Early Detection and Localization of Pancreatic Cancer by Label-Free Tumor Synthesis

TL;DR

This paper introduces a tumor synthesis method to generate large datasets of small pancreatic tumors in healthy pancreas CT scans, enhancing AI detection and localization of early-stage pancreatic cancer.

Contribution

The study presents a novel tumor synthesis approach that enables training AI models with synthetic data, improving early detection of small pancreatic tumors without manual annotation.

Findings

AI trained on synthetic tumors achieves detection rates comparable to real tumors.

Synthetic tumors significantly improve detection of small pancreatic tumors.

The method enhances AI generalizability across different hospital datasets.

Abstract

Early detection and localization of pancreatic cancer can increase the 5-year survival rate for patients from 8.5% to 20%. Artificial intelligence (AI) can potentially assist radiologists in detecting pancreatic tumors at an early stage. Training AI models require a vast number of annotated examples, but the availability of CT scans obtaining early-stage tumors is constrained. This is because early-stage tumors may not cause any symptoms, which can delay detection, and the tumors are relatively small and may be almost invisible to human eyes on CT scans. To address this issue, we develop a tumor synthesis method that can synthesize enormous examples of small pancreatic tumors in the healthy pancreas without the need for manual annotation. Our experiments demonstrate that the overall detection rate of pancreatic tumors, measured by Sensitivity and Specificity, achieved by AI trained on synthetic tumors is comparable to that of real tumors. More importantly, our method shows a much higher detection rate for small tumors. We further investigate the per-voxel segmentation performance of pancreatic tumors if AI is trained on a combination of CT scans with synthetic tumors and CT scans with annotated large tumors at an advanced stage. Finally, we show that synthetic tumors improve AI generalizability in tumor detection and localization when processing CT scans from different hospitals. Overall, our proposed tumor synthesis method has immense potential to improve the early detection of pancreatic cancer, leading to better patient outcomes.