arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2401.02717cs.CVcs.AI
收藏

面向多模态医学图像分割的互补信息互学习

Complementary Information Mutual Learning for Multimodality Medical Image Segmentation

School of Computer Science and Technology(计算机科学与技术学院);East China Normal University(华东师范大学);School of Data Science(数据科学学院);The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳));Shenzhen Institute of Artificial Intelligence and Robotics for Society(深圳市人工智能与机器人研究院);Huashan Hospital(华山医院);Fudan University(复旦大学);Shanghai AI Laboratory(上海人工智能实验室);School of Software Engineering(软件工程学院);Shanghai Research Institute for Intelligent Autonomous Systems(上海智能自主系统研究院);Tongji University(同济大学)

Chuyun Shen, Wenhao Li, Haoqing Chen, Xiaoling Wang, Fengping Zhu, Yuxin Li, Xiangfeng Wang, Bo Jin

AI总结:

针对多模态医学图像分割中模态冗余导致精度下降、过拟合风险高的问题,提出CIML框架,通过任务分解、消息传递冗余过滤及互补信息学习去除冗余,在精度和分割效果上超越现有最优方法。

摘要:

由于医学成像的局限性以及肿瘤信号的多样性,放射科医生必须利用多模态图像进行肿瘤分割与诊断,这推动了分割领域中多模态学习的发展。然而,模态间的冗余性给现有基于相减的联合学习方法带来了诸多挑战,例如误判模态重要性、忽略特定模态信息以及增加认知负荷,这些棘手问题最终会降低分割精度并提升过拟合风险。本文提出互补信息互学习(CIML)框架,该框架能够对模态间冗余信息的负面影响进行数学建模并加以解决。CIML采用加法思路,通过归纳偏置驱动的任务分解和基于消息传递的冗余过滤来去除模态间的冗余信息。CIML首先基于专家先验知识将多模态分割任务分解为多个子任务,最大程度降低模态间的信息依赖。此外,CIML引入了一种机制,使每个模态都能通过消息传递从其他模态中以加法方式提取信息。为实现提取信息的非冗余性,受变分信息瓶颈启发,冗余过滤被转化为互补信息学习问题,该互补信息学习过程可通过变分推断和跨模态空间注意力高效求解。验证任务与标准基准上的数值结果表明,CIML可有效去除模态间的冗余信息,在验证精度和分割效果上均优于SOTA方法。

英文摘要:

Radiologists must utilize multiple modal images for tumor segmentation and diagnosis due to the limitations of medical imaging and the diversity of tumor signals. This leads to the development of multimodal learning in segmentation. However, the redundancy among modalities creates challenges for existing subtraction-based joint learning methods, such as misjudging the importance of modalities, ignoring specific modal information, and increasing cognitive load. These thorny issues ultimately decrease segmentation accuracy and increase the risk of overfitting. This paper presents the complementary information mutual learning (CIML) framework, which can mathematically model and address the negative impact of inter-modal redundant information. CIML adopts the idea of addition and removes inter-modal redundant information through inductive bias-driven task decomposition and message passing-based redundancy filtering. CIML first decomposes the multimodal segmentation task into multiple subtasks based on expert prior knowledge, minimizing the information dependence between modalities. Furthermore, CIML introduces a scheme in which each modality can extract information from other modalities additively through message passing. To achieve non-redundancy of extracted information, the redundant filtering is transformed into complementary information learning inspired by the variational information bottleneck. The complementary information learning procedure can be efficiently solved by variational inference and cross-modal spatial attention. Numerical results from the verification task and standard benchmarks indicate that CIML efficiently removes redundant information between modalities, outperforming SOTA methods regarding validation accuracy and segmentation effect.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑