Weighted Concordance Index Loss-based Multimodal Survival Modeling for Radiation Encephalopathy Assessment in Nasopharyngeal Carcinoma Radiotherapy

TL;DR

This paper introduces a novel multimodal survival network with a weighted concordance index loss to improve prediction of radiation encephalopathy risk in nasopharyngeal carcinoma radiotherapy, effectively utilizing image and non-image data.

Contribution

It proposes a new weighted CI loss function and a multimodal deep survival network for better REP prediction in NPC radiotherapy.

Findings

WCI loss improves model convergence and accuracy.

Multimodal data enhances REP risk prediction.

The approach outperforms existing methods on private dataset.

Abstract

Radiation encephalopathy (REP) is the most common complication for nasopharyngeal carcinoma (NPC) radiotherapy. It is highly desirable to assist clinicians in optimizing the NPC radiotherapy regimen to reduce radiotherapy-induced temporal lobe injury (RTLI) according to the probability of REP onset. To the best of our knowledge, it is the first exploration of predicting radiotherapy-induced REP by jointly exploiting image and non-image data in NPC radiotherapy regimen. We cast REP prediction as a survival analysis task and evaluate the predictive accuracy in terms of the concordance index (CI). We design a deep multimodal survival network (MSN) with two feature extractors to learn discriminative features from multimodal data. One feature extractor imposes feature selection on non-image data, and the other learns visual features from images. Because the priorly balanced CI (BCI) loss function directly maximizing the CI is sensitive to uneven sampling per batch. Hence, we propose a novel weighted CI (WCI) loss function to leverage all REP samples effectively by assigning their different weights with a dual average operation. We further introduce a temperature hyper-parameter for our WCI to sharpen the risk difference of sample pairs to help model convergence. We extensively evaluate our WCI on a private dataset to demonstrate its favourability against its counterparts. The experimental results also show multimodal data of NPC radiotherapy can bring more gains for REP risk prediction.