arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.07008eess.IVcs.CVcs.LG
收藏

用于脑肿瘤分割的处理与迁移学习的优化框架

An Optimization Framework for Processing and Transfer Learning for the Brain Tumor Segmentation

University of Washington(华盛顿大学)

Tianyi Ren, Ethan Honey, Harshitha Rebala, Abhishek Sharma, Agamdeep Chopra, Mehmet Kurt

AI总结:

针对脑肿瘤分割的准确性与泛化性不足,提出基于3D U-Net的优化框架,结合预处理、后处理与迁移学习,在BraTS 2023三个挑战验证集上取得0.79、0.72、0.74的Dice分数。

摘要:

由于样本有限、形状高方差以及肿瘤形态分布不均,从多模态脑MRI图像中进行肿瘤分割是一项具有挑战性的任务。深度学习的最新进展显著提升了自动化医学图像分割的性能。然而,在准确性和泛化能力方面,模型预测尚未达到临床应用的期望水平。为了解决 BraTS 2023 挑战 1、2 和 3 中提出的独特问题,我们构建了一个基于 3D U-Net 模型的脑肿瘤分割优化框架。该框架整合了一系列技术,包括各种预处理和后处理技术以及迁移学习。在验证数据集上,该多模态脑肿瘤分割框架在挑战 1、2、3 上分别实现了 0.79、0.72、0.74 的平均病灶级 Dice 分数。

英文摘要:

Tumor segmentation from multi-modal brain MRI images is a challenging task due to the limited samples, high variance in shapes and uneven distribution of tumor morphology. The performance of automated medical image segmentation has been significant improvement by the recent advances in deep learning. However, the model predictions have not yet reached the desired level for clinical use in terms of accuracy and generalizability. In order to address the distinct problems presented in Challenges 1, 2, and 3 of BraTS 2023, we have constructed an optimization framework based on a 3D U-Net model for brain tumor segmentation. This framework incorporates a range of techniques, including various pre-processing and post-processing techniques, and transfer learning. On the validation datasets, this multi-modality brain tumor segmentation framework achieves an average lesion-wise Dice score of 0.79, 0.72, 0.74 on Challenges 1, 2, 3 respectively.

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。

↑