Prediction of pathologic complete response of neoadjuvant chemotherapy for early triple negative breast cancer using pre-therapeutic MRI

Angeline Nemeth (1) , Pierre Chaudet (2) , Benjamin Leporq (1) , Pierre-Étienne Heudel (2) , Olivier Trédan (2) , Isabelle Treilleux (2) , Franck Pilleul (1, 2) , Agnes Coulon (2) , O. Beuf (1)

1 RMN et optique : De la mesure au biomarqueur
2 Centre Léon Bérard [Lyon]

A total of 76 patients were enrolled in this retrospective monocentric study. All patients had a non-metastatic triple negative breast cancer and underwent a pre-therapeutic MRI protocol (T1-weighted, T2-weigthed, diffusion-weighted and dynamic-contrast-enhanced imaging) before a neoadjuvant chemotherapy. Results of radiomic analyses based on multiple contrast images and using 3 classifiers (support vector machine, Random forest and multilayer perceptron) were leading to a relative interest of using a combination of features extracted from DCE-MRI, T1W and T2W in the aim to predict responders and non-responders.

Domaines: Imagerie

Angeline Nemeth, Pierre Chaudet, Benjamin Leporq, Pierre-Étienne Heudel, Olivier Trédan, et al.. Prediction of pathologic complete response of neoadjuvant chemotherapy for early triple negative breast cancer using pre-therapeutic MRI. ISMRM 2020, Aug 2020, Visual Conference, France. ⟨hal-02899378⟩