Self-Paced Learning for Images of Antinuclear Antibodies

TL;DR

This paper introduces a novel self-paced learning framework for automating antinuclear antibody detection in microscopy images, effectively handling complex multi-instance, multi-label tasks without manual preprocessing, and achieving state-of-the-art results.

Contribution

It proposes a new MIML learning framework inspired by human labeling, incorporating instance sampling, pseudo-label dispatching, and self-paced training, specifically designed for ANA detection.

Findings

Achieves up to +7.0% F1-Macro and +12.6% mAP improvements over prior methods.

Ranks top-2 on public MIML benchmarks, reducing Hamming loss and one-error significantly.

Supports end-to-end optimization with superior performance on real-world ANA datasets.

Abstract

Antinuclear antibody (ANA) testing is a crucial method for diagnosing autoimmune disorders, including lupus, Sj\"ogren's syndrome, and scleroderma. Despite its importance, manual ANA detection is slow, labor-intensive, and demands years of training. ANA detection is complicated by over 100 coexisting antibody types, resulting in vast fluorescent pattern combinations. Although machine learning and deep learning have enabled automation, ANA detection in real-world clinical settings presents unique challenges as it involves multi-instance, multi-label (MIML) learning. In this paper, a novel framework for ANA detection is proposed that handles the complexities of MIML tasks using unaltered microscope images without manual preprocessing. Inspired by human labeling logic, it identifies consistent ANA sub-regions and assigns aggregated labels accordingly. These steps are implemented using three task-specific components: an instance sampler, a probabilistic pseudo-label dispatcher, and self-paced weight learning rate coefficients. The instance sampler suppresses low-confidence instances by modeling pattern confidence, while the dispatcher adaptively assigns labels based on instance distinguishability. Self-paced learning adjusts training according to empirical label observations. Our framework overcomes limitations of traditional MIML methods and supports end-to-end optimization. Extensive experiments on one ANA dataset and three public medical MIML benchmarks demonstrate the superiority of our framework. On the ANA dataset, our model achieves up to +7.0% F1-Macro and +12.6% mAP gains over the best prior method, setting new state-of-the-art results. It also ranks top-2 across all key metrics on public datasets, reducing Hamming loss and one-error by up to 18.2% and 26.9%, respectively. The source code can be accessed at https://github.com/fletcherjiang/ANA-SelfPacedLearning.