A novel semi-supervised learning model based on pelvic radiographs for ankylosing spondylitis diagnosis reduces 90% of annotation cost.

Objective: Our study aims to develop a deep learning-based Ankylosing Spondylitis (AS) diagnostic model that achieves human expert-level performance using only a minimal amount of labeled samples for training, in regions with limited access to expert resources.

Methods: Our semi-supervised diagnostic model for AS was developed using 5389 pelvic radiographs (PXRs) from a single medical center, collected from March 2014 to April 2022. The dataset was split into a training set and a validation set with an 8:2 ratio, allocating 431 labeled images and the remaining 3880 unlabeled images for semi-supervised learning. The model's performance was evaluated on 982 PXRs from the same center, assessing metrics such as AUC, accuracy, precision, recall, and F1 scores. Interpretability analysis was performed using explainable algorithms to validate the model's clinical applicability.

Results: Our semi-supervised learning model achieved accuracy, recall, and precision values of 0.891, 0.865, and 0.859, respectively, using only 10% of labeled data from the entire training set, surpassing human expert performance. Extensive interpretability analysis demonstrated the reliability of our model's predictions, making the deep neural network no longer a black box.

Conclusion: This study marks the first application of semi-supervised learning to diagnose AS using PXRs, achieving a 90% reduction in manual annotation costs. The model showcases robust generalization on an independent test set and delivers reliable diagnostic performance, supported by comprehensive interpretability analysis. This innovative approach paves the way for training high-performance diagnostic models on large datasets with minimal labeled data, heralding a cost-effective future for medical imaging research in big data analytics.