文献速递乳腺MR

基于变分自编码器的乳腺肿瘤分割图像增强方法

Image Augmentation based on Variational Autoencoder for Breast Tumor Segmentation.
PubMed 文献 · Acad Radiol · 2023-02-16

研究提出一种基于变分自编码器的3D Connected-UNets深度学习模型,用于动态增强MRI的乳腺肿瘤分割。在INbreast、DDSM公开数据集及私有数据集上评估,结果显示该模型分割性能优于现有方法。

要点

  • 变分自编码器辅助训练可缓解训练数据量受限问题
  • 3D连接模块可保留大病灶并减少分割噪声
  • 该方法在多个数据集上分割性能优于现有方法

核心结论

  • 所提模型在乳腺肿瘤分割上优于现有方法。

研究设计与样本

  • 研究为方法学开发与评估,采用3D Connected-UNets编码器-解码器架构,附加变分自编码器出口重建输入图像以共享解码器并施加额外控制。
  • 使用全连接3D临时随机域通过2D邻域和3D体积统计增强分割,并用3D连接模块评估以保留大模块、减少分割噪声。
  • 在INbreast、DDSM乳腺影像子集两个公开数据集及一个私有数据集上评估。

临床应用与阅片要点

  • 该模型可自动分割DCE-MRI乳腺肿瘤,有望减少手动标注耗时和观察者间差异。

局限性

  • 原文提到训练数据集规模受限。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

RATIONALE AND OBJECTIVES: Breast tumor segmentation based on Dynamic Contrast-Enhanced Magnetic Resonance Imaging is significant step for computable radiomics analysis of breast cancer. Manual tumor annotation is time-consuming process and involves medical acquaintance, biased, inclined to error, and inter-user discrepancy. A number of modern trainings have revealed the capability of deep learning representations in image segmentation.

MATERIALS AND METHODS: Here, we describe a 3D Connected-UNets for tumor segmentation from 3D Magnetic Resonance Imagings based on encoder-decoder architecture. Due to a restricted training dataset size, a variational auto-encoder outlet is supplementary to renovate the input image itself in order to identify the shared decoder and execute additional controls on its layers. Based on initial segmentation of Connected-UNets, fully connected 3D provisional unsystematic domain is used to enhance segmentation outcomes by discovering 2D neighbor areas and 3D volume statistics. Moreover, 3D connected modules evaluation is used to endure around large modules and decrease segmentation noise.

RESULTS: The proposed method has been assessed on two widely offered datasets, explicitly INbreast and the curated breast imaging subset of digital database for screening mammography The proposed model has also been estimated using a private dataset.

CONCLUSION: The experimental results show that the proposed model outperforms the state-of-the-art methods for breast tumor segmentation.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Balaji. Image Augmentation based on Variational Autoencoder for Breast Tumor Segmentation. Acad Radiol. 2023. PMID: 36804294. doi:10.1016/j.acra.2022.12.035

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。