Survival Prediction in Lung Cancer through Multi-Modal Representation Learning

TL;DR

This paper introduces a multi-modal learning approach combining CT, PET scans, and genomic data to improve lung cancer survival prediction by aligning patient representations across modalities and leveraging inter-patient similarities.

Contribution

It develops a novel multi-modal representation learning framework with a cross-patient module to better capture associations across patients and modalities for survival prediction.

Findings

Outperforms state-of-the-art methods on NSCLC dataset

Effective integration of imaging and genomic data

Improved alignment of patient embeddings

Abstract

Survival prediction is a crucial task associated with cancer diagnosis and treatment planning. This paper presents a novel approach to survival prediction by harnessing comprehensive information from CT and PET scans, along with associated Genomic data. Current methods rely on either a single modality or the integration of multiple modalities for prediction without adequately addressing associations across patients or modalities. We aim to develop a robust predictive model for survival outcomes by integrating multi-modal imaging data with genetic information while accounting for associations across patients and modalities. We learn representations for each modality via a self-supervised module and harness the semantic similarities across the patients to ensure the embeddings are aligned closely. However, optimizing solely for global relevance is inadequate, as many pairs sharing similar high-level semantics, such as tumor type, are inadvertently pushed apart in the embedding space. To address this issue, we use a cross-patient module (CPM) designed to harness inter-subject correspondences. The CPM module aims to bring together embeddings from patients with similar disease characteristics. Our experimental evaluation of the dataset of Non-Small Cell Lung Cancer (NSCLC) patients demonstrates the effectiveness of our approach in predicting survival outcomes, outperforming state-of-the-art methods.