Scholarlink

Background <p>Automatic segmentation of cervical tumors is important in quantitative analysis and radiotherapy planning.</p> Methods <p>A parallel encoder U-Net (PEU-Net) integrating the multi-modality information of PET/MRI was proposed to segment cervical tumor, which consisted of two parallel encoders with the same structure for PET and MR images. The features of the two modalities were extracted separately and fused at each layer of the decoder. Res2Net module on skip connection aggregated the features of various scales and refined the segmentation performance. PET/MRI images of 165 patients with cervical cancer were included in this study. U-Net, TransUNet, and nnU-Net with single or multi-modality (PET or/and T2WI) input were used for comparison. The Dice similarity coefficient (DSC) with volume data, DSC and the 95th percentile of Hausdorff distance (HD95) with tumor slices were calculated to evaluate the performance.</p> Results <p>The proposed PEU-Net exhibited the best performance (DSC<sub>3d</sub>: 0.726 ± 0.204, HD<sub>95</sub>: 4.603 ± 4.579&#xa0;mm), DSC<sub>2d</sub> (0.871 ± 0.113) was comparable to the best result of TransUNet with PET/MRI (0.873 ± 0.125).</p> Conclusions <p>The networks with multi-modality input outperformed those with single-modality images as input. The results showed that the proposed PEU-Net could use multi-modality information more effectively through the redesigned structure and achieved competitive performance.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Automatic cervical tumors segmentation in PET/MRI by parallel encoder U-net

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年6月5日

查看全文
  • Shuai Liu,
  • Zheng Tan,
  • Tan Gong,
  • Xiaoying Tang,
  • Hongzan Sun,
  • Fei Shang

摘要

Background

Automatic segmentation of cervical tumors is important in quantitative analysis and radiotherapy planning.

Methods

A parallel encoder U-Net (PEU-Net) integrating the multi-modality information of PET/MRI was proposed to segment cervical tumor, which consisted of two parallel encoders with the same structure for PET and MR images. The features of the two modalities were extracted separately and fused at each layer of the decoder. Res2Net module on skip connection aggregated the features of various scales and refined the segmentation performance. PET/MRI images of 165 patients with cervical cancer were included in this study. U-Net, TransUNet, and nnU-Net with single or multi-modality (PET or/and T2WI) input were used for comparison. The Dice similarity coefficient (DSC) with volume data, DSC and the 95th percentile of Hausdorff distance (HD95) with tumor slices were calculated to evaluate the performance.

Results

The proposed PEU-Net exhibited the best performance (DSC3d: 0.726 ± 0.204, HD95: 4.603 ± 4.579 mm), DSC2d (0.871 ± 0.113) was comparable to the best result of TransUNet with PET/MRI (0.873 ± 0.125).

Conclusions

The networks with multi-modality input outperformed those with single-modality images as input. The results showed that the proposed PEU-Net could use multi-modality information more effectively through the redesigned structure and achieved competitive performance.