Scholarlink

Background and purpose <p>Accurate motion tracking in magnetic resonance imaging-guided radiotherapy (MRIgRT) is essential for effective treatment delivery. This study aimed to enhance motion tracking precision in MRIgRT through an automatic real-time markerless tracking method using an enhanced Tracking-Learning-Detection (ETLD) framework combined with automatic segmentation, eliminating the need for pre-training.</p> Methods <p>We developed a novel motion tracking and segmentation method by integrating the ETLD framework with an improved Chan-Vese (ICV) model, termed ETLD + ICV. The ETLD framework was upgraded for real-time MRIgRT, including search process optimization, an enhanced median-flow tracker, and dynamic detection region adjustments. It receives 3.5D MRI data as input and outputs the location prediction of the target volume for each frame. Based on this, ICV was used for precise target volume coverage, refining the segmented region frame by frame using tracking results, with optimized key parameters. The method requires no pre-training and was tested on 3.5D MRI scans from 10 patients with liver metastases. No-reference image quality assessment and manual verification were used to filter out low-quality image data. Comprehensive statistical analyses were performed to assess the statistical significance of differences between experimental outcomes (<i>p</i> &lt; 0.05). In addition, comparative experiments based on an external benchmark dataset were conducted to further evaluate the performance of the proposed method.</p> Results <p>Evaluation across 106,000 frames from 77 treatment fractions demonstrated sub-millimeter tracking errors of less than 0.8&#xa0;mm, with over 99% precision and 98% recall for all patients in the Beam Eye View (BEV)/Beam Path View (BPV) orientation. The ETLD + ICV method achieved a Dice global score of more than 82% for all patients, demonstrating the method’s extensibility and precise target volume coverage. Comparisons based on the external dataset further showed that the proposed method achieved a balanced trade-off between accuracy and efficiency.</p> Conclusion <p>This study successfully developed an automatic real-time markerless motion tracking method for MRIgRT. The novel method not only delivers exceptional precision in tracking and segmentation but also shows enhanced adaptability to clinical demands, making it an indispensable asset in improving the efficacy of radiotherapy treatments.</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

A novel automatic real-time motion tracking method in MRI-guided radiotherapy using enhanced Tracking-Learning-Detection framework with automatic segmentation

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年8月1日

查看全文
  • Shengqi Chen,
  • Zilin Wang,
  • Jianrong Dai,
  • Shirui Qin,
  • Ying Cao,
  • Ruiao Zhao,
  • Jiayun Chen,
  • Guohua Wu,
  • Yuan Tang

摘要

Background and purpose

Accurate motion tracking in magnetic resonance imaging-guided radiotherapy (MRIgRT) is essential for effective treatment delivery. This study aimed to enhance motion tracking precision in MRIgRT through an automatic real-time markerless tracking method using an enhanced Tracking-Learning-Detection (ETLD) framework combined with automatic segmentation, eliminating the need for pre-training.

Methods

We developed a novel motion tracking and segmentation method by integrating the ETLD framework with an improved Chan-Vese (ICV) model, termed ETLD + ICV. The ETLD framework was upgraded for real-time MRIgRT, including search process optimization, an enhanced median-flow tracker, and dynamic detection region adjustments. It receives 3.5D MRI data as input and outputs the location prediction of the target volume for each frame. Based on this, ICV was used for precise target volume coverage, refining the segmented region frame by frame using tracking results, with optimized key parameters. The method requires no pre-training and was tested on 3.5D MRI scans from 10 patients with liver metastases. No-reference image quality assessment and manual verification were used to filter out low-quality image data. Comprehensive statistical analyses were performed to assess the statistical significance of differences between experimental outcomes (p < 0.05). In addition, comparative experiments based on an external benchmark dataset were conducted to further evaluate the performance of the proposed method.

Results

Evaluation across 106,000 frames from 77 treatment fractions demonstrated sub-millimeter tracking errors of less than 0.8 mm, with over 99% precision and 98% recall for all patients in the Beam Eye View (BEV)/Beam Path View (BPV) orientation. The ETLD + ICV method achieved a Dice global score of more than 82% for all patients, demonstrating the method’s extensibility and precise target volume coverage. Comparisons based on the external dataset further showed that the proposed method achieved a balanced trade-off between accuracy and efficiency.

Conclusion

This study successfully developed an automatic real-time markerless motion tracking method for MRIgRT. The novel method not only delivers exceptional precision in tracking and segmentation but also shows enhanced adaptability to clinical demands, making it an indispensable asset in improving the efficacy of radiotherapy treatments.