Metastatic Cancer Outcome Prediction with Injective Multiple Instance Pooling

TL;DR

This paper introduces injective multiple instance pooling functions to improve outcome prediction in metastatic cancer using medical imaging, achieving state-of-the-art results on public datasets.

Contribution

Proposes novel injective pooling functions for multiple instance learning, enhancing outcome prediction accuracy in metastatic cancer imaging analysis.

Findings

Achieved state-of-the-art performance on non-small-cell lung cancer CT outcome prediction.

Developed a benchmark cohort of 341 patients for multifocal metastatic cancer studies.

Released datasets, code, and features for reproducible research.

Abstract

Cancer stage is a large determinant of patient prognosis and management in many cancer types, and is often assessed using medical imaging modalities, such as CT and MRI. These medical images contain rich information that can be explored to stratify patients within each stage group to further improve prognostic algorithms. Although the majority of cancer deaths result from metastatic and multifocal disease, building imaging biomarkers for patients with multiple tumors has been a challenging task due to the lack of annotated datasets and standard study framework. In this paper, we process two public datasets to set up a benchmark cohort of 341 patient in total for studying outcome prediction of multifocal metastatic cancer. We identify the lack of expressiveness in common multiple instance classification networks and propose two injective multiple instance pooling functions that are better suited to outcome prediction. Our results show that multiple instance learning with injective pooling functions can achieve state-of-the-art performance in the non-small-cell lung cancer CT and head and neck CT outcome prediction benchmarking tasks. We will release the processed multifocal datasets, our code and the intermediate files i.e. extracted radiomic features to support further transparent and reproducible research.