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. Methods: This retrospective study consisted of 611 ¹⁸F-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 ¹⁸F-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. Results: 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 (P < 0.05). The risk score for head and neck cancer was significantly associated with overall survival by univariable and multivariable Cox regression analyses (P < 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. Conclusion: The proposed approach demonstrated accurate tumor segmentation and prognosis in patients across 6 cancer types on ¹⁸F-FDG and PSMA PET/CT scans.

癌症的自动检测和表征是优化早期治疗的重要临床需求。我们开发了一种深度、半监督的迁移学习方法，用于 PET/CT 上的全自动、全身肿瘤分割和预后。方法：这项回顾性研究包括 611 例肺癌、黑色素瘤、淋巴瘤、头颈癌和乳腺癌患者的¹⁸ F-FDG PET/CT 扫描以及 408 例前列腺特异性膜抗原 (PSMA) PET/CT 扫描。患有前列腺癌。该方法具有 nnU-net 主干，并使用有限的注释和放射组学分析学习了¹⁸ F-FDG 和 PSMA PET/CT 图像的分割任务。评估真阳性率和 Dice 相似系数来评估分割性能。使用从预测分割中提取的影像学指标开发预后模型，以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 回归分析对头颈癌进行生存估计，并进行完整的病理学分析。乳腺癌新辅助化疗后的反应预测。评估了总体准确性和接受者操作特征（AUC）曲线下的面积。结果：我们的方法对肺癌、黑色素瘤、淋巴瘤和前列腺癌患者的中位真阳性率分别为 0.75、0.85、0.87 和 0.75，中位 Dice 相似系数分别为 0.81、0.76、0.83 和 0.73。肿瘤分割任务。前列腺癌风险模型的总体准确度为 0.83，AUC 为 0.86。被分类为低至中和高风险的患者的平均随访前列腺特异性抗原水平分别为 18.61 和 727.46 ng/mL（P < 0.05）。通过单变量和多变量 Cox 回归分析，头颈癌的风险评分与总生存率显着相关（P < 0.05）。乳腺癌的预测模型仅使用治疗前成像测量以及治疗前和治疗后测量来预测病理完全缓解，准确度分别为 0.72 和 0.84，AUC 分别为 0.72 和 0.76。结论：所提出的方法在¹⁸ F-FDG 和 PSMA PET/CT 扫描中证明了 6 种癌症类型患者的准确肿瘤分割和预后。