Scholarlink

Purpose <p>Segmentation neural networks have demonstrated promising results for interventional needle localization on MRI. However, these networks require large training datasets with tedious annotation processes and additional post-processing steps that may introduce variability in the final localization results. This study aimed to develop keypoint detection networks for direct localization of the needle entry point and tip on intra-procedural liver MRI with a more efficient annotation process and more robust performance.</p> Methods <p>2D and 3D keypoint detection networks were developed by enhancing the stacked hourglass model and incorporating multi-task learning of predicting part affinity fields that connect the keypoints. The proposed networks were evaluated on intra-procedural single-slice controlled-breathing (SS-CB) and multislice controlled-breathing (MS-CB) images acquired from pre-clinical MRI-guided percutaneous liver intervention in thirteen in vivo pig subjects and compared with the results of segmentation-based UNet and Swin Transformer networks and human intra-reader variation.</p> Results <p>The 2D and 3D keypoint detection networks achieved median needle tip and axis localization errors of 1.56&#xa0;mm (1 pixel) and 1.1° for the SS-CB datasets, and 2.21&#xa0;mm (~ 1.5 pixel) and 1.45° for the MS-CB datasets, respectively. Average computational times were 10&#xa0;ms (2D) and 30&#xa0;ms (3D). The needle localization accuracy of the keypoint networks was significantly (Wilcoxon signed-rank tests <i>p</i> &lt; 0.001) higher than the UNet and Swin Transformer segmentation-based results and comparable to human intra-reader variation.</p> Conclusion <p>The proposed keypoint detection networks achieved rapid pixel-level needle localization on single-slice and multislice intra-procedural liver MRI with higher accuracy and a more efficient annotation process compared to segmentation-based models.</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

Keypoint detection network for needle localization on intra-procedural MRI in MRI-guided liver interventions

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年3月30日

查看全文
  • Wenqi Zhou,
  • Qing Dai,
  • Omar Curiel,
  • Tsu-Chin Tsao,
  • Jason Chiang,
  • David S. Lu,
  • Holden H. Wu

摘要

Purpose

Segmentation neural networks have demonstrated promising results for interventional needle localization on MRI. However, these networks require large training datasets with tedious annotation processes and additional post-processing steps that may introduce variability in the final localization results. This study aimed to develop keypoint detection networks for direct localization of the needle entry point and tip on intra-procedural liver MRI with a more efficient annotation process and more robust performance.

Methods

2D and 3D keypoint detection networks were developed by enhancing the stacked hourglass model and incorporating multi-task learning of predicting part affinity fields that connect the keypoints. The proposed networks were evaluated on intra-procedural single-slice controlled-breathing (SS-CB) and multislice controlled-breathing (MS-CB) images acquired from pre-clinical MRI-guided percutaneous liver intervention in thirteen in vivo pig subjects and compared with the results of segmentation-based UNet and Swin Transformer networks and human intra-reader variation.

Results

The 2D and 3D keypoint detection networks achieved median needle tip and axis localization errors of 1.56 mm (1 pixel) and 1.1° for the SS-CB datasets, and 2.21 mm (~ 1.5 pixel) and 1.45° for the MS-CB datasets, respectively. Average computational times were 10 ms (2D) and 30 ms (3D). The needle localization accuracy of the keypoint networks was significantly (Wilcoxon signed-rank tests p < 0.001) higher than the UNet and Swin Transformer segmentation-based results and comparable to human intra-reader variation.

Conclusion

The proposed keypoint detection networks achieved rapid pixel-level needle localization on single-slice and multislice intra-procedural liver MRI with higher accuracy and a more efficient annotation process compared to segmentation-based models.