用可动态适配的神经元胞自动机，实现医疗影像持续学习中的知识保留与更新
NCAdapt: Dynamic adaptation with domain-specific Neural Cellular Automata for continual hippocampus segmentation
- 基于领域特异的多头结构，在神经元胞自动机中加入可调卷积层
- 仅训练384参数的新卷积层，实现新领域适应且不破坏已有知识
- 轻量高效，性能超越现有先进持续学习方法，适合医疗影像场景
医学影像中的持续学习（CL）面临独特挑战：模型需在不断学习新领域的同时保持已有知识。本文提出NCAdapt，一种基于神经元胞自动机（NCA）的方法。该方法采用领域特异的多头结构，为每个新领域在NCA主干中集成可调节卷积层。初始训练完成后，冻结NCA主干，仅训练新增的384参数可调卷积层及对应领域特定的NCA卷积。在海马体分割任务上，NCAdapt对比了终身nnU-Net和U-Net等先进持续学习方法，表现出最先进性能。其轻量化设计有效应对医学影像持续学习挑战。论文接受后将公开代码，以支持复现和推动该领域发展。
原文摘要 · Abstract (English)
Continual learning (CL) in medical imaging presents a unique challenge, requiring models to adapt to new domains while retaining previously acquired knowledge. We introduce NCAdapt, a Neural Cellular Automata (NCA) based method designed to address this challenge. NCAdapt features a domain-specific multi-head structure, integrating adaptable convolutional layers into the NCA backbone for each new domain encountered. After initial training, the NCA backbone is frozen, and only the newly added adaptable convolutional layers, consisting of 384 parameters, are trained along with domain-specific NCA convolutions. We evaluate NCAdapt on hippocampus segmentation tasks, benchmarking its performance against Lifelong nnU-Net and U-Net models with state-of-the-art (SOTA) CL methods. Our lightweight approach achieves SOTA performance, underscoring its effectiveness in addressing CL challenges in medical imaging. Upon acceptance, we will make our code base publicly accessible to support reproducibility and foster further advancements in medical CL.
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。