Dataset Information

An optimized optical-flow-based method for quantitative tracking of ultrasound-guided right diaphragm deformation.

ABSTRACT:

Objectives

To develop a quantitative analysis method for right diaphragm deformation. This method is based on optical flow and applied to diaphragm ultrasound imaging.

Methods

This study enrolls six healthy subjects and eight patients under mechanical ventilation. Dynamic images with 3-5 breathing cycles were acquired from three directions of right diaphragm by a portable ultrasound system. Filtering and density clustering algorithms are used for denoising Digital Imaging and Communications in Medicine (DICOM) data. An optical flow based method is applied to track movements of the right diaphragm. An improved drift correction algorithm is used to optimize the results. The method can automatically analyze the respiratory cycle, inter-frame/cumulative vertical and horizontal displacements, and strain of the input right diaphragm ultrasound image.

Results

The optical-flow-based diaphragm ultrasound image motion tracking algorithm can accurately track the right diaphragm during respiratory motion. There are significant differences in horizontal and vertical displacements in each section (p-values < 0.05 for all). Significant differences are found between healthy subjects and mechanical ventilation patients for both horizontal and vertical displacements in Section III (p-values < 0.05 for both). There is no significant difference in global strain in each section between healthy subjects and mechanical ventilation patients (p-values > 0.05 for all).

Conclusions

The developed method can quantitatively evaluate the inter-frame/cumulative displacement of the diaphragm in both horizontal and vertical directions, as well as the global strain in three different imaging planes. The above indicators can be used to evaluate diaphragmatic dynamics.

SUBMITTER: Zhang Q

PROVIDER: S-EPMC10436632 | biostudies-literature | 2023 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

An optimized optical-flow-based method for quantitative tracking of ultrasound-guided right diaphragm deformation.

Zhang Qi Q Yang Dawei D Zhu Yu Y Liu Yatong Y Ye Xiong X

BMC medical imaging 20230817 1

<h4>Objectives</h4>To develop a quantitative analysis method for right diaphragm deformation. This method is based on optical flow and applied to diaphragm ultrasound imaging.<h4>Methods</h4>This study enrolls six healthy subjects and eight patients under mechanical ventilation. Dynamic images with 3-5 breathing cycles were acquired from three directions of right diaphragm by a portable ultrasound system. Filtering and density clustering algorithms are used for denoising Digital Imaging and Comm ...[more]

PMID: 37592200

Similar Datasets

Project description:BackgroundDespite the known interplay between blood flow and function, to our knowledge, there is currently no minimally invasive method to monitor diaphragm hemodynamics. We used contrast-enhanced ultrasound to quantify relative diaphragm blood flow (Q˙DIA) in humans and assessed the technique's efficacy and reliability during graded inspiratory pressure threshold loading. We hypothesized that: (1) Q˙DIA would linearly increase with pressure generation, and (2) that there would be good test-retest reliability and interanalyzer reproducibility.Research questionCan we validate what is, to our knowledge, the first minimally invasive method to measure relative diaphragm blood flow in humans?Study design and methodsQuantitative contrast-enhanced ultrasound of the costal diaphragm was performed in healthy participants (10 male participants, 6 female participants; mean age 28 ± 5 years; BMI 22.8 ± 2.0 kg/m) during unloaded breathing and three stages of loaded breathing on two separate days. Gastric and esophageal balloon catheters measured transdiaphragmatic pressure. Ultrasonography was performed during a constant-rate IV infusion of lipid-stabilized microbubbles following each stage. Ultrasound images were acquired after a destruction-replenishment sequence and diaphragm specific time-intensity data were used to determine Q˙DIA by two individuals.ResultsTransdiaphragmatic pressure for unloaded and each loading stage were 15.2 ± 0.8, 26.1 ± 0.8, 34.6 ± 0.8, and 40.0 ± 0.8 percentage of the maximum, respectively. Q˙DIA increased with each stage of loading (3.1 ± 3.1, 6.9 ± 3.6, 11.0 ± 4.9, and 13.5 ± 5.4 acoustic units/s; P < .0001). The linear relationship between diaphragmatic flow and pressure was reproducible from day to day. Q˙DIA had good to excellent test-retest reliability (0.86 [0.77, 0.92]; P < .0001) and excellent interanalyzer reproducibility (0.93 [0.90, 0.95]; P < .0001) with minimal bias.InterpretationRelative Q˙DIA measurements had valid physiological underpinnings, were reliable day-to-day, and were reproducible analyzer-to-analyzer. This study indicated that contrast-enhanced ultrasound is a viable, minimally invasive method for assessing costal Q˙DIA in humans and may provide a tool to monitor diaphragm hemodynamics in clinical settings.

Project description:Background The aim of this study was to establish a correlation model between external surface motion and internal diaphragm apex movement using machine learning and to realize online automatic prediction of the diaphragm motion trajectory based on optical surface monitoring. Methods The optical body surface parameters and kilovoltage (kV) X-ray fluoroscopic images of 7 liver tumor patients were captured synchronously for 50 seconds. The location of the diaphragm apex was manually delineated by a radiation oncologist and automatically detected with a convolutional network model in fluoroscopic images. The correlation model between the body surface parameters and the diaphragm apex of each patient was developed through linear regression (LR) based on synchronous datasets before radiotherapy. Model 1 (M1) was trained with data from the first 30 seconds of the datasets and tested with data from the following 20 seconds of the datasets in the first fraction to evaluate the intra-fractional prediction accuracy. Model 2 (M2) was trained with data from the first 30 seconds of the datasets in the next fraction. The motion trajectory of the diaphragm apex during the following 20 seconds in the next fraction was predicted with M1 and M2, respectively, to evaluate the inter-fractional prediction accuracy. The prediction errors of the 2 models were compared to analyze whether the correlation model needed to be re-established. Results The average mean absolute error (MAE) and root mean square error (RMSE) using M1 trained with automatic detection location for the first fraction were 3.12±0.80 and 3.82±0.98 mm in the superior-inferior (SI) direction and 1.38±0.24 and 1.74±0.32 mm in the anterior-posterior (AP) direction, respectively. The average MAE and RMSE of M1 versus M2 in the AP direction were 2.63±0.71 versus 1.28±0.48 mm and 3.26±0.90 versus 1.61±0.60 mm, respectively. The average MAE and RMSE of M1 versus M2 in the SI direction were 5.84±1.22 versus 3.37±0.43 mm and 7.22±1.45 versus 4.07±0.54 mm, respectively. The prediction accuracy of M2 was significantly higher than that of M1. Conclusions This study shows that it is feasible to use optical body surface information to automatically predict the diaphragm motion trajectory. At the same time, it is necessary to establish a new correlation model for the current fraction before each treatment.

Dataset Information

An optimized optical-flow-based method for quantitative tracking of ultrasound-guided right diaphragm deformation.

Objectives

Methods

Results

Conclusions

Publications

An optimized optical-flow-based method for quantitative tracking of ultrasound-guided right diaphragm deformation.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets