An official website of the United States government
The cerebrospinal fluid surrounds the brain and the spinal cord, and is believed to be a potential risk factor to many CNS diseases. The biomechanics of the CSF flow in the brain ventricles is poorly understood due partly to the difficulty in obtaining the flow data in vivo. This paper describes the outcomes of a computational study to examine the elastic response of the walls of the ventricles and its effects on the flow. Comparisons of the simulated results are guided by clinical data obtained with the Time-SLIP MRI, which captures ventricular CSF flows in real time in vivo.
more »
« less
MRI Image-Based Mapping of Human Head Motion and Brain Ventricular Cerebrospinal Fluid Flows Using Computer Vision
Cerebrospinal fluid (CSF) plays a critical role in brain metabolism and protection from external forces. Traditional MRI can provide some insights into CSF dynamics; however, more advanced and cost-effective methods are needed for precise and comprehensive visualization of flow patterns, velocities, and directions in clinical settings. In this paper, we demonstrate a new application of a few open-source computer vision software packages to capture CSF motion from time spatial inversion pulse (Time-SLIP) MRI clinical images (in DICOM format). To test the hypothesis that the CSF flow depends on head motions, a reliable and robust pipeline of processing Time-SLIP MRI images is developed to extract both anatomy and CSF motion dynamics. The paper presents a methodology for extracting unsteady flow information from Time-SLIP MRI images and the results of its application. The results show that the computer vision method can be applied to extract unsteady CSF flow information. We also discuss observations and identify future areas for improvement by integrating CFD simulations for validation as a vital component for studying CSF dynamics.
more »
« less
- Award ID(s):
- 2232598
- PAR ID:
- 10659075
- Publisher / Repository:
- Springer Nature Switzerland
- Date Published:
- Page Range / eLocation ID:
- 212 to 225
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
The cerebrospinal fluid surrounds the brain and the spinal cord, and is believed to be a potential risk factor to many CNS diseases. The biomechanics of the CSF flow in the brain ventricles is poorly understood due partly to the difficulty in obtaining the flow data in vivo. This paper describes the outcomes of a computational study to examine the elastic response of the walls of the ventricles and its effects on the flow. Comparisons of the simulated results are guided by clinical data obtained with the Time-SLIP MRI, which captures ventricular CSF flows in real time in vivo.more » « less
-
Abstract Motivation: Hemodynamic analysis is crucial for diagnosing and predicting cardiovascular diseases. However, methods relying on fluid flow simulations or blood flow imaging are complex, time-consuming, and require specialized expertise, limiting their clinical use. Goal: This research aims to automate the enhancement of blood flow images, providing clinicians with a fast, accurate tool for hemodynamic analysis without requiring advanced expertise. Objectives: A software tool based on physics-constrained neural networks was developed to enable clinicians to easily select and process regions of interest (ROIs) in time-resolved three-dimensional phase contrast magnetic resonance imaging (4D-Flow MRI) blood flow images for quick, accurate analysis. Methods: The Input Parameterized Physics-Informed Neural Network (IP-PINN) was introduced to improve the spatio-temporal resolution of 4D-Flow MRI. IP-PINN mitigates noise, velocity aliasing, and phase errors. A convolutional neural network processes ROI data into latent vectors, which are then used to predict velocity, pressure, and spin density via a multi-layer perceptron. The method is trained with synthetic blood flow data using an innovative loss function that addresses noise and artifacts. Results: IP-PINN successfully enhanced image resolution, reducing noise and artifacts when tested on synthetic 4D-Flow MRI data derived from blood flow simulations of intracranial aneurysms. For data with 20 decibels (dB) signal-to-noise ratio, results closely matched the ground truth with less than 5.5% relative error. Processing took under two minutes. The method also has the potential to reduce data acquisition time by 25%. Conclusions: IP-PINN could significantly enhance the clinical use of 4D-Flow MRI for personalized hemodynamic analysis in cardiovascular diseases.more » « less
-
Temporal Context Matters: Enhancing Single Image Prediction With Disease Progression RepresentationsClinical outcome or severity prediction from medical images has largely focused on learning representations from single-timepoint or snapshot scans. It has been shown that disease progression can be better characterized by temporal imaging. We therefore hypothesized that outcome predictions can be improved by utilizing the disease progression information from sequential images. We present a deep learning approach that leverages temporal progression information to improve clinical outcome predictions from single-timepoint images. In our method, a self-attention based Temporal Convolutional Network (TCN) is used to learn a representation that is most reflective of the disease trajectory. Meanwhile, a Vision Transformer is pretrained in a self-supervised fashion to extract features from single-timepoint images. The key contribution is to design a recalibration module that employs maximum mean discrepancy loss (MMD) to align distributions of the above two contextual representations. We train our system to predict clinical outcomes and severity grades from single-timepoint images. Experiments on chest and osteoarthritis radiography datasets demonstrate that our approach outperforms other state-of-the-art techniques.more » « less
-
We present a novel method for soybean [Glycine max(L.) Merr.] yield estimation leveraging high-throughput seed counting via computer vision and deep learning techniques. Traditional methods for collecting yield data are labor-intensive, costly, and prone to equipment failures at critical data collection times and require transportation of equipment across field sites. Computer vision, the field of teaching computers to interpret visual data, allows us to extract detailed yield information directly from images. By treating it as a computer vision task, we report a more efficient alternative, employing a ground robot equipped with fisheye cameras to capture comprehensive videos of soybean plots from which images are extracted in a variety of development programs. These images are processed through the P2PNet-Yield model, a deep learning framework, where we combined a feature extraction module (the backbone of the P2PNet-Soy) and a yield regression module to estimate seed yields of soybean plots. Our results are built on 2 years of yield testing plot data—8,500 plots in 2021 and 650 plots in 2023. With these datasets, our approach incorporates several innovations to further improve the accuracy and generalizability of the seed counting and yield estimation architecture, such as the fisheye image correction and data augmentation with random sensor effects. The P2PNet-Yield model achieved a genotype ranking accuracy score of up to 83%. It demonstrates up to a 32% reduction in time to collect yield data as well as costs associated with traditional yield estimation, offering a scalable solution for breeding programs and agricultural productivity enhancement.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript
- Book Chapter:
- https://doi.org/10.1007/978-3-031-94962-3_19
