3D Hermite Transform Optical Flow Estimation in Left Ventricle CT Sequences

Abstract

Heart diseases are the most important causes of death in the world and over the years, the study of cardiac movement has been carried out mainly in two dimensions, however, it is important to consider that the deformations due to the movement of the heart occur in a three-dimensional space. The 3 D + t analysis allows to describe most of the motions of the heart, for example, the twisting motion that takes place on every beat cycle that allows us identifying abnormalities of the heart walls. Therefore, it is necessary to develop algorithms that help specialists understand the cardiac movement. In this work, we developed a new approach to determine the cardiac movement in three dimensions using a differential optical flow approach in which we use the steered Hermite transform (SHT) which allows us to decompose cardiac volumes taking advantage of it as a model of the human vision system (HVS). Our proposal was tested in complete cardiac computed tomography (CT) volumes ( 3 D + t ), as well as its respective left ventricular segmentation. The robustness to noise was tested with good results. The evaluation of the results was carried out through errors in forwarding reconstruction, from the volume at time t to time t + 1 using the optical flow obtained (interpolation errors). The parameters were tuned extensively. In the case of the 2D algorithm, the interpolation errors and normalized interpolation errors are very close and below the values reported in ground truth flows. In the case of the 3D algorithm, the results were compared with another similar method in 3D and the interpolation errors remained below 0.1. These results of interpolation errors for complete cardiac volumes and the left ventricle are shown graphically for clarity. Finally, a series of graphs are observed where the characteristic of contraction and dilation of the left ventricle is evident through the representation of the 3D optical flow.

MicroRNA-193a-5p Regulates the Synthesis of Polyunsaturated Fatty Acids by Targeting Fatty Acid Desaturase 1 (FADS1) in Bovine Mammary Epithelial Cells

“…In this pathway, FADS1 plays a critical role [ 43 , 44 ]. Approximately 17.9 million people die from CVD every year [ 45 , 46 ]. Increasing evidence shows that nutrition plays a pivotal role in the development of chronic diseases, especially CVD [ 47 ].…”

“…Increasing evidence shows that nutrition plays a pivotal role in the development of chronic diseases, especially CVD [ 47 ]. Diet and lifestyle are the key risk factors for CVD prevention and have been the focus of intense research [ 46 ]. Dairy products, as an integral part of human nutrition, contain n-3 fatty acids, usually at concentrations below biological requirements.…”

What is new in computer vision and artificial intelligence in medical image analysis applications

“…years, the study of cardiac movement has been carried out mainly in two dimensional images, however, it is important to consider that the deformations due to the movement of the heart occur in a three-dimensional space. New 3D results can demonstrate the heart's movement complexity as shown in Figure 4 (26). Future trends in the cardiac area aim at building fully automatic tools able to understand the images and relate them to specific pathologies.…”

Projection-based dynamic tomography

“…Each (filtered) back-projection is warped with the measured spatial displacement field (estimated at the corresponding acquisition time) so that the sum of all those warped back-projections reconstructs the volume in a static configuration. Instead of developing techniques based on measurement between multiple volumes (e.g., in [37,38,39,40,41]), the projection-based strategy is very well fitted to the displacement measurement as it provides a spatial displacement field for each frame [42]. Developed in the medical imaging field and called 2D/3D image registration [34,43,44,45,46,47,48], a similar approach has also been developed in material science and called Projection-based Digital Volume Correlation, P-DVC [49,50,51,52].…”

“…Instead of developing techniques based on measurement between multiple volumes (e.g. in Ruhlandt et al (2017), De Schryver et al (2018), Zang et al (2018Zang et al ( , 2019, Mira et al (2020)), the projection-based strategy is very well fitted to the displacement measurement as it provides a spatial displacement field for each frame (Guillard et al 2017). Developed in the medical imaging field and called 2D/3D image registration (Zeng et al 2005, 2007, Hinkle et al 2012, Markelj et al 2012, Wang and Gu 2013, Delmon et al 2014, Suzuki et al 2017, a similar approach has also been developed in material science and called projection-based digital volume correlation, P-DVC (Leclerc et al 2015b, Taillandier-Thomas et al 2016, Jailin et al 2017, 2018b.…”