OncoNet: Weakly Supervised Siamese Network to automate cancer treatment response assessment between longitudinal FDG PET/CT examinations
This provides clinicians with a tool for rapid, consistent interpretation of imaging changes, though it is incremental as it builds on existing weak supervision and Siamese network methods.
The paper tackled automating cancer treatment response assessment from longitudinal FDG PET/CT exams using weak supervision, achieving AUROCs of 0.86 and 0.84 on internal and external test sets and a kappa score of 0.8 for clinical agreement.
FDG PET/CT imaging is a resource intensive examination critical for managing malignant disease and is particularly important for longitudinal assessment during therapy. Approaches to automate longtudinal analysis present many challenges including lack of available longitudinal datasets, managing complex large multimodal imaging examinations, and need for detailed annotations for traditional supervised machine learning. In this work we develop OncoNet, novel machine learning algorithm that assesses treatment response from a 1,954 pairs of sequential FDG PET/CT exams through weak supervision using the standard uptake values (SUVmax) in associated radiology reports. OncoNet demonstrates an AUROC of 0.86 and 0.84 on internal and external institution test sets respectively for determination of change between scans while also showing strong agreement to clinical scoring systems with a kappa score of 0.8. We also curated a dataset of 1,954 paired FDG PET/CT exams designed for response assessment for the broader machine learning in healthcare research community. Automated assessment of radiographic response from FDG PET/CT with OncoNet could provide clinicians with a valuable tool to rapidly and consistently interpret change over time in longitudinal multi-modal imaging exams.