Dealing with Segmentation Errors in Needle Reconstruction for MRI-Guided Brachytherapy

2025-07-24

AI Summary

In MRI-guided brachytherapy, deep learning–based needle segmentation often suffers from false positives/negatives (e.g., fragmentation, merging, misalignment), and existing post-processing methods lack robustness, leading to substantial reconstruction errors. To address this, we propose an error-aware post-processing algorithm integrated into a two-stage automated needle reconstruction pipeline. Our method jointly models segmentation uncertainty and geometric priors to systematically correct common segmentation artifacts. It is the first to achieve zero false-positive and zero false-negative needle detection. Evaluated on a clinical prostate cancer MRI dataset, it achieves median tip, base, and shaft localization errors of 1.07 mm, 0.43 mm, and 0.75 mm, respectively—significantly outperforming state-of-the-art methods. This work provides a reliable, verifiable solution for high-precision MRI-guided needle reconstruction.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Calibration & Uncertainty Quantification
• Intelligent Robots: State Estimation

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Brachytherapy involves bringing a radioactive source near tumor tissue using implanted needles. Image-guided brachytherapy planning requires amongst others, the reconstruction of the needles. Manually annotating these needles on patient images can be a challenging and time-consuming task for medical professionals. For automatic needle reconstruction, a two-stage pipeline is commonly adopted, comprising a segmentation stage followed by a post-processing stage. While deep learning models are effective for segmentation, their results often contain errors. No currently existing post-processing technique is robust to all possible segmentation errors. We therefore propose adaptations to existing post-processing techniques mainly aimed at dealing with segmentation errors and thereby improving the reconstruction accuracy. Experiments on a prostate cancer dataset, based on MRI scans annotated by medical professionals, demonstrate that our proposed adaptations can help to effectively manage segmentation errors, with the best adapted post-processing technique achieving median needle-tip and needle-bottom point localization errors of $1.07$ (IQR $pm 1.04$) mm and $0.43$ (IQR $pm 0.46$) mm, respectively, and median shaft error of $0.75$ (IQR $pm 0.69$) mm with 0 false positive and 0 false negative needles on a test set of 261 needles.

Problem

• Addressing segmentation errors in MRI-guided brachytherapy needle reconstruction
• Improving robustness of post-processing techniques for segmentation inaccuracies
• Enhancing accuracy of automatic needle reconstruction in prostate cancer treatment

Innovation

• Adapted post-processing for segmentation errors
• Improved needle reconstruction accuracy
• Robust handling of deep learning errors