Deep learning for [18F]fluorodeoxyglucose-PET-CT classification in patients with lymphoma: a dual-centre retrospective analysis
Artikel i vetenskaplig tidskrift, 2024
Methods: In this retrospective analysis we collected 16 583 [18F]FDG-PET-CTs of 5072 patients with lymphoma who had undergone PET-CT before or after treatment at the Memorial Sloa Kettering Cancer Center, New York, NY, USA. Using maximum intensity projection (MIP), three dimensional (3D) PET, and 3D CT data, our ResNet34-based deep learning model (Lymphoma Artificial Reader System [LARS]) for [18F]FDG-PET-CT binary classification (Deauville 1–3 vs 4–5), was trained on 80% of the dataset, and tested on 20% of this dataset. For external testing, 1000 [18F]FDG-PET-CTs were obtained from a second centre (Medical University of Vienna, Vienna, Austria). Seven model variants were evaluated, including MIP-based LARS-avg (optimised for accuracy) and LARS-max (optimised for sensitivity), and 3D PET-CT-based LARS-ptct. Following expert curation, areas under the curve (AUCs), accuracies, sensitivities, and specificities were calculated.
Findings: In the internal test cohort (3325 PET-CTs, 1012 patients), LARS-avg achieved an AUC of 0·949 (95% CI 0·942–0·956), accuracy of 0·890 (0·879–0·901), sensitivity of 0·868 (0·851–0·885), and specificity of 0·913 (0·899–0·925); LARS-max achieved an AUC of 0·949 (0·942–0·956), accuracy of 0·868 (0·858–0·879), sensitivity of 0·909 (0·896–0·924), and specificity of 0·826 (0·808–0·843); and LARS-ptct achieved an AUC of 0·939 (0·930–0·948), accuracy of 0·875 (0·864–0·887), sensitivity of 0·836 (0·817–0·855), and specificity of 0·915 (0·901–0·927). In the external test cohort (1000 PET-CTs, 503 patients), LARS-avg achieved an AUC of 0·953 (0·938–0·966), accuracy of 0·907 (0·888–0·925), sensitivity of 0·874 (0·843–0·904), and specificity of 0·949 (0·921–0·960); LARS-max achieved an AUC of 0·952 (0·937–0·965), accuracy of 0·898 (0·878–0·916), sensitivity of 0·899 (0·871–0·926), and specificity of 0·897 (0·871–0·922); and LARS-ptct achieved an AUC of 0·932 (0·915–0·948), accuracy of 0·870 (0·850–0·891), sensitivity of 0·827 (0·793–0·863), and specificity of 0·913 (0·889–0·937).
Interpretation: Deep learning accurately distinguishes between [18F]FDG-PET-CT scans of lymphoma patients with and without hypermetabolic tumour sites. Deep learning might therefore be potentially useful to rule out the presence of metabolically active disease in such patients, or serve as a second reader or decision support tool. Funding: National Institutes of Health-National Cancer Institute Cancer Center Support Grant.
Författare
Ida Häggström
Chalmers, Elektroteknik, Signalbehandling och medicinsk teknik
Memorial Sloan-Kettering Cancer Center
Doris Leithner
Memorial Sloan-Kettering Cancer Center
New York University
Jennifer Alvén
Chalmers, Elektroteknik, Signalbehandling och medicinsk teknik
Gabriele Campanella
Icahn School of Medicine at Mount Sinai
Murad Abusamra
Memorial Sloan-Kettering Cancer Center
Honglei Zhang
Memorial Sloan-Kettering Cancer Center
Shalini Chhabra
Memorial Sloan-Kettering Cancer Center
Lucian Beer
Medizinische Universität Wien
Alexander Haug
Medizinische Universität Wien
Gilles Salles
Memorial Sloan-Kettering Cancer Center
Weill Cornell Medical College
Markus Raderer
Medizinische Universität Wien
Philipp B. Staber
Memorial Sloan-Kettering Cancer Center
Anton Becker
New York University
Weill Cornell Medical College
Memorial Sloan-Kettering Cancer Center
Hedvig Hricak
Weill Cornell Medical College
Memorial Sloan-Kettering Cancer Center
Thomas J. Fuchs
Icahn School of Medicine at Mount Sinai
Heiko Schöder
Memorial Sloan-Kettering Cancer Center
Weill Cornell Medical College
Marius E. Mayerhoefer
New York University
Medizinische Universität Wien
Memorial Sloan-Kettering Cancer Center
Weill Cornell Medical College
The Lancet Digital Health
25897500 (eISSN)
Vol. 6 2 e114-e125Ämneskategorier
Radiologi och bildbehandling
Cancer och onkologi
DOI
10.1016/S2589-7500(23)00203-0
PubMed
38135556