyzing the TCGA-LGG dataset (3929 images) from the TCI archive, and achieve pixel accuracies of 0.994 and 0.9975 from basic U-Net and improved U-Net architectures, respectively. Our results outperformed common CNN-based state-of-the-art works.