More Like this

1. CEREBROSPINAL FLUID FLOW SIMULATIONS IN BRAIN VENTRICLES WITH ELASTIC WALL RESPONSES

   Liou, Willlam W; Yang, Yang; Yamada, Shinya (June 2019, 6th International Conference on Computational and Mathematical Biomedical Engineering)

   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
2. CEREBROSPINAL FLUID FLOW SIMULATIONS IN BRAIN VENTRICLES WITH ELASTIC WALL RESPONSES

   Liou, William W; Yang, Yang; Yamada, Shinya (June 2019, 6th International Conference on Computational and Mathematical Biomedical Engineering)

   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
3. Robust soybean seed yield estimation using high-throughput ground robot videos

   https://doi.org/10.3389/fpls.2025.1554193  

   Feng, Jiale; Blair, Samuel W; Ayanlade, Timilehin T; Balu, Aditya; Ganapathysubramanian, Baskar; Singh, Arti; Sarkar, Soumik; Singh, Asheesh K (March 2025, Frontiers in Plant Science)

   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
4. Temporal Context Matters: Enhancing Single Image Prediction With Disease Progression Representations

   https://doi.org/10.1109/CVPR52688.2022.01826  

   Konwer, Aishik; Xu, Xuan; Bae, Joseph; Chen, Chao; Prasanna, Prateek (July 2022, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR))

   Clinical 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
5. Geometric control analysis of the unsteady aerodynamics of a pitching–plunging airfoil in dynamic stall

   https://doi.org/10.1063/5.0190449  

   Pla_Olea, L; Taha, H E (March 2024, Physics of Fluids)

   Geometric control theory is the application of differential geometry to the study of nonlinear dynamical systems. This control theory permits an analytical study of nonlinear interactions between control inputs, such as symmetry breaking or force and motion generation in unactuated directions. This paper studies the unsteady aerodynamics of a harmonically pitching–plunging airfoil in a geometric control framework. The problem is formulated using the Beddoes–Leishman model, a semi-empirical state space model that characterizes the unsteady lift and drag forces of a two-dimensional airfoil. In combination with the averaging theorem, the application of a geometric control formulation to the problem enables an analytical study of the nonlinear dynamics behind the unsteady aerodynamic forces. The results show lift enhancement when oscillating near stall and thrust generation in the post-stall flight regime, with the magnitude of these force generation mechanisms depending on the parameters of motion. These findings demonstrate the potential of geometric control theory as a heuristic tool for the identification and discovery of unconventional phenomena in unsteady flows. 

   more » « less