Deep Semisupervised Transfer Learning for Fully Automated Whole-Body Tumor Quantification and Prognosis of Cancer on PET/CT.

Autor:	Leung KH; Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins University School of Medicine, Baltimore, Maryland; kleung8@jhmi.edu., Rowe SP; Department of Radiology, University of North Carolina at Chapel Hill School of Medicine, Chapel Hill, North Carolina; and., Sadaghiani MS; Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins University School of Medicine, Baltimore, Maryland., Leal JP; Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins University School of Medicine, Baltimore, Maryland., Mena E; Center for Cancer Research, National Cancer Institute, Bethesda, Maryland., Choyke PL; Center for Cancer Research, National Cancer Institute, Bethesda, Maryland., Du Y; Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins University School of Medicine, Baltimore, Maryland., Pomper MG; Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins University School of Medicine, Baltimore, Maryland.
Jazyk:	angličtina
Zdroj:	Journal of nuclear medicine : official publication, Society of Nuclear Medicine [J Nucl Med] 2024 Apr 01; Vol. 65 (4), pp. 643-650. Date of Electronic Publication: 2024 Apr 01.
DOI:	10.2967/jnumed.123.267048
Abstrakt:	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 18 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 18 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. 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 18 F-FDG and PSMA PET/CT scans. (© 2024 by the Society of Nuclear Medicine and Molecular Imaging.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu