Towards a deep learning approach for classifying treatment response in glioblastomas
Journal:
arXiv
Published Date:
Apr 25, 2025
Abstract
Glioblastomas are the most aggressive type of glioma, having a 5-year
survival rate of 6.9%. Treatment typically involves surgery, followed by
radiotherapy and chemotherapy, and frequent magnetic resonance imaging (MRI)
scans to monitor disease progression. To assess treatment response,
radiologists use the Response Assessment in Neuro-Oncology (RANO) criteria to
categorize the tumor into one of four labels based on imaging and clinical
features: complete response, partial response, stable disease, and progressive
disease. This assessment is very complex and time-consuming. Since deep
learning (DL) has been widely used to tackle classification problems, this work
aimed to implement the first DL pipeline for the classification of RANO
criteria based on two consecutive MRI acquisitions. The models were trained and
tested on the open dataset LUMIERE. Five approaches were tested: 1) subtraction
of input images, 2) different combinations of modalities, 3) different model
architectures, 4) different pretraining tasks, and 5) adding clinical data. The
pipeline that achieved the best performance used a Densenet264 considering only
T1-weighted, T2-weighted, and Fluid Attenuated Inversion Recovery (FLAIR)
images as input without any pretraining. A median Balanced Accuracy of 50.96%
was achieved. Additionally, explainability methods were applied. Using Saliency
Maps, the tumor region was often successfully highlighted. In contrast,
Grad-CAM typically failed to highlight the tumor region, with some exceptions
observed in the Complete Response and Progressive Disease classes, where it
effectively identified the tumor region. These results set a benchmark for
future studies on glioblastoma treatment response assessment based on the RANO
criteria while emphasizing the heterogeneity of factors that might play a role
when assessing the tumor's response to treatment.
