Chest X-Rays are widely used in medicine for preliminary examination and treatment of patients.
This mainly involves taking and analyzing the X-Ray image, a menial task that is prone to human errors. To overcome the scope for error and meet the growing demand from trained radiologists, the present paper looks at a novel deep learning-based architecture Convolution Attention-based sentence REconstruction and Scoring (CARES) for the identification and localization of radiological findings in a chest X-Ray image.
In addition, the present paper proposes a novel scoring mechanism: Radiological Finding Quality Index (RFQI) that considers the exact radiological finding, localization, size/severity for each such term present in the report.
This paper also demonstrates how the proposed AI-based labeler outperforms the in-use CheXpert labeler on an inhouse curated dataset.