Back-in-Time Diffusion: Unsupervised Detection of Medical Deepfakes

TL;DR

This paper introduces a novel unsupervised anomaly detection method for medical images using diffusion models, effectively identifying deepfakes like fake tumors in CT and MRI scans with high accuracy.

Contribution

The work presents a new diffusion-based approach for detecting medical deepfakes, outperforming existing methods and providing datasets and tools for future research.

Findings

Achieved an average AUC of 0.9 for fake tumor injection detection.

Achieved an average AUC of 0.96 for fake tumor removal detection.

Published new datasets and code to facilitate further research.

Abstract

Recent progress in generative models has made it easier for a wide audience to edit and create image content, raising concerns about the proliferation of deepfakes, especially in healthcare. Despite the availability of numerous techniques for detecting manipulated images captured by conventional cameras, their applicability to medical images is limited. This limitation stems from the distinctive forensic characteristics of medical images, a result of their imaging process. In this work we propose a novel anomaly detector for medical imagery based on diffusion models. Normally, diffusion models are used to generate images. However, we show how a similar process can be used to detect synthetic content by making a model reverse the diffusion on a suspected image. We evaluate our method on the task of detecting fake tumors injected and removed from CT and MRI scans. Our method significantly outperforms other state of the art unsupervised detectors with an increased AUC of 0.9 from 0.79 for injection and of 0.96 from 0.91 for removal on average. We also explore our hypothesis using AI explainability tools and publish our code and new medical deepfake datasets to encourage further research into this domain.