Application of deep learning in antinuclear antibodies classification: progress and challenges / 中华检验医学杂志

ABSTRACT

Antinuclear antibodies (ANA) testing is essential for the diagnosis, classification, and disease activity monitoring of systemic autoimmune rheumatic diseases. In recent years, with the enhancement of computing power and the innovation of algorithms, the newly hip branch, deep learning (DL), practically delivered all of the most stunning achievements and breakthroughs in artificial intelligence (AI) so far. The application of DL to visual tasks, known as computer vision, has revealed significant power within the medical image recognition. Indirect immunofluorescence on HEp-2 cells is the reference method for ANA testing, the results is interpreted manually by specialized physicians. ANA fluorescent pattern classification is based on image recognition, which has a broad prospect of combining with DL to realize automatic interpretation system. This paper reviews the recent research progress and challenges of DL in the field of ANA detection in order to provide references for the standardization of ANA testing in the future.