Synthetic PET from CT improves diagnosis and prognosis for lung cancer: Proof of concept

• Published in: Cell reports. Medicine Vol. 5; no. 3; p. 101463
• Main Authors: Salehjahromi, Morteza, Karpinets, Tatiana V., Sujit, Sheeba J., Qayati, Mohamed, Chen, Pingjun, Aminu, Muhammad, Saad, Maliazurina B., Bandyopadhyay, Rukhmini, Hong, Lingzhi, Sheshadri, Ajay, Lin, Julie, Antonoff, Mara B., Sepesi, Boris, Ostrin, Edwin J., Toumazis, Iakovos, Huang, Peng, Cheng, Chao, Cascone, Tina, Vokes, Natalie I., Behrens, Carmen, Siewerdsen, Jeffrey H., Hazle, John D., Chang, Joe Y., Zhang, Jianhua, Lu, Yang, Godoy, Myrna C.B., Chung, Caroline, Jaffray, David, Wistuba, Ignacio, Lee, J. Jack, Vaporciyan, Ara A., Gibbons, Don L., Gladish, Gregory, Heymach, John V., Wu, Carol C., Zhang, Jianjun, Wu, Jia
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 19.03.2024; Elsevier
• Subjects: Fluorodeoxyglucose F18; generative adversarial network; generative AI; Humans; image synthesis; lung cancer; Lung Neoplasms - diagnostic imaging; Lung Neoplasms - genetics; Positron Emission Tomography Computed Tomography - methods; Prognosis; prognostic marker; radiogenomics; radiomics; screening; synthetic PET; Tomography, X-Ray Computed; Turing test; generative adversarial network; lung cancer; synthetic PET; radiomics; screening; prognostic marker; generative AI; image synthesis; radiogenomics; Turing test
• ISSN: 2666-3791; 2666-3791
• DOI: 10.1016/j.xcrm.2024.101463

[18F]Fluorodeoxyglucose positron emission tomography (FDG-PET) and computed tomography (CT) are indispensable components in modern medicine. Although PET can provide additional diagnostic value, it is costly and not universally accessible, particularly in low-income countries. To bridge this gap, we have developed a conditional generative adversarial network pipeline that can produce FDG-PET from diagnostic CT scans based on multi-center multi-modal lung cancer datasets (n = 1,478). Synthetic PET images are validated across imaging, biological, and clinical aspects. Radiologists confirm comparable imaging quality and tumor contrast between synthetic and actual PET scans. Radiogenomics analysis further proves that the dysregulated cancer hallmark pathways of synthetic PET are consistent with actual PET. We also demonstrate the clinical values of synthetic PET in improving lung cancer diagnosis, staging, risk prediction, and prognosis. Taken together, this proof-of-concept study testifies to the feasibility of applying deep learning to obtain high-fidelity PET translated from CT. [Display omitted] •Deep learning can generate high-fidelity synthetic PET from CT•Radiologists confirm high imaging fidelity between synthetic and actual PET•Radiogenomics proves the biological fidelity of synthetic PET•Synthetic PET improves cancer diagnosis, risk prediction, and prognosis Salehjahromi et al. develop a GAN-based CT-to-PET translation framework and validate it through thoracic radiologists and radiogenomics analysis. The synthetic PET scans demonstrate potential in enhancing early lung cancer detection, stratification of high-risk populations, and prognostication. Early assessments indicate promising applications in clinical oncology practice.