Assessment of lung deformation in patients with idiopathic pulmonary fibrosis with elastic registration technique on pulmonary three-dimensional ultrashort echo time MRI

OBJECTIVE

To assess lung deformation in patients with idiopathic pulmonary fibrosis (IPF) using with elastic registration algorithm applied to three-dimensional ultrashort echo time (3D-UTE) MRI and analyze relationship of lung deformation with the severity of IPF.

METHODS

Seventy-six patients with IPF (mean age: 62 ± 6 years) and 62 age- and gender-matched healthy controls (mean age: 58 ± 4 years) were prospectively enrolled. End-inspiration and end-expiration images acquired with a single breath-hold 3D-UTE sequence were registered using elastic registration algorithm. Jacobian determinants were calculated from deformation fields and represented on color maps. Jac-mean (absolute value of the log means of Jacobian determinants) and the Dice similarity coefficient (Dice) were compared between different groups.

RESULTS

Compared with healthy controls, the Jac-mean of IPF patients significantly decreased (0.21 ± 0.08 vs. 0.27 ± 0. 07, p < 0.001). Furthermore, the Jac-mean and Dice correlated with the metrics of pulmonary function tests and the composite physiological index. The lung deformation in IPF patients with dyspnea Medical Research Council (MRC) ≥ 3 (Jac-mean: 0.16 ± 0.03; Dice: 0.06 ± 0.02) was significantly lower than MRC1 (Jac-mean: 0. 25 ± 0.03, p < 0.001; Dice: 0.10 ± 0.01, p < 0.001) and MRC 2 (Jac-mean: 0.22 ± 0.11, p = 0.001; Dice: 0.08 ± 0.03, p = 0.006). Meanwhile, Jac-mean and Dice correlated with health-related quality of life, 6 min-walk distance, and the extent of pulmonary fibrosis. Jac-mean correlated with pulmonary vascular-related indexes on high-resolution CT.

CONCLUSION

The decreased lung deformation in IPF patients correlated with the clinical severity of IPF patients. Elastic registration of inspiratory-to-expiratory 3D UTE MRI may be a new morphological and functional marker for non-radiation and noninvasive evaluation of IPF.

CRITICAL RELEVANCE STATEMENT

This prospective study demonstrated that lung deformation decreased in idiopathic pulmonary fibrosis (IPF) patients and correlated with the severity of IPF. Elastic registration of inspiratory-to-expiratory three-dimensional ultrashort echo time (3D UTE) MRI may be a new morphological and functional marker for non-radiation and noninvasive evaluation of IPF.

KEY POINTS

• Elastic registration of inspiratory-to-expiratory three-dimensional ultrashort echo time (3D UTE) MRI could evaluate lung deformation. • Lung deformation significantly decreased in idiopathic pulmonary fibrosis (IPF) patients, compared with the healthy controls. • Reduced lung deformation of IPF patients correlated with worsened pulmonary function and the composite physiological index (CPI).

Deep learning for improving PET/CT attenuation correction by elastic registration of anatomical data

BACKGROUND

For PET/CT, the CT transmission data are used to correct the PET emission data for attenuation. However, subject motion between the consecutive scans can cause problems for the PET reconstruction. A method to match the CT to the PET would reduce resulting artifacts in the reconstructed images.

PURPOSE

This work presents a deep learning technique for inter-modality, elastic registration of PET/CT images for improving PET attenuation correction (AC). The feasibility of the technique is demonstrated for two applications: general whole-body (WB) imaging and cardiac myocardial perfusion imaging (MPI), with a specific focus on respiratory and gross voluntary motion.

MATERIALS AND METHODS

A convolutional neural network (CNN) was developed and trained for the registration task, comprising two distinct modules: a feature extractor and a displacement vector field (DVF) regressor. It took as input a non-attenuation-corrected PET/CT image pair and returned the relative DVF between them-it was trained in a supervised fashion using simulated inter-image motion. The 3D motion fields produced by the network were used to resample the CT image volumes, elastically warping them to spatially match the corresponding PET distributions. Performance of the algorithm was evaluated in different independent sets of WB clinical subject data: for recovering deliberate misregistrations imposed in motion-free PET/CT pairs and for improving reconstruction artifacts in cases with actual subject motion. The efficacy of this technique is also demonstrated for improving PET AC in cardiac MPI applications.

RESULTS

A single registration network was found to be capable of handling a variety of PET tracers. It demonstrated state-of-the-art performance in the PET/CT registration task and was able to significantly reduce the effects of simulated motion imposed in motion-free, clinical data. Registering the CT to the PET distribution was also found to reduce various types of AC artifacts in the reconstructed PET images of subjects with actual motion. In particular, liver uniformity was improved in the subjects with significant observable respiratory motion. For MPI, the proposed approach yielded advantages for correcting artifacts in myocardial activity quantification and potentially for reducing the rate of the associated diagnostic errors.

CONCLUSION

This study demonstrated the feasibility of using deep learning for registering the anatomical image to improve AC in clinical PET/CT reconstruction. Most notably, this improved common respiratory artifacts occurring near the lung/liver border, misalignment artifacts due to gross voluntary motion, and quantification errors in cardiac PET imaging.

Novel atlas of fiber directions built from ex-vivo diffusion tensor images of porcine hearts

Cardiac MR image-based predictive models integrating statistical atlases of heart anatomy and fiber orientations can aid in better diagnosis of cardiovascular disease, a major cause of death worldwide. Such atlases have been built from diffusion tensor (DT) images and can be used in anisotropic models for personalized computational electro-mechanical simulations when the fiber directions from DTI are not available. In this paper, we propose a framework for building the first statistical fiber atlas from high-resolution ex-vivo DT images of porcine hearts. A mean geometry that represents the average cardiac morphology of the dataset was first generated via groupwise registration. Then, the associated average cardiac fiber architecture was mapped out by computing the mean of the transformed DT fields of the subjects. To evaluate the stability of the atlas, we performed leave-one-out cross-validation. The resulting tensor statistics indicate that the fiber atlas could accurately describe the fiber architecture of a healthy pig heart.

[Radiotherapy treatment planning of prostate cancer using magnetic resonance imaging]

PURPOSE

Magnetic resonance imaging (MRI) plays an increasing role in radiotherapy dose planning. Indeed, MRI offers superior soft tissue contrast compared to computerized tomography (CT) and therefore could provide a better delineation of target volumes and organs at risk than CT for radiotherapy. Furthermore, an MRI-only radiotherapy workflow would suppress registration errors inherent to the registration of MRI with CT. However, the estimation of the electronic density of tissues using MRI images is still a challenging issue. The purpose of this work was to design and evaluate a pseudo-CT generation method for prostate cancer treatments.

MATERIALS AND METHODS

A pseudo-CT was generated for ten prostate cancer patients using an elastic deformation based method. For each patient, dose delivered to the patient was calculated using both the planning CT and the pseudo-CT. Dose differences between CT and pseudo-CT were investigated.

RESULTS

Mean dose relative difference in the planning target volume is 0.9% on average and ranges from 0.1% to 1.7%. In organs at risks, this value is 1.8%, 0.8%, 0.8% and 1% on average in the rectum, the right and left femoral heads, and the bladder respectively.

CONCLUSION

The dose calculated using the pseudo-CT is very close to the dose calculated using the CT for both organs at risk and PTV. These results confirm that pseudo-CT images generated using the proposed method could be used to calculate radiotherapy treatment doses on MRI images.

Local analysis of strains and rotations for macromolecular electron microscopy maps

Macromolecular complexes perform their physiological functions by local rearrangements of their constituents and biochemically interacting with their reaction partners. These rearrangements may involve local rotations and the induction of local strains causing different mechanical efforts and stretches at the different areas of the protein. The analysis of these local deformations may reveal important insight into the way proteins perform their tasks. In this paper we introduce a method to perform this kind of local analysis using Electron Microscopy volumes in a fully objective and automatic manner. For doing so, we exploit the continuous nature of the result of an elastic image registration using B-splines as its basis functions. We show that the results obtained by the new automatic method are consistent with previous observations on these macromolecules.

3D surface-based registration of ultrasound and histology in prostate cancer imaging

Several transrectal ultrasound (TRUS)-based techniques aiming at accurate localization of prostate cancer are emerging to improve diagnostics or to assist with focal therapy. However, precise validation prior to introduction into clinical practice is required. Histopathology after radical prostatectomy provides an excellent ground truth, but needs accurate registration with imaging. In this work, a 3D, surface-based, elastic registration method was developed to fuse TRUS images with histopathologic results. To maximize the applicability in clinical practice, no auxiliary sensors or dedicated hardware were used for the registration. The mean registration errors, measured in vitro and in vivo, were 1.5±0.2 and 2.1±0.5mm, respectively.

Elastic image registration to quantify 3-D regional myocardial deformation from volumetric ultrasound: experimental validation in an animal model

Although real-time 3-D echocardiography has the potential to allow more accurate assessment of global and regional ventricular dynamics compared with more traditional 2-D ultrasound examinations, it still requires rigorous testing and validation should it break through as a standard examination in routine clinical practice. However, only a limited number of studies have validated 3-D strain algorithms in an in vivo experimental setting. The aim of the present study, therefore, was to validate a registration-based strain estimation methodology in an animal model. Volumetric images were acquired in 14 open-chest sheep instrumented with ultrasonic microcrystals. Radial strain (ɛRR), longitudinal strain (ɛLL) and circumferential strain (ɛCC) were estimated during different stages: at rest, during reduced and increased cardiac inotropy induced by esmolol and dobutamine infusion, respectively, and during acute ischemia. Agreement between image-based and microcrystal-based strain estimates was evaluated by their linear correlation, indicating that all strain components could be estimated with acceptable accuracy (r = 0.69 for ɛRR, r = 0.64 for ɛLL and r = 0.62 for ɛCC). These findings are comparable to the performance of the current state-of-the-art commercial 3-D speckle tracking methods. Furthermore, shape of the strain curves, timing of peak values and location of dysfunctional regions were identified well. Whether 3-D elastic registration performs better than 3-D block matching-based methodologies still remains to be proven.

Registration of histological whole slide images guided by vessel structures

Introduction:

The registration of histological whole slide images is an important prerequisite for modern histological image analysis. A partial reconstruction of the original volume allows e.g. colocalization analysis of tissue parameters or high-detail reconstructions of anatomical structures in 3D.

Methods:

In this paper, we present an automatic staining-invariant registration method, and as part of that, introduce a novel vessel-based rigid registration algorithm using a custom similarity measure. The method is based on an iterative best-fit matching of prominent vessel structures.

Results:

We evaluated our method on a sophisticated synthetic dataset as well as on real histological whole slide images. Based on labeled vessel structures we compared the relative differences for corresponding structures. The average positional error was close to 0, the median for the size change factor was 1, and the median overlap was 0.77.

Conclusion:

The results show that our approach is very robust and creates high quality reconstructions. The key element for the resulting quality is our novel rigid registration algorithm.