Meeting Banner
Abstract #3495

Improving the generalizability of convolutional neural networks for T2-lesion segmentation of gliomas in the post-treatment setting

Jacob Ellison1, Francesco Caliva1, Pablo Damasceno2, Tracy Luks1, Marisa LaFontaine1, Julia Cluceru1, Anil Kemisetti1, Yan Li1, Valentina Pedoia2, Javier Villanueva-Meyer1, and Janine M Lupo1
1Radiology and Biomedical Imaging, UCSF, San Francisco, CA, United States, 2Center for Intelligent Imaging, UCSF, San Francisco, CA, United States

Routine monitoring of response to therapy in patients with glioma greatly benefits from using volumetrics quantified from lesion segmentation. Yet, the vast majority of deep learning models developed for this task have been trained using data from treatment-naïve, newly-diagnosed patients, whose T2-lesions have different appearance on imaging. We found that increasing the proportion of treated patients in training, incorporating a cross-entropy loss term that takes into account the spatial distance from surgical resection cavity and leading tumor edge, and transfer learning from newly-diagnosed to post-treatment imaging domains were effective strategies to improve the generalizability of segmentation of the T2-lesion post-treatment.

This abstract and the presentation materials are available to members only; a login is required.

Join Here