人工智能在垂体腺瘤放射外科中的应用:基于深度学习的自动分割模型及其临床适用性评估
本研究开发了基于nnU-Net的深度学习模型,用于立体定向放射外科计划中MRI扫描的垂体腺瘤自动分割,并在582例患者的MRI上训练、146例未见患者上评估。模型对肿瘤、正常腺体和视神经的Dice相似系数分别为82.3%、63.9%和79.6%。专家评定20.6%的分割无需修改即可用于治疗计划,52.7%需轻微手动修改,26.7%不可用,且预测分割评分低于原始手动分割对照组(p < 0.001)。手动改进不准确分割比从头创建节省53.6%时间(p < 0.001)。
要点
- 模型对肿瘤、正常腺体、视神经的Dice系数分别为82.3%、63.9%、79.6%。
- 专家评定20.6%分割无需修改即可用于计划,52.7%需轻微修改,26.7%不可用。
- 手动改进不准确分割比从头创建节省53.6%时间(p < 0.001)。
核心结论
- 预测分割无需或仅需轻微手动修改即可用于治疗计划,显著提高计划流程效率。
- 预测分割可加载到临床实践使用的计划软件中进行治疗计划。
- 作者讨论了自动分割模型临床应用的考虑及其在现有临床工作流程中的整合,并概述未来研究方向。
研究设计与样本
- 基于nnU-Net的深度学习模型,在582例接受Leksell Gamma Knife治疗患者的MRI扫描及专家分割上训练,历时12年。
- 模型准确性由人类专家在146例先前未见的独立数据集上评估。
- 主要结局为预测分割与原始手动分割对照组之间的专家评分比较。
主要发现
- 模型对肿瘤、正常腺体、视神经的Dice相似系数分别为82.3%、63.9%、79.6%。
- 专家评定20.6%的分割无需任何修改即可用于治疗计划,52.7%需轻微手动修改即可应用,26.7%不可用。
- 预测分割的评分低于原始分割对照组(p < 0.001)。
- 较大的肿瘤体积、既往放射外科治疗史和非功能性垂体腺瘤与更好的专家评分相关(分别为p = 0.005、p = 0.007、p < 0.001)。
- 在无既往手术的亚组中,专家评分更有利,但关联未达统计学显著性(p = 0.074)。
临床怎么用
- 预测分割无需或仅需轻微手动修改即可用于治疗计划,可加载到临床实践使用的计划软件中。
- 手动改进不准确分割而非从头创建可降低时间成本。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
OBJECTIVE: The objective of this study was to develop a deep learning model for automated pituitary adenoma segmentation in MRI scans for stereotactic radiosurgery planning and to assess its accuracy and efficiency in clinical settings. METHODS: An nnU-Net-based model was trained on MRI scans with expert segmentations of 582 patients treated with Leksell Gamma Knife over the course of 12 years. The accuracy of the model was evaluated by a human expert on a separate dataset of 146 previously unseen patients. The primary outcome was the comparison of expert ratings between the predicted segmentations and a control group consisting of original manual segmentations. Secondary outcomes were the influence of tumor volume, previous surgery, previous stereotactic radiosurgery (SRS), and endocrinological status on expert ratings, performance in a subgroup of nonfunctioning macroadenomas (measuring 1000-4000 mm3) without previous surgery and/or radiosurgery, and influence of using additional MRI modalities as model input and time cost reduction. RESULTS: The model achieved Dice similarity coefficients of 82.3%, 63.9%, and 79.6% for tumor, normal gland, and optic nerve, respectively. A human expert rated 20.6% of the segmentations as applicable in treatment planning without any modifications, 52.7% as applicable with minor manual modifications, and 26.7% as inapplicable. The ratings for predicted segmentations were lower than for the control group of original segmentations (p < 0.001). Larger tumor volume, history of a previous radiosurgery, and nonfunctioning pituitary adenoma were associated with better expert ratings (p = 0.005, p = 0.007, and p < 0.001, respectively). In the subgroup without previous surgery, although expert ratings were more favorable, the association did not reach statistical significance (p = 0.074). In the subgroup of noncomplex cases (n = 9), 55.6% of the segmentations were rated as applicable without any manual modifications and no segmentations were rated as inapplicable. Manually improving inaccurate segmentations instead of creating them from scratch led to 53.6% reduction of the time cost (p < 0.001). CONCLUSIONS: The results were applicable for treatment planning with either no or minor manual modifications, demonstrating a significant increase in the efficiency of the planning process. The predicted segmentations can be loaded into the planning software used in clinical practice for treatment planning. The authors discuss some considerations of the clinical utility of the automated segmentation models, as well as their integration within established clinical workflows, and outline directions for future research.
引用
- Černý M, May J, Hamáčková L, et al. Utility of artificial intelligence in radiosurgery for pituitary adenoma: a deep learning-based automated segmentation model and evaluation of its clinical applicability. J Neurosurg. 2025. PMID: 40250054. doi:10.3171/2024.12.JNS242167
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。