用低秩适配微调大视觉模型，高效诊断放疗后肺损伤。
LoRA-fine-tuned Large Vision Models for Automated Assessment of Post-SBRT Lung Injury
- 采用低秩适配（LoRA）微调DinoV2和SwinV2模型
- 在50/75mm³图像上性能接近全量微调，训练速度提升显著
- 适合医疗影像快速部署，降低算力需求
本研究探究了低秩适配（LoRA）在微调大视觉模型（DinoV2与SwinV2）用于诊断立体定向体部放疗（SBRT）后放射性肺损伤（RILI）方面的有效性。为评估该方法的鲁棒性与效率，将LoRA与传统全量微调及仅推理（无微调）方法进行对比。使用以治疗中心为圆心、大小分别为50 mm³和75 mm³的裁剪图像，并结合不同技术将2D大视觉模型适配至3D数据，以分析模型对空间上下文的敏感性。实验结果表明，LoRA在性能上达到或优于传统微调，同时大幅降低计算开销与训练时间，所需可训练参数更少。
原文摘要 · Abstract (English)
This study investigates the efficacy of Low-Rank Adaptation (LoRA) for fine-tuning large Vision Models, DinoV2 and SwinV2, to diagnose Radiation-Induced Lung Injury (RILI) from X-ray CT scans following Stereotactic Body Radiation Therapy (SBRT). To evaluate the robustness and efficiency of this approach, we compare LoRA with traditional full fine-tuning and inference-only (no fine-tuning) methods. Cropped images of two sizes (50 mm3 and 75 mm3), centered at the treatment isocenter, in addition to different adaptation techniques for adapting the 2D LVMs for 3D data were used to determine the sensitivity of the models to spatial context. Experimental results show that LoRA achieves comparable or superior performance to traditional fine-tuning while significantly reducing computational costs and training times by requiring fewer trainable parameters.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。