Multimodal Learning for Non-small Cell Lung Cancer Prognosis
This work addresses the problem of improving prognosis accuracy for lung cancer patients, representing an incremental advance by incorporating multimodal data inspired by clinical practice.
The paper tackled survival time analysis for non-small cell lung cancer by developing a multimodal network that uses both textual clinical data and visual scans, achieving a new state-of-the-art concordance of 89.3%.
This paper focuses on the task of survival time analysis for lung cancer. Although much progress has been made in this problem in recent years, the performance of existing methods is still far from satisfactory. Traditional and some deep learning-based survival time analyses for lung cancer are mostly based on textual clinical information such as staging, age, histology, etc. Unlike existing methods that predicting on the single modality, we observe that a human clinician usually takes multimodal data such as text clinical data and visual scans to estimate survival time. Motivated by this, in this work, we contribute a smart cross-modality network for survival analysis network named Lite-ProSENet that simulates a human's manner of decision making. Extensive experiments were conducted using data from 422 NSCLC patients from The Cancer Imaging Archive (TCIA). The results show that our Lite-ProSENet outperforms favorably again all comparison methods and achieves the new state of the art with the 89.3% on concordance. The code will be made publicly available.