arXiv 2307.035792023-07-07cs.CV

基于深度学习级联配准的胎儿脑MRI无监督分割

Unsupervised Segmentation of Fetal Brain MRI using Deep Learning Cascaded Registration

Universitat Pompeu Fabra（庞培法布拉大学）；BCNatal；Institución Catalana de Investigación y Estudios Avanzados (ICREA)（加泰罗尼亚高级研究与发展研究院）；Centre for Biomedical Research on Rare Diseases (CIBERER)（罕见疾病生物医学研究中心）；European Commission, Joint Research Centre (JRC)（欧盟委员会联合研究中心）

Valentin Comte, Mireia Alenya, Andrea Urru, Judith Recober, Ayako Nakaki, Francesca Crovetto, Oscar Camara, Eduard Gratacós, Elisenda Eixarch, Fàtima Crispi, Ge… 展开作者

Valentin Comte, Mireia Alenya, Andrea Urru, Judith Recober, Ayako Nakaki, Francesca Crovetto, Oscar Camara, Eduard Gratacós, Elisenda Eixarch, Fàtima Crispi, Gemma Piella, Mario Ceresa, Miguel A. González Ballester

备注：: 17 pages, 8 figures, 5 tables, paper submitted to IEEE transaction on medical imaging

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出一种基于级联深度学习配准和多图谱融合的胎儿脑MRI无监督分割方法，无需标注数据训练即可达到与nnU-Net相当的性能。

摘要：

胎儿脑磁共振图像的准确分割对于分析胎儿大脑发育和检测潜在的神经发育异常至关重要。传统的基于深度学习的自动分割虽然有效，但需要大量带有真实标签的训练数据，而这些标签通常由临床医生通过耗时的标注过程生成。为克服这一挑战，我们提出了一种基于多图谱分割的新型无监督分割方法，该方法无需依赖带标签数据进行训练即可准确分割多种组织。我们的方法采用级联深度学习网络进行3D图像配准，该网络计算移动图像的小幅增量形变，使其与固定图像精确对齐。该级联网络随后可用于将多幅已标注图像与待分割图像进行配准，并融合传播的标签以形成精细化的分割结果。我们的实验表明，所提出的级联架构优于已测试的最先进配准方法。此外，所得到的分割方法在性能和推理时间上与nnU-Net相当，但在多图谱分割任务中仅使用了少量标注数据子集，且未使用任何标注数据训练网络。我们的配准与多图谱分割流程已在 https://github.com/ValBcn/CasReg 公开提供。

英文摘要：

Accurate segmentation of fetal brain magnetic resonance images is crucial for analyzing fetal brain development and detecting potential neurodevelopmental abnormalities. Traditional deep learning-based automatic segmentation, although effective, requires extensive training data with ground-truth labels, typically produced by clinicians through a time-consuming annotation process. To overcome this challenge, we propose a novel unsupervised segmentation method based on multi-atlas segmentation, that accurately segments multiple tissues without relying on labeled data for training. Our method employs a cascaded deep learning network for 3D image registration, which computes small, incremental deformations to the moving image to align it precisely with the fixed image. This cascaded network can then be used to register multiple annotated images with the image to be segmented, and combine the propagated labels to form a refined segmentation. Our experiments demonstrate that the proposed cascaded architecture outperforms the state-of-the-art registration methods that were tested. Furthermore, the derived segmentation method achieves similar performance and inference time to nnU-Net while only using a small subset of annotated data for the multi-atlas segmentation task and none for training the network. Our pipeline for registration and multi-atlas segmentation is publicly available at https://github.com/ValBcn/CasReg.

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。