AMPLIFAI: A Multiphase CT Dataset for Benchmarking Clinical Reasoning in LI-RADS Assessment of Liver Lesions

2026-08-14

AI Summary

This study addresses the critical bottleneck of lacking high-quality, publicly available multi-phase CT datasets supporting LI-RADS assessment by introducing AMPLIFAI. As the first open-access resource to provide both LI-RADS categorization and fine-grained segmentation annotations for three key imaging features, this dataset strictly adheres to standardized data sheet specifications. By offering structured and reproducible benchmark data, AMPLIFAI effectively bridges a significant gap in the field. Consequently, it substantially advances research on AI-driven hepatocellular carcinoma diagnosis, particularly in enhancing model transparency, standardization, and clinical trustworthiness. This contribution establishes a foundational resource for developing more reliable and interpretable diagnostic algorithms in liver cancer imaging.

Abstract

Hepatocellular carcinoma (HCC) is the third leading cause of cancer-related mortality worldwide, with early detection improving survival from <20\% to >70\%. The standardized LI-RADS criteria establish a biopsy-free, fully imaging-based framework that can serve as a foundation for automating HCC diagnosis with artificial intelligence (AI). However, the lack of large, publicly available datasets with high-quality labels has limited the development of AI models for LI-RADS characterization. We introduce the \textbf{AMPLIFAI} dataset, the first public dataset of multiphase abdominal CT scans annotated with LI-RADS categories and segmented for three major LI-RADS features: arterial phase hyperenhancement, washout, and enhancing capsule. Following the \emph{Datasheets for Datasets} format, this paper details the dataset's composition, curation process, and annotation pipeline to facilitate transparent, reproducible research.

Problem

• LI-RADS
• Hepatocellular Carcinoma
• Dataset
• Clinical Reasoning

Innovation

• AMPLIFAI Dataset
• LI-RADS Assessment
• Multiphase CT
• Feature Segmentation
• Clinical Reasoning