Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins University School of Medicine, Baltimore, Maryland;
Department of Radiology, University of North Carolina at Chapel Hill School of Medicine, Chapel Hill, North Carolina; and.
J Nucl Med. 2024 Apr 1;65(4):643-650. doi: 10.2967/jnumed.123.267048.
Automatic detection and characterization of cancer are important clinical needs to optimize early treatment. We developed a deep, semisupervised transfer learning approach for fully automated, whole-body tumor segmentation and prognosis on PET/CT. This retrospective study consisted of 611 F-FDG PET/CT scans of patients with lung cancer, melanoma, lymphoma, head and neck cancer, and breast cancer and 408 prostate-specific membrane antigen (PSMA) PET/CT scans of patients with prostate cancer. The approach had a nnU-net backbone and learned the segmentation task on F-FDG and PSMA PET/CT images using limited annotations and radiomics analysis. True-positive rate and Dice similarity coefficient were assessed to evaluate segmentation performance. Prognostic models were developed using imaging measures extracted from predicted segmentations to perform risk stratification of prostate cancer based on follow-up prostate-specific antigen levels, survival estimation of head and neck cancer by the Kaplan-Meier method and Cox regression analysis, and pathologic complete response prediction of breast cancer after neoadjuvant chemotherapy. Overall accuracy and area under the receiver-operating-characteristic (AUC) curve were assessed. Our approach yielded median true-positive rates of 0.75, 0.85, 0.87, and 0.75 and median Dice similarity coefficients of 0.81, 0.76, 0.83, and 0.73 for patients with lung cancer, melanoma, lymphoma, and prostate cancer, respectively, on the tumor segmentation task. The risk model for prostate cancer yielded an overall accuracy of 0.83 and an AUC of 0.86. Patients classified as low- to intermediate- and high-risk had mean follow-up prostate-specific antigen levels of 18.61 and 727.46 ng/mL, respectively ( < 0.05). The risk score for head and neck cancer was significantly associated with overall survival by univariable and multivariable Cox regression analyses ( < 0.05). Predictive models for breast cancer predicted pathologic complete response using only pretherapy imaging measures and both pre- and posttherapy measures with accuracies of 0.72 and 0.84 and AUCs of 0.72 and 0.76, respectively. The proposed approach demonstrated accurate tumor segmentation and prognosis in patients across 6 cancer types on F-FDG and PSMA PET/CT scans.
自动检测和表征癌症是优化早期治疗的重要临床需求。我们开发了一种深度、半监督的转移学习方法，用于全自动、全身肿瘤分割和预测 F-FDG 和 PSMA PET/CT 的预后。这项回顾性研究包括 611 例肺癌、黑色素瘤、淋巴瘤、头颈部癌症和乳腺癌患者的 F-FDG PET/CT 扫描和 408 例前列腺癌患者的 PSMA PET/CT 扫描。该方法采用 nnU-net 骨干网络，使用有限的注释和放射组学分析在 F-FDG 和 PSMA PET/CT 图像上学习分割任务。通过真阳性率和 Dice 相似系数评估分割性能。使用从预测分割中提取的成像指标开发预后模型，根据后续前列腺特异性抗原水平对前列腺癌进行风险分层，通过 Kaplan-Meier 方法和 Cox 回归分析对头颈部癌症进行生存估计，以及对新辅助化疗后乳腺癌的病理完全缓解进行预测。评估了整体准确性和接收器工作特征 (ROC) 曲线下面积 (AUC)。我们的方法在肿瘤分割任务中分别获得了肺癌、黑色素瘤、淋巴瘤和前列腺癌患者的中位数真阳性率为 0.75、0.85、0.87 和 0.75，中位数 Dice 相似系数为 0.81、0.76、0.83 和 0.73。前列腺癌的风险模型整体准确率为 0.83，AUC 为 0.86。低危到中危和高危患者的平均随访前列腺特异性抗原水平分别为 18.61 和 727.46ng/mL（<0.05）。单变量和多变量 Cox 回归分析显示，头颈部癌症的风险评分与总生存显著相关（<0.05）。乳腺癌的预测模型仅使用治疗前的成像指标以及治疗前和治疗后的指标进行预测，准确率分别为 0.72 和 0.84，AUC 分别为 0.72 和 0.76。该方法在 6 种癌症类型的 F-FDG 和 PSMA PET/CT 扫描中均能准确地进行肿瘤分割和预测预后。
Eur J Nucl Med Mol Imaging. 2022-12
Comput Methods Programs Biomed. 2022-6
Cancers (Basel). 2025-8-1
Cancers (Basel). 2025-4-30
Eur J Nucl Med Mol Imaging. 2025-5-2
Cancer Innov. 2025-2-20
CA Cancer J Clin. 2023-1
Sci Data. 2022-10-4
CA Cancer J Clin. 2022-7
Zotero 插件