[论文解读] The Little W-Net That Could: State-of-the-Art Retinal Vessel Segmentation with Minimalistic Models
本文提出了一种极简主义的W-Net架构,参数量相比当前最先进模型减少了数个数量级,但在多个基准数据集上实现了最先进水平的视网膜血管分割性能。尽管结构简单,该极简W-Net在AUC和DICE分数上均优于复杂模型,同时在资源受限环境中的部署效率极高。
The segmentation of the retinal vasculature from eye fundus images represents one of the most fundamental tasks in retinal image analysis. Over recent years, increasingly complex approaches based on sophisticated Convolutional Neural Network architectures have been slowly pushing performance on well-established benchmark datasets. In this paper, we take a step back and analyze the real need of such complexity. Specifically, we demonstrate that a minimalistic version of a standard U-Net with several orders of magnitude less parameters, carefully trained and rigorously evaluated, closely approximates the performance of current best techniques. In addition, we propose a simple extension, dubbed W-Net, which reaches outstanding performance on several popular datasets, still using orders of magnitude less learnable weights than any previously published approach. Furthermore, we provide the most comprehensive cross-dataset performance analysis to date, involving up to 10 different databases. Our analysis demonstrates that the retinal vessel segmentation problem is far from solved when considering test images that differ substantially from the training data, and that this task represents an ideal scenario for the exploration of domain adaptation techniques. In this context, we experiment with a simple self-labeling strategy that allows us to moderately enhance cross-dataset performance, indicating that there is still much room for improvement in this area. Finally, we also test our approach on the Artery/Vein segmentation problem, where we again achieve results well-aligned with the state-of-the-art, at a fraction of the model complexity in recent literature. All the code to reproduce the results in this paper is released.
研究动机与目标
- 挑战当前视网膜血管分割任务中深度学习模型过度复杂的趋势。
- 评估极简架构是否能够达到或超越复杂、最先进的模型性能。
- 迄今为止最全面的跨数据集视网膜血管分割评估,涵盖10个不同的数据库。
- 研究当前模型在跨领域泛化方面的局限性,并探索领域自适应策略。
- 将极简方法扩展至动脉/静脉分割任务,以更少的模型复杂度取得具有竞争力的结果。
提出的方法
- 提出一种仅含68K可学习参数的极简W-Net变体,源自标准U-Net但深度和宽度均有所减少。
- 采用自标签策略,通过利用目标领域中的未标注数据来提升跨数据集泛化能力。
- 使用标准训练流程,包括交叉熵损失和数据增强,推理阶段采用测试时增强。
- 通过自助抽样法进行严格评估,以检验性能差异的统计显著性。
- 将极简W-Net与更大的U-Net(76K参数)进行对比,验证架构设计优于参数数量本身带来的优势。
- 发布所有代码和训练好的模型,以确保可复现性并促进未来研究。
实验结果
研究问题
- RQ1一个参数显著更少的极简深度学习模型是否能在视网膜血管分割任务中实现最先进性能?
- RQ2在多样化数据集上,极简W-Net与近期发表的更复杂架构相比,性能如何?
- RQ3当在与训练分布不同的数据集上测试时,模型泛化能力下降的程度如何?
- RQ4仅通过简单自标签策略,是否可在无需额外标注的情况下提升跨数据集性能?
- RQ5尽管在标准基准上表现优异,视网膜血管分割任务是否仍对领域自适应技术开放?
主要发现
- 极简W-Net在DRIVE数据集上取得82.82的DICE分数,在CHASE-DB上为81.55,在HRF上为81.04,优于更大的U-Net(76K参数),并匹配或超越更复杂的模型。
- 极简W-Net在DRIVE上AUC达98.09,在CHASE-DB上为98.44,在HRF上为98.24,表现出优于现有SOTA模型的性能。
- 通过自助抽样法进行的统计分析表明,W-Net在所有数据集上的性能显著优于更大的U-Net(p < 0.05)。
- 模型仅需325KB磁盘空间,使其非常适用于便携式或嵌入式设备的部署。
- 跨数据集评估显示,当在与训练集不同的数据上测试时,性能显著下降,凸显了领域自适应的必要性。
- 自标签策略带来中等程度的跨数据集泛化性能提升,表明通过领域自适应仍有进一步优化空间。
更好的研究,从现在开始
从阅读论文到最终审阅,大幅缩短您的研究时间。
无需绑定信用卡
本解读由 AI 生成,并经人工编辑审核。