A Vessel Bifurcation Landmark Pair Dataset for Abdominal CT Deformable Image Registration (DIR) Validation

2025-01-15

AI Summary

Current deformable image registration (DIR) methods for abdominal CT lack high-precision, anatomically meaningful validation benchmarks—particularly at critical structures such as vascular bifurcations. To address this, we introduce the first vascular bifurcation–based benchmark dataset specifically designed for DIR validation in abdominal CT, comprising 30 patient cases and 1,895 manually refined and algorithm-assisted anatomical landmark pairs. We propose a novel DIR validation paradigm grounded in vascular bifurcation anatomy, integrating U-Net–based organ segmentation, manually guided local block matching, non-rigid projection mapping, and interactive refinement; notably, we incorporate digital phantoms for the first time to enable sub-millimeter ground-truth validation. Our method achieves a mean target registration error of 0.7 ± 1.2 mm, with 63 high-quality landmark pairs per case. The dataset is publicly available on Zenodo, accompanied by comprehensive usage documentation on GitHub.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Calibration & Uncertainty Quantification
• Intelligent Robots: Localization, Mapping, and Navigation

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Systems and Infrastructure for Web, Mobile and WoT: Virtualization and resource management in Web systems and infrastructures
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Deformable image registration (DIR) is an enabling technology in many diagnostic and therapeutic tasks. Despite this, DIR algorithms have limited clinical use, largely due to a lack of benchmark datasets for quality assurance during development. To support future algorithm development, here we introduce our first-of-its-kind abdominal CT DIR benchmark dataset, comprising large numbers of highly accurate landmark pairs on matching blood vessel bifurcations. Abdominal CT image pairs of 30 patients were acquired from several public repositories as well as the authors' institution with IRB approval. The two CTs of each pair were originally acquired for the same patient on different days. An image processing workflow was developed and applied to each image pair: 1) Abdominal organs were segmented with a deep learning model, and image intensity within organ masks was overwritten. 2) Matching image patches were manually identified between two CTs of each image pair 3) Vessel bifurcation landmarks were labeled on one image of each image patch pair. 4) Image patches were deformably registered, and landmarks were projected onto the second image. 5) Landmark pair locations were refined manually or with an automated process. This workflow resulted in 1895 total landmark pairs, or 63 per case on average. Estimates of the landmark pair accuracy using digital phantoms were 0.7+/-1.2mm. The data is published in Zenodo at https://doi.org/10.5281/zenodo.14362785. Instructions for use can be found at https://github.com/deshanyang/Abdominal-DIR-QA. This dataset is a first-of-its-kind for abdominal DIR validation. The number, accuracy, and distribution of landmark pairs will allow for robust validation of DIR algorithms with precision beyond what is currently available.

Problem

• Deformable Image Registration
• Abdominal CT Images
• Vascular Bifurcations

Innovation

• Abdominal CT Image Registration
• Deformable Image Registration (DIR) Accuracy
• Vascular Bifurcation Markers