用轻量微调提升脑肿瘤分割模型在非洲低资源数据上的表现
Parameter-efficient Fine-tuning for improved Convolutional Baseline for Brain Tumor Segmentation in Sub-Saharan Africa Adult Glioma Dataset
- 采用卷积适配器式参数高效微调，仅更新少量参数
- 在小样本非洲数据集上达0.80平均Dice，优于纯本地训练的0.72
- 适合医疗资源有限地区，尤其关注低算力场景下的模型部署
利用深度学习自动化脑肿瘤分割在医学影像中仍是挑战，尤其在低资源环境面临数据稀缺和域偏移问题。本文提出基于MedNeXt架构的卷积适配器式参数高效微调（PEFT）方法。以BraTS-2021为预训练数据，BraTS-Africa为微调数据（60训练/35验证），该数据集来自撒哈拉以南非洲人群，磁共振图像质量与BraTS-2021差异显著（前者仅1251训练样本）。实验表明，仅在BraTS-2021上训练的模型在BraTS-Africa上性能下降20%（平均Dice降低）。而使用PEFT结合双数据集训练后，平均Dice达到0.80，优于仅在本地数据训练的0.72。尽管其性能接近全量微调（0.77），但方差更小。进一步分析发现模型存在过度分割倾向，特异性高达0.99，敏感性仅为0.75。代码已开源。
原文摘要 · Abstract (English)
Automating brain tumor segmentation using deep learning methods is an ongoing challenge in medical imaging. Multiple lingering issues exist including domain-shift and applications in low-resource settings which brings a unique set of challenges including scarcity of data. As a step towards solving these specific problems, we propose Convolutional adapter-inspired Parameter-efficient Fine-tuning (PEFT) of MedNeXt architecture. To validate our idea, we show our method performs comparable to full fine-tuning with the added benefit of reduced training compute using BraTS-2021 as pre-training dataset and BraTS-Africa as the fine-tuning dataset. BraTS-Africa consists of a small dataset (60 train / 35 validation) from the Sub-Saharan African population with marked shift in the MRI quality compared to BraTS-2021 (1251 train samples). We first show that models trained on BraTS-2021 dataset do not generalize well to BraTS-Africa as shown by 20% reduction in mean dice on BraTS-Africa validation samples. Then, we show that PEFT can leverage both the BraTS-2021 and BraTS-Africa dataset to obtain mean dice of 0.8 compared to 0.72 when trained only on BraTS-Africa. Finally, We show that PEFT (0.80 mean dice) results in comparable performance to full fine-tuning (0.77 mean dice) which may show PEFT to be better on average but the boxplots show that full finetuning results is much lesser variance in performance. Nevertheless, on disaggregation of the dice metrics, we find that the model has tendency to oversegment as shown by high specificity (0.99) compared to relatively low sensitivity(0.75). The source code is available at https://github.com/CAMERA-MRI/SPARK2024/tree/main/PEFT_MedNeXt
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。