- 简介2024年脑肿瘤分割脑膜瘤放疗（BraTS-MEN-RT）挑战旨在利用目前已知最大的多机构数据集，即放疗计划脑部MRI，来推进自动化分割算法，该数据集具有经过专家注释的靶标标签，适用于接受常规外部束放疗或立体定向放射外科手术的脑膜瘤患者。每个案例包括一个已去标识化的三维增强后的T1加权放疗计划MRI，以其本地采集空间为伴，同时伴随一个表示粗瘤体积（GTV）和任何有风险的术后部位的单一标签“目标体积”。目标体积标注遵循已建立的放疗计划协议，确保案例和机构之间的一致性。对于术前脑膜瘤，目标体积包括整个GTV和相关的结节性硬膜尾，而对于术后病例，它包括治疗机构确定的有风险的切除腔边缘。病例注释经过专家神经放射科医师和放射肿瘤科医师的审核和批准。参赛团队将使用这个全面的数据集开发、容器化和评估自动分割模型。模型性能将使用病变级别的Dice相似系数和95％的Hausdorff距离进行评估。表现最佳的团队将在2024年10月的医学图像计算和计算机辅助干预会议上获得认可。BraTS-MEN-RT有望通过实现精确的肿瘤分割和促进个性化治疗，最终改善患者预后，显著推进自动化放疗计划。
- 图表
- 解决问题BraTS-MEN-RT challenge aims to advance automated segmentation algorithms for radiotherapy planning brain MRIs with expert-annotated target labels for patients with meningioma. The challenge aims to improve patient outcomes by enabling precise tumor segmentation and facilitating tailored treatment.
- 关键思路The challenge provides a comprehensive dataset for developing and evaluating automated segmentation models using expert-annotated target labels for patients with meningioma. Model performance will be assessed using the lesion-wise Dice Similarity Coefficient and the 95% Hausdorff distance.
- 其它亮点The challenge dataset includes defaced 3D post-contrast T1-weighted radiotherapy planning MRI with single-label target volume annotations adhering to established radiotherapy planning protocols. The top-performing teams will be recognized at the Medical Image Computing and Computer Assisted Intervention Conference in October 2024.
- Related studies in this field include automated segmentation algorithms for brain tumors, such as the BraTS challenge, as well as studies on radiotherapy planning and treatment for meningioma.
沙发等你来抢
去评论
评论
沙发等你来抢