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 2602.08797cs.CVcs.AI
收藏

利用半监督教师-学生框架解决Brain Tumor Segmentation在3D MRI扫描中的数据标注稀缺问题

Addressing data annotation scarcity in Brain Tumor Segmentation on 3D MRI scan Using a Semi-Supervised Teacher-Student Framework

College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics(人工智能学院,南京航空航天大学);Key Laboratory of Brain-Machine Intelligence Technology, Ministry of Education(脑机智能技术重点实验室,教育部);Shenzhen Research Institute, Nanjing University of Aeronautics and Astronautics(深圳研究院,南京航空航天大学)

Jiaming Liu, Cheng Ding, Daoqiang Zhang

AI总结:

本文提出半监督教师-学生框架,通过置信度驱动课程学习和选择性遗忘,在有限标注下实现高效脑肿瘤分割,提升分割精度和鲁棒性。

摘要:

准确的MRI脑肿瘤分割受限于昂贵的标注和不同扫描仪和地点的数据异质性。我们提出了一种半监督教师-学生框架,结合了不确定性的伪标签教师和逐步的、基于置信度的课程学习。教师产生概率掩码和每个像素的不确定性;未标注的扫描被图像级置信度排序并分阶段引入,而双损失目标训练学生从高置信度区域学习并从低置信度区域中学习。基于一致性改进进一步提高了伪标签的质量。在BraTS 2021上,验证DSC从0.393(10%数据)增加到0.872(100%),最大的增益出现在早期阶段,证明了数据效率。教师达到了0.922的验证DSC,学生在肿瘤子区域(如NCR/NET 0.797和水肿0.980)上超过了教师;值得注意的是,学生恢复了增强类(DSC 0.620),而教师失败。这些结果表明,基于置信度的课程学习和选择性遗忘在有限监督和噪声伪标签下提供了稳健的分割。

英文摘要:

Accurate brain tumor segmentation from MRI is limited by expensive annotations and data heterogeneity across scanners and sites. We propose a semi-supervised teacher-student framework that combines an uncertainty-aware pseudo-labeling teacher with a progressive, confidence-based curriculum for the student. The teacher produces probabilistic masks and per-pixel uncertainty; unlabeled scans are ranked by image-level confidence and introduced in stages, while a dual-loss objective trains the student to learn from high-confidence regions and unlearn low-confidence ones. Agreement-based refinement further improves pseudo-label quality. On BraTS 2021, validation DSC increased from 0.393 (10% data) to 0.872 (100%), with the largest gains in early stages, demonstrating data efficiency. The teacher reached a validation DSC of 0.922, and the student surpassed the teacher on tumor subregions (e.g., NCR/NET 0.797 and Edema 0.980); notably, the student recovered the Enhancing class (DSC 0.620) where the teacher failed. These results show that confidence-driven curricula and selective unlearning provide robust segmentation under limited supervision and noisy pseudo-labels.

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。

↑