Adaptive Few-Shot Learning PoC Ultrasound COVID-19 Diagnostic System
This addresses the need for scalable diagnostic tools in resource-limited healthcare environments, though it appears incremental as it adapts existing few-shot learning methods to a specific medical application.
The paper tackles the problem of diagnosing COVID-19 using ultrasound imaging in point-of-care settings with limited data, by developing a few-shot learning system that achieves appropriate efficiency and accuracy for distinguishing COVID-19, pneumonia, and healthy states.
This paper presents a novel ultrasound imaging point-of-care (PoC) COVID-19 diagnostic system. The adaptive visual diagnostics utilize few-shot learning (FSL) to generate encoded disease state models that are stored and classified using a dictionary of knowns. The novel vocabulary based feature processing of the pipeline adapts the knowledge of a pretrained deep neural network to compress the ultrasound images into discrimative descriptions. The computational efficiency of the FSL approach enables high diagnostic deep learning performance in PoC settings, where training data is limited and the annotation process is not strictly controlled. The algorithm performance is evaluated on the open source COVID-19 POCUS Dataset to validate the system's ability to distinguish COVID-19, pneumonia, and healthy disease states. The results of the empirical analyses demonstrate the appropriate efficiency and accuracy for scalable PoC use. The code for this work will be made publicly available on GitHub upon acceptance.