PairedContrast: A Multimodal Benchmark for Medical Image Translation

ICLR 2026 Conference Submission92 Authors

Keywords: benchmark; pan-cancer; paired datasets; medical image translation; contrast media

Abstract: Contrast medium play a pivotal role in radiological imaging, as it amplifies lesion conspicuity and improves detection in the diagnosis of tumor-related diseases. However, depending on the patient’s health condition or the medical resources available, the use of contrast medium is not always feasible. Recent work has therefore explored AI-based image translation to synthesize contrast-enhanced images directly from non-contrast scans, aiming to reduce side effects and streamline clinical workflows. Progress in this direction has been constrained by data limitations: (1) existing public datasets focus almost exclusively on brain-only paired MR modalities; (2) other collections include partially paired data but suffer from missing modalities/timestamps and imperfect spatial alignment; (3) explicit labeling of CT vs. CTC or DCE phases is often absent; (4) substantial resources remain private. To bridge this gap, we introduce the first public, fully paired, pan-cancer medical imaging dataset spanning 11 human organs. The MR data include complete dynamic contrast-enhanced (DCE) sequences covering all three phases (DCE1–DCE3), while the CT data provide paired non-contrast and contrast-enhanced acquisitions (CTC). The dataset is curated for anatomical correspondence, enabling rigorous evaluation of 1 → 1, N → 1, and N → N translation settings (e.g., predicting DCE phases from non-contrast inputs). Built upon this resource, we establish a comprehensive benchmark. We report results from representative baselines of contemporary image-to-image translation. We release the dataset and benchmark to catalyze research on safe, effective contrast synthesis, with direct relevance to multi-organ oncology imaging workflows.

Primary Area: datasets and benchmarks

Submission Number: 92