Scale-Aware Curriculum Learning for Ddata-Efficient Lung Nodule Detection with YOLOv11

TL;DR

This paper introduces Scale Adaptive Curriculum Learning (SACL), a dynamic training strategy for lung nodule detection that adapts to limited data scenarios, improving model performance without architectural changes.

Contribution

SACL is a novel, scale-aware curriculum learning method that dynamically adjusts training based on data availability, enhancing lung nodule detection in data-scarce environments.

Findings

SACL achieves comparable performance to static curriculum on full datasets.

SACL significantly outperforms baseline in limited data conditions.

Improvements of 4.6%, 3.5%, and 2.0% in mAP50 at 10%, 20%, and 50% data.

Abstract

Lung nodule detection in chest CT is crucial for early lung cancer diagnosis, yet existing deep learning approaches face challenges when deployed in clinical settings with limited annotated data. While curriculum learning has shown promise in improving model training, traditional static curriculum strategies fail in data-scarce scenarios. We propose Scale Adaptive Curriculum Learning (SACL), a novel training strategy that dynamically adjusts curriculum design based on available data scale. SACL introduces three key mechanisms:(1) adaptive epoch scheduling, (2) hard sample injection, and (3) scale-aware optimization. We evaluate SACL on the LUNA25 dataset using YOLOv11 as the base detector. Experimental results demonstrate that while SACL achieves comparable performance to static curriculum learning on the full dataset in mAP50, it shows significant advantages under data-limited conditions with 4.6%, 3.5%, and 2.0% improvements over baseline at 10%, 20%, and 50% of training data respectively. By enabling robust training across varying data scales without architectural modifications, SACL provides a practical solution for healthcare institutions to develop effective lung nodule detection systems despite limited annotation resources.