aiqbench analysis
The AMPLIFAI dataset addresses a critical bottleneck in medical AI by providing the first public, high-quality collection of multiphase CT scans annotated with LI-RADS criteria for liver cancer diagnosis. By explicitly segmenting key radiological features like arterial phase hyperenhancement and washout, this resource enables robust benchmarking of computer vision models aimed at automating hepatocellular carcinoma detection without invasive biopsies. Its release fosters reproducible research in a domain where data scarcity has previously stifled the development of reliable diagnostic algorithms.
AMPLIFAI: A Multiphase CT Dataset for Benchmarking Clinical Reasoning in LI-RADS Assessment of Liver Lesions
arXiv:2608.14778v1 Announce Type: cross Abstract: Hepatocellular carcinoma (HCC) is the third leading cause of cancer-related mortality worldwide, with early detection improving survival from 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.
Authors:Pranav Kulkarni, Nikhil Shah, Amritansh Suryavanshi, Jana Delfino, James Tonascia, Jade Wong-You-Cheong, Barton Lane, Joseph Chirico, Jeffrey D. Hirsch, Ang Li, Heng Huang, Florence X. Doo
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.
Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
arXiv:2608.14778 [cs.CV]
(or arXiv:2608.14778v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2608.14778 arXiv-issued DOI via DataCite (pending registration)
Full text under the publisher's open licence · 170 words
Related coverage
SPARC-Rad: A Multimodal Benchmark Dataset and Evaluation Pipeline for Spatial and Anatomical Reasoning in Radiology Vision-Language Models
arXiv · Aug 5, 2026
Introducing NV-Reason-CT Open 3D CT VLM for Radiologist Chain-of-Thought Reasoning
NVIDIA · Sep 23, 2026
Does Language Shift Break Medical Vision-Language Models? Indonesian Radiology Visual Question Answering Case Study
arXiv · Jun 3, 2026
NVIDIA’s NV-Reason-CT brings AI reasoning to 3D CT scans
Quantum Zeitgeist · Sep 24, 2026