Scholarlink

Background <p>Accurate detection and segmentation of brain metastases is critical for stereotactic radiosurgery (SRS) planning, but manual approaches remain time-consuming and subject to interobserver variability. Artificial intelligence (AI)-based auto-segmentation tools have shown promise but independent external validation on disparate datasets is limited.</p> Methods <p>This retrospective study included 50 patients with 236 brain metastases who underwent SRS using post-contrast 3 Tesla MPRAGE and 3D-TSE sequences. A cloud-based, federated AI algorithm was evaluated for detection sensitivity, false positivity (FP), dice similarity coefficient (DSC), and qualitative physician review. Ground truth contours from clinical treatment plans developed after multi-physician review.</p> Results <p>The AI algorithm successfully identified 123 out of 236 lesions treated, corresponding to a lesion-wise sensitivity of 52.1% and a mean patient-wise sensitivity of 69.2%, with a positive predictive value (PPV) of 78.0%. While the median volume of all lesions in the cohort was 0.045&#xa0;cc, the lesions detected by the algorithm were significantly larger with a median volume of 0.250&#xa0;cc (<i>p</i> &lt; 0.001). The mean Dice similarity coefficient (DSC) was 0.60, with consistently higher scores observed for lesions exceeding 1.0&#xa0;cm in diameter. Qualitative evaluation revealed that 46.3% of AI-generated segmentations required major revisions. Notably, most AI-generated contours were entirely enclosed within the ground truth annotations, often leading to underestimation of lesion margins.</p> Conclusion <p>The AI algorithm demonstrated moderate sensitivity with excellent false positivity. However, performance was limited for sub-centimeter lesions, likely due to the composition of the initial training dataset, which underscores the need/value of independent validation on diverse external datasets.</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

Evaluating the efficacy of a federated AI algorithm in assisting in the detection and segmentation of brain metastases: limitations and opportunities

  • 期刊论文

  • 发表日期：

    2025年11月5日

查看全文
  • Eyub Y. Akdemir,
  • Alonso N. Gutierrez,
  • Yanjia Zhang,
  • Sreenija Yarlagadda,
  • Selin Gurdikyan,
  • Joseph DiStefano,
  • D.Jay Wieczorek,
  • Yongsook C. Lee,
  • Ranjini Tolakanahalli,
  • Matthew D. Hall,
  • Robert H. Press,
  • Michael W. McDermott,
  • Evan D. Bander,
  • Wan-Yuo Guo,
  • Ethan Tu,
  • Minesh P. Mehta,
  • Rupesh Kotecha

摘要

Background

Accurate detection and segmentation of brain metastases is critical for stereotactic radiosurgery (SRS) planning, but manual approaches remain time-consuming and subject to interobserver variability. Artificial intelligence (AI)-based auto-segmentation tools have shown promise but independent external validation on disparate datasets is limited.

Methods

This retrospective study included 50 patients with 236 brain metastases who underwent SRS using post-contrast 3 Tesla MPRAGE and 3D-TSE sequences. A cloud-based, federated AI algorithm was evaluated for detection sensitivity, false positivity (FP), dice similarity coefficient (DSC), and qualitative physician review. Ground truth contours from clinical treatment plans developed after multi-physician review.

Results

The AI algorithm successfully identified 123 out of 236 lesions treated, corresponding to a lesion-wise sensitivity of 52.1% and a mean patient-wise sensitivity of 69.2%, with a positive predictive value (PPV) of 78.0%. While the median volume of all lesions in the cohort was 0.045 cc, the lesions detected by the algorithm were significantly larger with a median volume of 0.250 cc (p < 0.001). The mean Dice similarity coefficient (DSC) was 0.60, with consistently higher scores observed for lesions exceeding 1.0 cm in diameter. Qualitative evaluation revealed that 46.3% of AI-generated segmentations required major revisions. Notably, most AI-generated contours were entirely enclosed within the ground truth annotations, often leading to underestimation of lesion margins.

Conclusion

The AI algorithm demonstrated moderate sensitivity with excellent false positivity. However, performance was limited for sub-centimeter lesions, likely due to the composition of the initial training dataset, which underscores the need/value of independent validation on diverse external datasets.