Impact of pixel, intensity, & temporal resolution on automatic scoring of LUS from Coronavirus disease 2019 patients

With the outbreak of the COVID-19, remote diagnosis, patient monitoring, collection, and transmission of data from electronic devices is rapidly taking share in the health sector. These devices are however limited on resources like energy, memory and processing power. Consequently, it is highly relevant to investigate minimizing the data, keeping intact the information content. The objective of this study is to thus observe the impact of pixel, intensity, & temporal resolution on automated scoring of LUS data. First, 448 videos from 20 patients were normalized to a common pixel resolution, i.e., the largest found over the dataset (841 pixels/cm2). Next, pixel and intensity resolution were further reduced by down-sampling factor of 2,3, and 4, and by quantization factor of 2,4, and 8 respectively. Furthermore, number of frames were down-sampled as a function of time by factor of 1 to 10 with step-size of 1. Resampled, quantized, and temporally reduced videos were evaluated using the DL algorithm (doi: 10.1109/TMI.2020.2994459) and frame, video, and prognostic-level results were obtained. It was found that no significant change in the prognostic results is observed when the data is reduced by 32 times to its original size and by 10 times to the original number of frames.