%0 Journal Article
%A Morawitz, Janna
%A Sigl, Benjamin
%A Rubbert, Christian
%A Bruckmann, Nils-Martin
%A Dietzel, Frederic
%A Häberle, Lena J
%A Ting, Saskia
%A Mohrmann, Svjetlana
%A Ruckhäberle, Eugen
%A Bittner, Ann-Kathrin
%A Hoffmann, Oliver
%A Baltzer, Pascal
%A Kapetas, Panagiotis
%A Helbich, Thomas
%A Clauser, Paola
%A Fendler, Wolfgang P
%A Rischpler, Christoph
%A Herrmann, Ken
%A Schaarschmidt, Benedikt M
%A Stang, Andreas
%A Umutlu, Lale
%A Antoch, Gerald
%A Caspers, Julian
%A Kirchner, Julian
%T Clinical Decision Support for Axillary Lymph Node Staging in Newly Diagnosed Breast Cancer Patients Based on 18F-FDG PET/MRI and Machine Learning.
%J Journal of nuclear medicine
%V 64
%N 2
%@ 0097-9058
%C New York, NY
%I Soc.
%M DKFZ-2023-00281
%P 304 - 311
%D 2023
%X In addition to its high prognostic value, the involvement of axillary lymph nodes in breast cancer patients also plays an important role in therapy planning. Therefore, an imaging modality that can determine nodal status with high accuracy in patients with primary breast cancer is desirable. Our purpose was to investigate whether, in newly diagnosed breast cancer patients, machine-learning prediction models based on simple assessable imaging features on MRI or PET/MRI are able to determine nodal status with performance comparable to that of experienced radiologists; whether such models can be adjusted to achieve low rates of false-negatives such that invasive procedures might potentially be omitted; and whether a clinical framework for decision support based on simple imaging features can be derived from these models. Methods: Between August 2017 and September 2020, 303 participants from 3 centers prospectively underwent dedicated whole-body 18F-FDG PET/MRI. Imaging datasets were evaluated for axillary lymph node metastases based on morphologic and metabolic features. Predictive models were developed for MRI and PET/MRI separately using random forest classifiers on data from 2 centers and were tested on data from the third center. Results: The diagnostic accuracy for MRI features was 87.5
%K Humans
%K Female
%K Fluorodeoxyglucose F18
%K Breast Neoplasms: diagnostic imaging
%K Breast Neoplasms: pathology
%K Decision Support Systems, Clinical
%K Sensitivity and Specificity
%K Lymph Nodes: diagnostic imaging
%K Lymph Nodes: pathology
%K Magnetic Resonance Imaging
%K Neoplasm Staging
%K Radiopharmaceuticals
%K PET/MRI (Other)
%K breast cancer (Other)
%K lymph node metastases (Other)
%K machine learning (Other)
%K Fluorodeoxyglucose F18 (NLM Chemicals)
%K Radiopharmaceuticals (NLM Chemicals)
%F PUB:(DE-HGF)16
%9 Journal Article
%$ pmid:36137756
%R 10.2967/jnumed.122.264138
%U https://inrepo02.dkfz.de/record/265119