BioFors: A Large Biomedical Image Forensics Dataset

TL;DR

BioFors introduces a comprehensive biomedical image forensics dataset with benchmark tasks, revealing that current algorithms lack robustness for biomedical images and highlighting the need for specialized forensic methods.

Contribution

This paper presents BioFors, the first large-scale dataset for biomedical image forensics, along with benchmark tasks and analysis of existing algorithm limitations.

Findings

Existing algorithms are not robust on biomedical images

Biomedical image forensics requires specialized algorithms

BioFors enables standardized benchmarking in this domain

Abstract

Research in media forensics has gained traction to combat the spread of misinformation. However, most of this research has been directed towards content generated on social media. Biomedical image forensics is a related problem, where manipulation or misuse of images reported in biomedical research documents is of serious concern. The problem has failed to gain momentum beyond an academic discussion due to an absence of benchmark datasets and standardized tasks. In this paper we present BioFors -- the first dataset for benchmarking common biomedical image manipulations. BioFors comprises 47,805 images extracted from 1,031 open-source research papers. Images in BioFors are divided into four categories -- Microscopy, Blot/Gel, FACS and Macroscopy. We also propose three tasks for forensic analysis -- external duplication detection, internal duplication detection and cut/sharp-transition detection. We benchmark BioFors on all tasks with suitable state-of-the-art algorithms. Our results and analysis show that existing algorithms developed on common computer vision datasets are not robust when applied to biomedical images, validating that more research is required to address the unique challenges of biomedical image forensics.