Multicentric development and evaluation of 18F-FDG PET/CT and MRI radiomics models to predict para-aortic lymph node involvement in locally advanced cervical cancer

• Published in: European journal of nuclear medicine and molecular imaging Vol. 50; no. 8; pp. 2514 - 2528
• Main Authors: Lucia, François, Bourbonne, Vincent, Pleyers, Clémence, Dupré, Pierre-François, Miranda, Omar, Visvikis, Dimitris, Pradier, Olivier, Abgral, Ronan, Mervoyer, Augustin, Classe, Jean-Marc, Rousseau, Caroline, Vos, Wim, Hermesse, Johanne, Gennigens, Christine, De Cuypere, Marjolein, Kridelka, Frédéric, Schick, Ulrike, Hatt, Mathieu, Hustinx, Roland, Lovinfosse, Pierre
• Format: Journal Article Web Resource
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01-07-2023; Springer Nature B.V; Springer Verlag (Germany) [1976-....]; Springer Science and Business Media LLC
• Subjects: 18F-FDG PET/CT; Advanced Image Analyses (Radiomics and Artificial Intelligence); Aorta; Cancer; Cardiology; Cervical cancer; Chemoradiotherapy; Digital 18F-FDG PET/CT; Female; Fluorine isotopes; Fluorodeoxyglucose F18; General Medicine; Human health and pathology; Human health sciences; Humans; Imaging; Life Sciences; Lymph Nodes; Lymphatic system; Machine learning; Magnetic Resonance Imaging; Mathematical models; Medicine; Medicine & Public Health; MRI; Neural networks; Nuclear Medicine; Oncology; Original Article; Orthopedics; Para-aortic lymph node; Parameters; Positron emission; Positron emission tomography; Positron Emission Tomography Computed Tomography; Prediction models; Radiation; Radiologie, médecine & imagerie nucléaire; Radiology; Radiology, nuclear medicine & imaging; Radiology, Nuclear Medicine and imaging; Radiomics; Retrospective Studies; Sciences de la santé humaine; Statistical analysis; Statistics; Training; Uterine Cervical Neoplasms; Digital; Para-aortic lymph node; F-FDG PET/CT; MRI; Cervical cancer; Radiomics; 18F-FDG PET/CT; Digital 18F-FDG PET/CT
• ISSN: 1619-7070; 1619-7089; 1619-7089
• DOI: 10.1007/s00259-023-06180-w

Purpose
To develop machine learning models to predict para-aortic lymph node (PALN) involvement in patients with locally advanced cervical cancer (LACC) before chemoradiotherapy (CRT) using
18
F-FDG PET/CT and MRI radiomics combined with clinical parameters.
Methods
We retrospectively collected 178 patients (60% for training and 40% for testing) in 2 centers and 61 patients corresponding to 2 further external testing cohorts with LACC between 2010 to 2022 and who had undergone pretreatment analog or digital
18
F-FDG PET/CT, pelvic MRI and surgical PALN staging. Only primary tumor volumes were delineated. Radiomics features were extracted using the Radiomics toolbox®. The ComBat harmonization method was applied to reduce the batch effect between centers. Different prediction models were trained using a neural network approach with either clinical, radiomics or combined models. They were then evaluated on the testing and external validation sets and compared.
Results
In the training set (
n
 = 102), the clinical model achieved a good prediction of the risk of PALN involvement with a C-statistic of 0.80 (95% CI 0.71, 0.87). However, it performed in the testing (
n
 = 76) and external testing sets (
n
 = 30 and
n
 = 31) with C-statistics of only 0.57 to 0.67 (95% CI 0.36, 0.83). The ComBat-radiomic (GLDZM_HISDE_PET_FBN64 and Shape_maxDiameter2D3_PET_FBW0.25) and ComBat-combined (FIGO 2018 and same radiomics features) models achieved very high predictive ability in the training set and both models kept the same performance in the testing sets, with C-statistics from 0.88 to 0.96 (95% CI 0.76, 1.00) and 0.85 to 0.92 (95% CI 0.75, 0.99), respectively.
Conclusions
Radiomic features extracted from pre-CRT analog and digital
18
F-FDG PET/CT outperform clinical parameters in the decision to perform a para-aortic node staging or an extended field irradiation to PALN. Prospective validation of our models should now be carried out.