Deep Learning based HEp-2 Image Classification: A Comprehensive Review

•Deep learning based HEp-2 image classification has attracted increasing attention recently and it has great potential for practical applications.•This paper provides a comprehensive review of existing deep learning based HEp-2 image classification methods by organizing them in a deep network usage based taxonomy.•In the literature, deep learning is used for performing HEp-2 image classification in two levels, namely, cell-level and specimen-level. This paper covers the literature at both levels.•The common HEp-2 benchmark datasets are surveyed and their evaluation protocols are discussed.•The ongoing trends of deep learning research in HEp-2 image classification are summarized, and the key issues and future research directions are discussed.