Veasey Benjamin P, Amini Amir A
Medical Imaging LaboratoryUniversity of Louisville Louisville KY 40208 USA.
IEEE Open J Eng Med Biol. 2025 Jan 16;6:296-304. doi: 10.1109/OJEMB.2025.3530841. eCollection 2025.
This paper investigates using Low-Rank Adaptation (LoRA) to adapt large vision models (LVMs) pretrained with self-supervised learning (SSL) for lung nodule malignancy classification. Inspired by LoRA's success in the field of Natural Language Processing, we hypothesized that such an adaptation technique can significantly improve classification performance, parameter efficiency, and training speed for the novel application of lung image cancer diagnostic. Utilizing two comprehensive lung nodule datasets, NLSTx and LIDC, which together encompass a diverse array of biopsy- and radiologist-confirmed lung CT scans, our rigorous experimental setup demonstrates that LoRA-adapted models markedly surpass traditional fine-tuning methods. The best LoRA-adapted model achieved a 3% increase in ROC AUC over the state-of-the-art model, utilized 89.9% fewer parameters, and reduced training times by 36.5%. Integrating LoRA with out-of-domain pretrained LVMs offers a promising avenue for enhancing performance of lung nodule malignancy classification. The annotations for the NLSTx dataset are also released with this paper on GitHub at https://github.com/benVZ/NLSTx.
本文研究使用低秩自适应（LoRA）来调整通过自监督学习（SSL）预训练的大型视觉模型（LVM），以用于肺结节恶性分类。受LoRA在自然语言处理领域成功的启发，我们假设这种自适应技术可以显著提高肺图像癌症诊断这一新型应用的分类性能、参数效率和训练速度。利用两个综合肺结节数据集NLSTx和LIDC，它们共同涵盖了一系列经活检和放射科医生确认的肺部CT扫描，我们严格的实验设置表明，经LoRA调整的模型明显优于传统的微调方法。最佳的经LoRA调整的模型在ROC AUC上比最先进的模型提高了3%，使用的参数减少了89.9%，训练时间减少了36.5%。将LoRA与域外预训练的LVM集成，为提高肺结节恶性分类性能提供了一条有前景的途径。NLSTx数据集的注释也随本文在GitHub上发布，网址为https://github.com/benVZ/NLSTx。
