用蒙特卡洛树搜索优化医学图像分割网络，效率更高、模型更轻。
Optimizing Neural Network Architecture for Medical Image Segmentation Using Monte Carlo Tree Search
- 用MCTS动态搜索最优网络结构，提升搜索效率。
- 在多个数据集上精度超越现有模型，参数仅0.6M，GPU内存更低。
- 适合资源受限的医疗场景，兼顾精度与部署可行性。
本文提出一种新型医学图像分割框架MNAS-Unet，结合蒙特卡洛树搜索（MCTS）与神经网络架构搜索（NAS）。MNAS-Unet通过MCTS动态探索有潜力的网络结构，显著提升架构搜索的效率与精度，并优化了DownSC与UpSC单元结构，实现快速精准的模型调整。实验表明，MNAS-Unet在PROMISE12、Ultrasound Nerve和CHAOS等多个医学图像数据集上优于NAS-Unet及其他先进模型。相比NAS-Unet，MNAS-Unet将架构搜索预算减少54%（早停于139轮而非300轮），同时构建出仅含0.6M参数的轻量级模型，且GPU内存消耗更低，进一步提升实际应用价值。结果表明，MNAS-Unet在资源受限条件下仍可实现高精度分割，兼具高效性与实用性。
原文摘要 · Abstract (English)
This paper proposes a novel medical image segmentation framework, MNAS-Unet, which combines Monte Carlo Tree Search (MCTS) and Neural Architecture Search (NAS). MNAS-Unet dynamically explores promising network architectures through MCTS, significantly enhancing the efficiency and accuracy of architecture search. It also optimizes the DownSC and UpSC unit structures, enabling fast and precise model adjustments. Experimental results demonstrate that MNAS-Unet outperforms NAS-Unet and other state-of-the-art models in segmentation accuracy on several medical image datasets, including PROMISE12, Ultrasound Nerve, and CHAOS. Furthermore, compared with NAS-Unet, MNAS-Unet reduces the architecture search budget by 54% (early stopping at 139 epochs versus 300 epochs under the same search setting), while achieving a lightweight model with only 0.6M parameters and lower GPU memory consumption, which further improves its practical applicability. These results suggest that MNAS-Unet can improve search efficiency while maintaining competitive segmentation accuracy under practical resource constraints.
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。