Recovery of 3D rib motion from dynamic chest radiography and CT data using local contrast normalization and articular motion model

Decomposition of musculoskeletal structures from radiographs using an improved CycleGAN framework

This paper presents methods of decomposition of musculoskeletal structures from radiographs into multiple individual muscle and bone structures. While existing solutions require dual-energy scan for the training dataset and are mainly applied to structures with high-intensity contrast, such as bones, we focused on multiple superimposed muscles with subtle contrast in addition to bones. The decomposition problem is formulated as an image translation problem between (1) a real X-ray image and (2) multiple digitally reconstructed radiographs, each of which contains a single muscle or bone structure, and solved using unpaired training based on the CycleGAN framework. The training dataset was created via automatic computed tomography (CT) segmentation of muscle/bone regions and virtually projecting them with geometric parameters similar to the real X-ray images. Two additional features were incorporated into the CycleGAN framework to achieve a high-resolution and accurate decomposition: hierarchical learning and reconstruction loss with the gradient correlation similarity metric. Furthermore, we introduced a new diagnostic metric for muscle asymmetry directly measured from a plain X-ray image to validate the proposed method. Our simulation and real-image experiments using real X-ray and CT images of 475 patients with hip diseases suggested that each additional feature significantly enhanced the decomposition accuracy. The experiments also evaluated the accuracy of muscle volume ratio measurement, which suggested a potential application to muscle asymmetry assessment from an X-ray image for diagnostic and therapeutic assistance. The improved CycleGAN framework can be applied for investigating the decomposition of musculoskeletal structures from single radiographs.

Vector-field dynamic x-ray (VF-DXR) using optical flow method in patients with chronic obstructive pulmonary disease

BACKGROUND

We assessed the difference in lung motion during inspiration/expiration between chronic obstructive pulmonary disease (COPD) patients and healthy volunteers using vector-field dynamic x-ray (VF-DXR) with optical flow method (OFM).

METHODS

We enrolled 36 COPD patients and 47 healthy volunteers, classified according to pulmonary function into: normal, COPD mild, and COPD severe. Contrast gradient was obtained from sequential dynamic x-ray (DXR) and converted to motion vector using OFM. VF-DXR images were created by projection of the vertical component of lung motion vectors onto DXR images. The maximum magnitude of lung motion vectors in tidal inspiration/expiration, forced inspiration/expiration were selected and defined as lung motion velocity (LMV). Correlations between LMV with demographics and pulmonary function and differences in LMV between COPD patients and healthy volunteers were investigated.

RESULTS

Negative correlations were confirmed between LMV and % forced expiratory volume in one second (%FEV1) in the tidal inspiration in the right lung (Spearman's rank correlation coefficient, rs = -0.47, p < 0.001) and the left lung (rs = -0.32, p = 0.033). A positive correlation between LMV and %FEV1 in the tidal expiration was observed only in the right lung (rs = 0.25, p = 0.024). LMVs among normal, COPD mild and COPD severe groups were different in the tidal respiration. COPD mild group showed a significantly larger magnitude of LMV compared with the normal group.

CONCLUSIONS

In the tidal inspiration, the lung parenchyma moved faster in COPD patients compared with healthy volunteers. VF-DXR was feasible for the assessment of lung parenchyma using LMV.

[Paradigm Shift in Respiratory Diagnosis: Current Status and Future Prospects of Dynamic Chest Radiography]

Dynamic chest radiography (DCR) is a flat-panel detector (FPD) -based functional X-ray imaging, which is performed as an additional examination in chest radiography. The large field of view of FPDs permits real-time observation of motion/kinetic findings on the entire lungs, right and left diaphragm, ribs, and chest wall; heart wall motions; respiratory changes in lung density; and diameter of the intrathoracic trachea. Since the dynamic FPDs had been developed in the early 2000s, we focused on the potential of dynamic FPDs for functional X-ray imaging and have launched a research project for the development of an imaging protocol and digital image-processing techniques for the DCR. The quantitative analysis of motion/kinetic findings is helpful for a better understanding of pulmonary function, because the interpretation of dynamic chest radiographs is challenging and time-consuming for radiologists, pulmonologists, and surgeons. Recent clinical studies have demonstrated the usefulness of DCR combined with the digital image processing techniques for the evaluation of pulmonary function and circulation. Especially, there is a major concern in color-mapping images based on dynamic changes in radiographic lung density, where pulmonary impairments can be detected as color defects, even without the use of contrast media or radioactive medicine. Dynamic chest radiography is now commercially available for the use in general X-ray room and therefore can be deployed as a simple and rapid means of functional imaging in both routine and emergency medicine. This review article describes the current status and future prospects of DCR, which might bring a paradigm shift in respiratory diagnosis.

The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective

Image-based navigation is widely considered the next frontier of minimally invasive surgery. It is believed that image-based navigation will increase the access to reproducible, safe, and high-precision surgery as it may then be performed at acceptable costs and effort. This is because image-based techniques avoid the need of specialized equipment and seamlessly integrate with contemporary workflows. Furthermore, it is expected that image-based navigation techniques will play a major role in enabling mixed reality environments, as well as autonomous and robot-assisted workflows. A critical component of image guidance is 2D/3D registration, a technique to estimate the spatial relationships between 3D structures, e.g., preoperative volumetric imagery or models of surgical instruments, and 2D images thereof, such as intraoperative X-ray fluoroscopy or endoscopy. While image-based 2D/3D registration is a mature technique, its transition from the bench to the bedside has been restrained by well-known challenges, including brittleness with respect to optimization objective, hyperparameter selection, and initialization, difficulties in dealing with inconsistencies or multiple objects, and limited single-view performance. One reason these challenges persist today is that analytical solutions are likely inadequate considering the complexity, variability, and high-dimensionality of generic 2D/3D registration problems. The recent advent of machine learning-based approaches to imaging problems that, rather than specifying the desired functional mapping, approximate it using highly expressive parametric models holds promise for solving some of the notorious challenges in 2D/3D registration. In this manuscript, we review the impact of machine learning on 2D/3D registration to systematically summarize the recent advances made by introduction of this novel technology. Grounded in these insights, we then offer our perspective on the most pressing needs, significant open problems, and possible next steps.

Vector-Field dynamic X-ray (VF-DXR) using Optical Flow Method

OBJECTIVES

To explore the feasibility of Vector-Field DXR (VF-DXR) using optical flow method (OFM).

METHODS

Five healthy volunteers and five COPD patients were studied. DXR was performed in the standing position using a prototype X-ray system (Konica Minolta Inc., Tokyo, Japan). During the examination, participants took several tidal breaths and one forced breath. DXR image file was converted to the videos with different frames per second (fps): 15 fps, 7.5 fps, five fps, three fps, and 1.5 fps. Pixel-value gradient was calculated by the serial change of pixel value, which was subsequently converted mathematically to motion vector using OFM. Color-coding map and vector projection into horizontal and vertical components were also tested.

RESULTS

Dynamic motion of lung and thorax was clearly visualized using VF-DXR with an optimal frame rate of 5 fps. Color-coding map and vector projection into horizontal and vertical components were also presented. VF-DXR technique was also applied in COPD patients.

CONCLUSION

The feasibility of VF-DXR was demonstrated with small number of healthy subjects and COPD patients.

ADVANCES IN KNOWLEDGE

A new Vector-Field Dynamic X-ray (VF-DXR) technique is feasible for dynamic visualization of lung, diaphragms, thoracic cage, and cardiac contour.

Estimating rotation angle from asymmetric projection of chest

BACKGROUND

Manual or machine-based analysis of chest radiographs needs the images acquired with technical adequacy. Currently, the equidistance between the medial end of clavicles and the center of spinous processes serves as the only criterion to assess whether a frontal PA chest radiograph is taken with any rotation. However, this measurement is normally difficult to implement because there exists overlapping of anatomies within the region. Moreover, there is no way available to predict exact rotating angles even the distances were correctly measured from PA chest radiographs.

OBJECTIVE

To quantitatively assess positioning adequacy of PA chest examination, this study proposes and investigates a new method to estimate rotation angles from asymmetric projection of thoracic cage on radiographs.

METHOD

By looking into the process of radiographic projection, generalized expressions have been established to correlate rotating angles of thorax with projection difference of left and right sides of thoracic cage. A trunk phantom with different positioning angles is employed to acquire radiographs as standard reference to verify the theoretical expressions.

RESULTS

The angles estimated from asymmetric projections of thoracic cage yield good agreement with those actual rotated angles, and an approximate linear relationship exists between rotation angle and asymmetric projection of thoracic cage. Under the experimental projection settings, every degree of rotation corresponds to the width difference of two sides of thoracic cage around 13-14 pixels.

CONCLUSION

The proposed new method may be used to quantify rotating angles of chest and assess image quality for thoracic radiographic examination.

Dynamic Chest X-Ray Using a Flat-Panel Detector System: Technique and Applications

Dynamic X-ray (DXR) is a functional imaging technique that uses sequential images obtained by a flat-panel detector (FPD). This article aims to describe the mechanism of DXR and the analysis methods used as well as review the clinical evidence for its use. DXR analyzes dynamic changes on the basis of X-ray translucency and can be used for analysis of diaphragmatic kinetics, ventilation, and lung perfusion. It offers many advantages such as a high temporal resolution and flexibility in body positioning. Many clinical studies have reported the feasibility of DXR and its characteristic findings in pulmonary diseases. DXR may serve as an alternative to pulmonary function tests in patients requiring contact inhibition, including patients with suspected or confirmed coronavirus disease 2019 or other infectious diseases. Thus, DXR has a great potential to play an important role in the clinical setting. Further investigations are needed to utilize DXR more effectively and to establish it as a valuable diagnostic tool.