Hepatic Vessel Map (HVM): An Expert-Annotated CT Dataset for Clinically Applicable AI in Liver Vascular Segmentation
Tingting Xie1,2,3,4, Xunqi Li5, Linyu Zhang2
1Guangdong Cardiovascular Institute, Guangdong Provincial People's Hospital, Guangdong Academy of Sciences, Guangzhou, 510080, China.
Insights
The Hepatic Vessel Map (HVM) Dataset offers detailed 3D CT annotations for liver and portal veins, crucial for AI in liver disease diagnosis and surgical planning. This resource aids in developing better AI models for hepatobiliary surgery.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Hepatobiliary Surgery
Background:
- Accurate hepatic and portal venous anatomy visualization is vital for liver disease management and surgical interventions.
- Current 3D CT segmentation methods are manual, time-consuming, and operator-dependent.
- Existing AI approaches lack sufficient annotated data and validation in diseased liver populations.
Purpose of the Study:
- To introduce the Hepatic Vessel Map (HVM) Dataset, a comprehensive resource for hepatic and portal venous anatomy.
- To address the limitations of current AI methods in liver vascular segmentation and analysis.
- To support the development of AI-driven tools for hepatobiliary surgery and intervention.
Main Methods:
- Creation of a dual-center dataset with contrast-enhanced CT scans from 282 patients.
- Detailed annotation of hepatic veins, portal veins (to third-order branches), and liver tumors across over 41,400 slices.
- Inclusion of a significant proportion of cases with underlying hepatic pathology and validation for preoperative planning.
Main Results:
- The HVM Dataset contains over 48,300 annotations, providing fine-grained vascular details.
- The dataset includes diverse cases, with a focus on diseased liver populations relevant to clinical practice.
- Validation confirms the dataset's utility for preoperative planning in major hepatectomy.
Conclusions:
- The HVM Dataset is a foundational resource for developing and benchmarking AI segmentation models for hepatic and portal venous structures.
- It enables quantitative vascular research and the creation of patient-specific 3D "digital vascular roadmaps".
- This resource will advance AI-driven innovations in hepatobiliary surgery, improving precision and patient safety.
Abstract:
Precise delineation of hepatic and portal venous anatomy is crucial for the diagnosis of liver disease, surgical planning, and prognosis prediction. Current three-dimensional visualization of these complex vascular structures relies on manual or semi-automated CT segmentation, which is time-consuming and operator-dependent. Although artificial intelligence (AI) presents a promising alternative, existing methods remain constrained by the scarcity of publicly available datasets with fine-grained vascular annotations and inadequate validation in real-world diseased liver populations, which represent the majority of patients undergoing hepatic procedures. To address this gap, we present the Hepatic Vessel Map (HVM) Dataset, a dual-center resource comprising contrast-enhanced CT scans from 282 patients with over 4,1400 slices and 4,8300 annotations, each with meticulously annotated hepatic veins, portal veins (to third-order branches), and liver tumors. The dataset comprises a substantial proportion of cases with underlying hepatic pathology and has been validated for use in preoperative planning for major hepatectomy, ensuring both clinical relevance and model generalizability. This dataset supports: 1) development and benchmarking of robust hepatic and portal venous segmentation models; 2) vasoimcs research through quantitative analysis of vascular morphology, topology, and radiomic features; 3) generation of patient-specific 3D "digital vascular roadmaps" to enhance surgical precision and safety. As such, this dataset establishes a foundational resource for advancing AI-driven innovations in hepatobiliary surgery and intervention.
