Related Experiment Video
Updated: Mar 13, 2026
Imaging and Quantification of the Hepatic Vasculature of Mice Using Ultrafast Doppler Ultrasound
Published on: July 19, 2024
SMC-LUD:Large-Scale B-Mode Liver Ultrasound Dataset for Hepatocellular Carcinoma and Hemangioma Classification
Jisoo Tak1,2, Ryoung-Eun Ko3, Ryan Donghan Kwon4
1Department of MetaBioBealth, Institute for Cross-disciplinary Studies, Sungkyunkwan University, Suwon, South Korea.
Insights
A new dataset of 5,385 liver ultrasound images aids hepatocellular carcinoma (HCC) classification. This resource supports AI development for liver cancer diagnosis.
Area of Science:
- Medical Imaging
- Oncology
- Data Science
Background:
- Hepatocellular carcinoma (HCC) is a major global cause of cancer mortality.
- Accurate classification of liver lesions via ultrasound is difficult.
- There is a lack of large, well-annotated ultrasound datasets for liver lesion classification.
Purpose of the Study:
- To introduce the Samsung Medical Center - Liver Ultrasound Dataset (SMC-LUD).
- To provide a valuable resource for developing and validating AI models for liver cancer diagnosis.
Main Methods:
- Collected 5,385 B-mode liver ultrasound images from 1,021 patients (2015-2024).
- Categorized images into hepatocellular carcinoma (2,716) and hemangioma (2,669).
- Ensured diagnostic accuracy through histopathological confirmation (HCC) and radiological diagnosis (hemangioma), with radiologist and pathologist verification.
Main Results:
- Established the SMC-LUD, a publicly available dataset.
- Dataset includes 5,385 anonymized images with patient-level organization.
- Contains histopathologically confirmed HCC and radiologically diagnosed hemangioma cases.
Conclusions:
- The SMC-LUD addresses the scarcity of annotated liver ultrasound data.
- This dataset will facilitate the advancement of deep learning models for liver cancer screening and diagnosis.
Abstract:
Hepatocellular carcinoma (HCC) is a leading cause of cancer-related mortality globally, and accurate classification of liver lesions using ultrasound remains challenging. We present SMC-LUD (Samsung Medical Center - Liver Ultrasound Dataset), a publicly available dataset of B-mode liver ultrasound images collected from Samsung Medical Center, Seoul, Korea, between 2015 and 2024. The dataset comprises 5,385 anonymized ultrasound images from 1,021 patients, categorized into two clinically relevant classes: hepatocellular carcinoma (images = 2,716) and hemangioma (images = 2,669). All HCC cases were histopathologically confirmed through surgical resection or biopsy, while hemangioma cases were radiologically diagnosed based on characteristic imaging features. Each image was labeled and verified by board-certified radiologists and pathologists. The dataset is organized with patient-level grouping. This resource addresses the scarcity of large, well-annotated ultrasound datasets for liver lesion classification and provides a valuable foundation for developing and validating deep learning models in liver cancer screening and diagnosis.
