结合迁移学习与类别特定解码器的腹腔镜图像分割方法
Leveraging Transfer Learning with Class-Specific Decoders for Laparoscopic Segmentation
浏览论文内容
中文总结 AI 辅助
该研究提出结合迁移学习与类别特定解码器的腹腔镜分割方法，在直肠和胆囊切除术数据集上验证了器官特定解码器模型（CEMD）的性能，其Dice系数达62.4%且收敛更快，但未解决类别不平衡问题。
中文摘要 AI 辅助
手术数据中有效的多器官分割需要学习复杂的解剖特征，并缓解类别不平衡带来的挑战，类别不平衡源于体积较小、暴露有限的结构占比相对较低。近期腹腔镜多器官分割研究聚焦于通过类别特定解码器架构学习结构特定特征，取得了良好结果。本研究将以解码器为核心的架构扩展至跨手术领域的知识迁移研究，利用代表不同手术领域（直肠手术与胆囊切除术）的两个数据集，探究在部分共同解剖表征下手术概念知识的迁移情况；同时对比不同训练阶段编码器与解码器的特征适配，分析网络中的知识适配与保留情况。实验结果证实了解码器特定架构的先前发现，表明器官特定解码器模型（CEMD）在跨域预训练后进行全微调，可达到最高的分割性能（Dice系数为62.4%），且比从头训练收敛速度快得多。但研究也发现，手术数据中的类别不平衡仍是一个持续存在的挑战，迁移学习无法完全解决代表性不足的解剖结构的类别不平衡问题。
英文摘要
Effective multi-organ segmentation in surgical data requires learning the intricate anatomical features and alleviating the challenge of class imbalance, which results from relatively lower proportions of small and limitedly exposed structures. Recent works on laparoscopic multi-organ segmentation focus on learning structure-specific features through class-specific decoder architectures and report favorable results. This work extends the decoder-focused architectures to investigate knowledge sharing in the cross-surgical domain. We utilize two datasets representing different surgical domains, rectal and cholecystectomy surgeries, to explore how surgical conceptual knowledge transfers under partially common anatomical representations. Additionally, we compare the feature adaptation for the encoder and decoder at different training stages to analyse the knowledge adaptation and retention in the network. Our results corroborate previous findings on decoder-specific architectures and demonstrate that the organ-specific decoder model (CEMD), fully fine-tuned after cross-domain pre-training, achieves the highest segmentation performance (62.4\% dice) while converging substantially faster than training from scratch. However, we also find that class imbalance in surgical data remains a persistent challenge that transfer learning does not fully resolve for underrepresented anatomical structures.
发表机构
- Fraunhofer IAIS（弗劳恩霍夫智能分析与信息系统研究所）
- University of Bonn（波恩大学）
机构由 AI 辅助整理，请以论文原文为准。
