Kavli Affiliate: Jing Wang
| First 5 Authors: Erich Schmitz, Yunhui Guo, Jing Wang, ,
| Summary:
Glioblastoma Multiforme (GBM) is an aggressive form of malignant brain tumor
with a generally poor prognosis. Treatment usually includes a mix of surgical
resection, radiation therapy, and akylating chemotherapy but, even with these
intensive treatments, the 2-year survival rate is still very low.
O6-methylguanine-DNA methyltransferase (MGMT) promoter methylation has been
shown to be a predictive bio-marker for resistance to chemotherapy, but it is
invasive and time-consuming to determine the methylation status. Due to this,
there has been effort to predict the MGMT methylation status through analyzing
MRI scans using machine learning, which only requires pre-operative scans that
are already part of standard-of-care for GBM patients. We developed a 3D
SpotTune network with adaptive fine-tuning capability to improve the
performance of conventional transfer learning in the identification of MGMT
promoter methylation status. Using the pretrained weights of MedicalNet coupled
with the SpotTune network, we compared its performance with two equivalent
networks: one that is initialized with MedicalNet weights, but with no adaptive
fine-tuning and one initialized with random weights. These three networks are
trained and evaluated using the UPENN-GBM dataset, a public GBM dataset
provided by the University of Pennsylvania. The SpotTune network showed better
performance than the network with randomly initialized weights and the
pre-trained MedicalNet with no adaptive fine-tuning. SpotTune enables transfer
learning to be adaptive to individual patients, resulting in improved
performance in predicting MGMT promoter methylation status in GBM using MRIs as
compared to conventional transfer learning without adaptive fine-tuning.
| Search Query: ArXiv Query: search_query=au:”Jing Wang”&id_list=&start=0&max_results=3