Chronic active multiple sclerosis (MS) lesions are characterized on Quantitative susceptibility mapping (QSM) by a paramagnetic rim (rim+) at the edge of the lesion. We present QSMRim-Net, a deep neural network that fuses lesion-level radiomic and convolutional image features together for automated identification of rim+ lesions on MRI. On the lesion-level, using five-fold cross validation, the proposed QSMRim-Net detected rim+ lesions with an area under the receiver operating characteristic curve of 0.965 and an area under the precision recall curve of 0.655. QSMRim-Net out-performed other state-of-the-art methods on both metrics.
This abstract and the presentation materials are available to members only; a login is required.