Browsing by Author "Zhang, Zhendong"

Now showing 1 - 2 of 2
  • Thumbnail Image
    ItemOpen Access
    A comprehensive lung CT landmark pair dataset for evaluating deformable image registration algorithms.
    (Medical physics, 2024-05) Criscuolo, Edward R; Fu, Yabo; Hao, Yao; Zhang, Zhendong; Yang, Deshan

    Purpose

    Deformable image registration (DIR) is a key enabling technology in many diagnostic and therapeutic tasks, but often does not meet the required robustness and accuracy for supporting clinical tasks. This is in large part due to a lack of high-quality benchmark datasets by which new DIR algorithms can be evaluated. Our team was supported by the National Institute of Biomedical Imaging and Bioengineering to develop DIR benchmark dataset libraries for multiple anatomical sites, comprising of large numbers of highly accurate landmark pairs on matching blood vessel bifurcations. Here we introduce our lung CT DIR benchmark dataset library, which was developed to improve upon the number and distribution of landmark pairs in current public lung CT benchmark datasets.

    Acquisition and validation methods

    Thirty CT image pairs were acquired from several publicly available repositories as well as authors' institution with IRB approval. The data processing workflow included multiple steps: (1) The images were denoised. (2) Lungs, airways, and blood vessels were automatically segmented. (3) Bifurcations were directly detected on the skeleton of the segmented vessel tree. (4) Falsely identified bifurcations were filtered out using manually defined rules. (5) A DIR was used to project landmarks detected on the first image onto the second image of the image pair to form landmark pairs. (6) Landmark pairs were manually verified. This workflow resulted in an average of 1262 landmark pairs per image pair. Estimates of the landmark pair target registration error (TRE) using digital phantoms were 0.4 mm ± 0.3 mm.

    Data format and usage notes

    The data is published in Zenodo at https://doi.org/10.5281/zenodo.8200423. Instructions for use can be found at https://github.com/deshanyang/Lung-DIR-QA.

    Potential applications

    The dataset library generated in this work is the largest of its kind to date and will provide researchers with a new and improved set of ground truth benchmarks for quantitatively validating DIR algorithms within the lung.
  • No Thumbnail Available
    ItemEmbargo
    Liver Vessel Segmentation and Accurate Landmark Pairs Detection for Quantitative Liver Deformable Image Registration Verification
    (2023) Zhang, Zhendong

    Background: Target Registration Error (TRE) calculated based on selected anatomical landmarks is commonly known as the only trustable way to evaluate DIR accuracy. However, manual landmark pair selection is labor intensive and subjected to observer variability. Currently, no DIR benchmark datasets are available for Liver CTs. Manually selected landmark pairs have limited DIR evaluation power due to inadequate landmarks quantity (i.e., ~5 landmark pairs per dataset1 for liver CTs) and positional accuracy. For the purpose of liver DIR verification, there is a great need to establish a large quantity of landmark pairs with good positional accuracy.Purpose: An image processing procedure was developed in this study to automatically and precisely detect landmark pairs on corresponding vessel bifurcations between pairs of intra-patient CT images. With high positional accuracy, the generated landmark pairs can be used to evaluate deformable image registration (DIR) methods quantitatively for liver CTs. Methods: Landmark pairs were detected within the liver between pairs of contrast-enhanced CT scans for 32 patients. For each case, the liver vessel tree was automatically segmented in one image. Landmarks were automatically detected on vessel bifurcations. The corresponding landmarks in the second image were placed using a parametric DIR method (pTVreg). Manual validation was applied to reject outliers and adjust the landmarks’ positions to account for vessel segmentation uncertainty caused by the inconsistent image quality. Landmark pairs' positional accuracy of the procedure was evaluated using digital phantoms on target registration errors (TREs). Results: On average, ~71 landmark pairs per case were detected after manual outlier rejection. The proposed procedure increased the quantity of liver landmark pairs by ~10 times compared to the reported in the literature. A fully manual spot check showed that the reported procedure performed better than or as good as human at landmark pairs positional accuracy. Measured in the digital phantoms, the mean and standard deviation of TREs were 0.67 ± 0.48 mm with 99% of landmark pairs having TREs smaller than 2mm. Conclusion: A large number of liver landmark pairs with high positional accuracy were detected in contrasted enhanced CT image pairs using the reported method. The detected landmark pairs can be used for the quantitative evaluation of DIR methods.