Quantitative susceptibility mapping (QSM) is a promising iron quantification method for assessing subcortical deep gray matter (SGM) in various neurodegenerative diseases. The accuracy of the measurement depends largely on the accuracy of the structural segmentation. Manually drawn regions-of-interest from a well-trained specialist are often the best but are very time-consuming. In this work, we propose an automatic segmentation method for DGM iron quantification by taking advantage of a hybrid image approach combining T1W images and QSM data. Preliminary results on 5 stroke patients presented an overall 77.8±5.8% Dice coefficient compared to the manually drawn ground truth. The measured susceptibility of the DGM showed good agreement between both methods.