Post-hoc Overall Survival Time Prediction from Brain MRI

TL;DR

This paper presents a post-hoc method for predicting overall survival time from brain MRI scans that does not require tumor segmentation labels for training, making it more applicable to large-scale datasets.

Contribution

The authors introduce a novel post-hoc OS prediction model that uses only survival time and demographics for training, eliminating the need for costly segmentation labels.

Findings

Achieves competitive OS prediction accuracy compared to state-of-the-art pre-hoc methods.

Provides tumor localization via saliency maps without segmentation labels.

Reduces reliance on expensive annotated datasets.

Abstract

Overall survival (OS) time prediction is one of the most common estimates of the prognosis of gliomas and is used to design an appropriate treatment planning. State-of-the-art (SOTA) methods for OS time prediction follow a pre-hoc approach that require computing the segmentation map of the glioma tumor sub-regions (necrotic, edema tumor, enhancing tumor) for estimating OS time. However, the training of the segmentation methods require ground truth segmentation labels which are tedious and expensive to obtain. Given that most of the large-scale data sets available from hospitals are unlikely to contain such precise segmentation, those SOTA methods have limited applicability. In this paper, we introduce a new post-hoc method for OS time prediction that does not require segmentation map annotation for training. Our model uses medical image and patient demographics (represented by age) as inputs to estimate the OS time and to estimate a saliency map that localizes the tumor as a way to explain the OS time prediction in a post-hoc manner. It is worth emphasizing that although our model can localize tumors, it uses only the ground truth OS time as training signal, i.e., no segmentation labels are needed. We evaluate our post-hoc method on the Multimodal Brain Tumor Segmentation Challenge (BraTS) 2019 data set and show that it achieves competitive results compared to pre-hoc methods with the advantage of not requiring segmentation labels for training.