A Multi-Centric Anthropomorphic 3D CT Phantom-Based Benchmark Dataset for Harmonization

TL;DR

This paper introduces a comprehensive, open-source 3D CT phantom dataset from multiple scanners to facilitate AI harmonization, addressing data distribution shifts caused by different acquisition settings in medical imaging.

Contribution

It provides a standardized benchmark dataset and methodology for developing and evaluating AI harmonization techniques in CT imaging.

Findings

Dataset includes 1378 scans from 13 scanners across 8 institutions.

Baseline results demonstrate variability in image and feature stability.

Open-source code supports further research in AI harmonization.

Abstract

Artificial intelligence (AI) has introduced numerous opportunities for human assistance and task automation in medicine. However, it suffers from poor generalization in the presence of shifts in the data distribution. In the context of AI-based computed tomography (CT) analysis, significant data distribution shifts can be caused by changes in scanner manufacturer, reconstruction technique or dose. AI harmonization techniques can address this problem by reducing distribution shifts caused by various acquisition settings. This paper presents an open-source benchmark dataset containing CT scans of an anthropomorphic phantom acquired with various scanners and settings, which purpose is to foster the development of AI harmonization techniques. Using a phantom allows fixing variations attributed to inter- and intra-patient variations. The dataset includes 1378 image series acquired with 13 scanners from 4 manufacturers across 8 institutions using a harmonized protocol as well as several acquisition doses. Additionally, we present a methodology, baseline results and open-source code to assess image- and feature-level stability and liver tissue classification, promoting the development of AI harmonization strategies.