深度学习用于头颈癌18F-FDG PET/CT肿瘤勾画的临床评估
本研究回顾性纳入2014年1月至2019年12月接受放疗的头颈癌患者PET/CT扫描,训练并评估5种深度学习肿瘤勾画方法,以专家PET GTV为参考标准,主要终点为Dice相似系数。nnU-Net获得最高相似度(DSC 0.80),AI与专家间变异性和专家间观察者变异性无显著差异,内部与外部AI-专家变异性无显著差异。
要点
- nnU-Net在5种深度学习方法中相似度最高,DSC为0.80(95%CI 0.77-0.86)。
- AI与专家间变异性(DSC 0.78)与专家间观察者变异性(DSC 0.82)无显著差异,P=0.12。
- 内部与外部AI-专家变异性无显著差异(DSC 0.80 vs 0.81),P=0.87。
核心结论
- 深度学习可用于自动化18F-FDG PET/CT肿瘤体积衍生的影像生物标志物提取。
- 基于深度学习的肿瘤体积有潜力辅助放射肿瘤学中的临床肿瘤体积勾画。
研究设计与样本
- 回顾性纳入2014年1月至2019年12月接受放疗的头颈癌患者扫描(ISRCTN16907234)。
- 共纳入1,220次18F-FDG PET/CT扫描,来自1,190例患者(平均年龄±SD 63±10岁;858例男性)。
- 使用5折交叉验证训练5种深度学习方法(n=805)。
- 使用3个测试数据集:内部集比较方法,另一内部集比较AI-专家变异性和专家间观察者变异性,外部集比较内部与外部AI-专家变异性。
- 以专家PET GTV为参考标准;基准观察者变异性使用6位专家的PET GTV测量;主要终点为Dice相似系数。
主要发现
- nnU-Net方法获得最高相似度,DSC为0.80(95%CI 0.77-0.86;n=196)。
- 专家间观察者变异性与AI-专家变异性无显著差异:AI的DSC为0.78 vs 专家的DSC为0.82,平均差异0.04(95%CI -0.01至0.09),P=0.12,n=64。
- 内部与外部AI-专家变异性无显著差异:内部DSC为0.80 vs 外部DSC为0.81,平均差异0.004(95%CI -0.05至0.04),P=0.87,n=125。
- AI的PET GTV衍生生物标志物与专家结果一致性良好。
关键数值与推荐
- 主要终点为Dice相似系数(DSC)。
- nnU-Net的DSC为0.80(95%CI 0.77-0.86;n=196)。
- AI-专家变异性与专家间观察者变异性比较:AI的DSC为0.78 vs 专家的DSC为0.82,平均差异0.04(95%CI -0.01至0.09),P=0.12,n=64。
- 内部与外部AI-专家变异性比较:内部DSC为0.80 vs 外部DSC为0.81,平均差异0.004(95%CI -0.05至0.04),P=0.87,n=125。
临床怎么用
- 原文未据此给出推荐。
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
Artificial intelligence (AI) may decrease 18F-FDG PET/CT-based gross tumor volume (GTV) delineation variability and automate tumor-volume-derived image biomarker extraction. Hence, we aimed to identify and evaluate promising state-of-the-art deep learning methods for head and neck cancer (HNC) PET GTV delineation. Methods: We trained and evaluated deep learning methods using retrospectively included scans of HNC patients referred for radiotherapy between January 2014 and December 2019 (ISRCTN16907234). We used 3 test datasets: an internal set to compare methods, another internal set to compare AI-to-expert variability and expert interobserver variability (IOV), and an external set to compare internal and external AI-to-expert variability. Expert PET GTVs were used as the reference standard. Our benchmark IOV was measured using the PET GTV of 6 experts. The primary outcome was the Dice similarity coefficient (DSC). ANOVA was used to compare methods, a paired t test was used to compare AI-to-expert variability and expert IOV, an unpaired t test was used to compare internal and external AI-to-expert variability, and post hoc Bland-Altman analysis was used to evaluate biomarker agreement. Results: In total, 1,220 18F-FDG PET/CT scans of 1,190 patients (mean age ± SD, 63 ± 10 y; 858 men) were included, and 5 deep learning methods were trained using 5-fold cross-validation (n = 805). The nnU-Net method achieved the highest similarity (DSC, 0.80 [95% CI, 0.77-0.86]; n = 196). We found no evidence of a difference between expert IOV and AI-to-expert variability (DSC, 0.78 for AI vs. 0.82 for experts; mean difference of 0.04 [95% CI, -0.01 to 0.09]; P = 0.12; n = 64). We found no evidence of a difference between the internal and external AI-to-expert variability (DSC, 0.80 internally vs. 0.81 externally; mean difference of 0.004 [95% CI, -0.05 to 0.04]; P = 0.87; n = 125). PET GTV-derived biomarkers of AI were in good agreement with experts. Conclusion: Deep learning can be used to automate 18F-FDG PET/CT tumor-volume-derived imaging biomarkers, and the deep-learning-based volumes have the potential to assist clinical tumor volume delineation in radiation oncology.
引用
- Kovacs DG, Ladefoged CN, Andersen KF, et al. Clinical Evaluation of Deep Learning for Tumor Delineation on 18F-FDG PET/CT of Head and Neck Cancer. J Nucl Med. 2024. PMID: 38388516. doi:10.2967/jnumed.123.266574
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。