Skip to main content

Medical-image Analysis and Statistical Interpretation Lab

Development and Characterization of a Chest CT Atlas

Posted by on Tuesday, October 13, 2020 in Computed Tomography, Lung Screening CT, Registration.

Kaiwen Xu, Riqiang Gao, Mirza S. Khan, Shunxing Bao, Yucheng Tang, Steve A. Deppen, Yuankai Huo, Kim L. Sandler, Pierre P. Massion, Mattias P. Heinrich, Bennett A. Landman. Development and characterization of a chest CT atlas. SPIE Medical Imaging, 2021.

Full text: https://arxiv.org/abs/2012.03124

Abstract

A major goal of lung cancer screening is to identify individuals with particular phenotypes that are associated with high risk of cancer. Identifying relevant phenotypes is complicated by the variation in body position and body composition. In the brain, standardized coordinate systems (e.g., atlases) have enabled separate consideration of local features from gross/global structure. To date, no analogous standard atlas has been presented to enable spatial mapping and harmonization in chest computational tomography (CT). In this paper, we propose a thoracic atlas built upon a large low dose CT (LDCT) database of lung cancer screening program. The study cohort includes 466 male and 387 female subjects with no screening detected malignancy (age 46-79 years, mean 64.9 years). To provide spatial mapping, we optimize a multi-stage inter-subject non-rigid registration pipeline for the entire thoracic space. Briefly, with 50 scans of 50 randomly selected female subjects as fine tuning dataset, we search for the optimal configuration of the non-rigid registration module in a range of adjustable parameters including: registration searching radius, degree of keypoint dispersion, regularization coefficient and similarity patch size, to minimize the registration failure rate approximated by the number of samples with low Dice similarity score (DSC) for lung and body segmentation. We evaluate the optimized pipeline on a separate cohort (100 scans of 50 female and 50 male subjects) relative to two baselines with alternative non-rigid registration module: the same software with default parameters and an alternative software. We achieve a significant improvement in terms of registration success rate based on manual QA. For the entire study cohort, the optimized pipeline achieves a registration success rate of 91.7%. The application validity of the developed atlas is evaluated in terms of discriminative capability for different anatomic phenotypes, including body mass index (BMI), chronic obstructive pulmonary disease (COPD), and coronary artery calcification (CAC).

Figure. Four consecutive modules of the atlas creation pipeline. (A) Preprocessing module: (A.1) original moving scan; (A.2) the overlap between the ambient removed scan and lung & body segmentation masks. (B) Affine registration module based on NiftyReg toolbox: (B.1) moving scan with intensity window (0, 1000); (B.2) axial view of reference scan; (B.3) reference scan with intensity window (0, 1000); (B.4) affine registered intensity windowed moving scan; (B.5) interpolation of the preprocessed moving scan with the affine registration transformation matrix. (C) Non-rigid registration module based on corrField (registration) and NiftyReg (interpolation): (C.1) affine registered moving scan overlapped with lung and body segmentation masks; (C.2) overlapped with non-NaN region mask; (C.3) reference scan with non-NaN region mask; (C.4) non-rigid deformed moving scan overlapped with deformed non-NaN region mask; (C.5) non-rigid deformed moving scan overlapped with deformed lung / body masks. (D) Atlas creation module: (D.1) average atlas of HU; (D.2) average atlas of Jacobian determinant map.
Figure. Four consecutive modules of the atlas creation pipeline. (A) Preprocessing module: (A.1) original moving scan; (A.2) the overlap between the ambient removed scan and lung & body segmentation masks. (B) Affine registration module based on NiftyReg toolbox: (B.1) moving scan with intensity window (0, 1000); (B.2) axial view of reference scan; (B.3) reference scan with intensity window (0, 1000); (B.4) affine registered intensity windowed moving scan; (B.5) interpolation of the preprocessed moving scan with the affine registration transformation matrix. (C) Non-rigid registration module based on corrField (registration) and NiftyReg (interpolation): (C.1) affine registered moving scan overlapped with lung and body segmentation masks; (C.2) overlapped with non-NaN region mask; (C.3) reference scan with non-NaN region mask; (C.4) non-rigid deformed moving scan overlapped with deformed non-NaN region mask; (C.5) non-rigid deformed moving scan overlapped with deformed lung / body masks. (D) Atlas creation module: (D.1) average atlas of HU; (D.2) average atlas of Jacobian determinant map.

Tags: