Deep learning for [(18)F]fluorodeoxyglucose-PET-CT classification in patients with lymphoma: A dual-centre retrospective analysis Journal Article

   


Authors: Häggström, I.; Leithner, D.; Alvén, J.; Campanella, G.; Abusamra, M.; Zhang, H.; Chhabra, S.; Beer, L.; Haug, A.; Salles, G.; Raderer, M.; Staber, P. B.; Becker, A.; Hricak, H.; Fuchs, T. J.; Schöder, H.; Mayerhoefer, M. E.
Article Title: Deep learning for [(18)F]fluorodeoxyglucose-PET-CT classification in patients with lymphoma: A dual-centre retrospective analysis
Abstract: Background: The rising global cancer burden has led to an increasing demand for imaging tests such as [18F]fluorodeoxyglucose ([18F]FDG)-PET-CT. To aid imaging specialists in dealing with high scan volumes, we aimed to train a deep learning artificial intelligence algorithm to classify [18F]FDG-PET-CT scans of patients with lymphoma with or without hypermetabolic tumour sites. 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. © 2024 The Author(s). Published by Elsevier Ltd. This is an Open Access article under the CC BY 4.0 license
Keywords: adult; aged; retrospective studies; major clinical study; area under the curve; united states; diagnostic accuracy; sensitivity and specificity; radiopharmaceuticals; mantle cell lymphoma; cohort analysis; diagnostic imaging; oncology; retrospective study; hodgkin disease; computerized tomography; artificial intelligence; lymphoma; fluorodeoxyglucose f 18; fluorodeoxyglucose f18; radiopharmaceutical agent; follicular lymphoma; diseases; receiver operating characteristic; classification algorithm; after-treatment; retrospective analysis; diagnostic test accuracy study; procedures; fdg pet; tumor metabolism; diffuse large b cell lymphoma; classification (of information); tumor site; learning systems; maximum intensity projection; ct-scan; humans; human; male; female; article; deep learning; positron emission tomography-computed tomography; positron emission tomography computed tomography; artificial intelligence algorithms; areas under the curves; f-fluorodeoxyglucose; imaging tests; lymphoma artificial reader system
Journal Title: The Lancet Digital Health
Volume: 6
Issue: 2
ISSN: 2589-7500
Publisher: Elsevier Inc.  
Date Published: 2024-02-01
Start Page: e114
End Page: e125
Language: English
DOI: 10.1016/s2589-7500(23)00203-0
PUBMED: 38135556
PROVIDER: scopus
PMCID: PMC10972536
DOI/URL:

https://www.scopus.com/inward/record.uri?eid=2-s2.0-85180592075&doi=10.1016%2fS2589-7500%2823%2900203-0&partnerID=40&md5=1679cd0e3f107f4920ba2c50c38239ef
Notes: Article -- MSK Cancer Center Support Grant (P30 CA008748) acknowledged in PDF -- Source: Scopus
Altmetric
What is Altmetric?
Citation Impact
What is Dimensions Citation Badge?
BMJ Impact Analytics
MSK Authors
  1. Heiko Schoder
    542 Schoder
  2. Hedvig Hricak
    419 Hricak
  3. Ida Haeggstroem
    11 Haeggstroem
  4. Doris Leithner
    43 Leithner
  5. Marius E Mayerhoefer
    70 Mayerhoefer
  6. Anton Sebastian Becker
    40 Becker
  7. Gilles Andre Salles
    269 Salles
  8. Murad Mohammad Abusamra
    8 Abusamra
  9. Honglei Zhang
    3 Zhang
  10. Shalini Chhabra
    9 Chhabra
Related MSK Work