基于深度学习的肿瘤分割与总代谢肿瘤体积预测在弥漫性大B细胞淋巴瘤患者3D FDG-PET影像预后中的价值
回顾性分析本地中心297例和外部中心117例弥漫性大B细胞淋巴瘤患者的PET数据,训练3D U-Net分割模型;验证集平均DSC为0.78±0.25,预测总代谢肿瘤体积与真实值高度一致(R²线性=0.874,p<0.001),预测总代谢肿瘤体积≥201.2 cm³是无进展生存和总生存的独立预后因素。
要点
- 3D U-Net模型在外部验证集分割淋巴瘤病灶的平均DSC为0.78±0.25。
- 预测总代谢肿瘤体积与真实总代谢肿瘤体积线性回归R²=0.874(p<0.001)。
- 预测总代谢肿瘤体积≥201.2 cm³是无进展生存(HR=3.097)和总生存(HR=6.601)的独立预后因素。
核心结论
- 基于U-Net架构的全卷积网络模型能准确分割淋巴瘤病灶并全自动评估PET上的总代谢肿瘤体积,预测总代谢肿瘤体积是弥漫性大B细胞淋巴瘤患者生存的独立预后因素。
研究设计与样本
- 回顾性分析两个PET数据集:本地中心297例用于训练,外部中心117例用于验证;在PET图像内随机采样的图像块上训练3D U-Net架构;以DSC、JSC、敏感度、阳性预测值、HD 95和ASSD六项指标评估分割性能,并在真实临床应用中验证预测总代谢肿瘤体积的预后价值。
诊断标准与关键数值
- 验证集平均DSC为0.78±0.25、JSC为0.69±0.26、敏感度为0.81±0.27、阳性预测值为0.82±0.25、HD 95为24.58±35.18、ASSD为4.46±8.92;验证集平均真实总代谢肿瘤体积为276.6±393.5 cm³,预测总代谢肿瘤体积为301.9±510.5 cm³;预测总代谢肿瘤体积≥201.2 cm³时无进展生存HR=3.097(p=0.001)、总生存HR=6.601(p<0.001)。
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)。
英文原文(摘要)· 点击展开
OBJECTIVES: To demonstrate the effectiveness of automatic segmentation of diffuse large B-cell lymphoma (DLBCL) in 3D FDG-PET scans using a deep learning approach and validate its value in prognosis in an external validation cohort.
METHODS: Two PET datasets were retrospectively analysed: 297 patients from a local centre for training and 117 patients from an external centre for validation. A 3D U-Net architecture was trained on patches randomly sampled within the PET images. Segmentation performance was evaluated by six metrics, including the Dice similarity coefficient (DSC), Jaccard similarity coefficient (JSC), sensitivity (Se), positive predictive value (PPV), Hausdorff distance 95 (HD 95), and average symmetric surface distance (ASSD). Finally, the prognostic value of predictive total metabolic tumour volume (pTMTV) was validated in real clinical applications.
RESULTS: The mean DSC, JSC, Se, PPV, HD 95, and ASSD (with standard deviation) for the validation cohort were 0.78 ± 0.25, 0.69 ± 0.26, 0.81 ± 0.27, 0.82 ± 0.25, 24.58 ± 35.18, and 4.46 ± 8.92, respectively. The mean ground truth TMTV (gtTMTV) and pTMTV were 276.6 ± 393.5 cm3 and 301.9 ± 510.5 cm3 in the validation cohort, respectively. Perfect homogeneity in the Bland-Altman analysis and a strong positive correlation in the linear regression analysis (R2 linear = 0.874, p < 0.001) were demonstrated between gtTMTV and pTMTV. pTMTV (≥ 201.2 cm3) (PFS: HR = 3.097, p = 0.001; OS: HR = 6.601, p < 0.001) was shown to be an independent factor of PFS and OS.
CONCLUSIONS: The FCN model with a U-Net architecture can accurately segment lymphoma lesions and allow fully automatic assessment of TMTV on PET scans for DLBCL patients. Furthermore, pTMTV is an independent prognostic factor of survival in DLBCL patients.
KEY POINTS: •The segmentation model based on a U-Net architecture shows high performance in the segmentation of DLBCL patients on FDG-PET images. •The proposed method can provide quantitative information as a predictive TMTV for predicting the prognosis of DLBCL patients.
引用
- Jiang, Chen, Teng, et al. Deep learning-based tumour segmentation and total metabolic tumour volume prediction in the prognosis of diffuse large B-cell lymphoma patients in 3D FDG-PET images. Eur Radiol. 2022. PMID: 35166895. doi:10.1007/s00330-022-08573-1
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。