The elasticity of red blood cells (RBCs) plays a vital role in their efficient movement through blood vessels, facilitating the transportation of oxygen within the bloodstream. However, various diseases significantly impact RBC elasticity, making it an important parameter for diagnosing and monitoring health conditions. In this study, we propose a novel approach to determine RBC elasticity by analyzing video recordings and using a convolutional neural network (CNN) for classification. Due to the scarcity of available blood flow recordings, computer simulations based on a numerical model are employed to generate a substantial amount of training data. The simulation model incorporates the representation of RBCs as elastic objects within a fluid flow, allowing for a detailed understanding of their behavior. We compare the performance of different CNN architectures, including ResNet and EfficientNet, for video classification of RBC elasticity. Our results demonstrate the potential of using CNNs and simulation-based data for the accurate classification of RBC elasticity.

The elasticity of red blood cells (RBCs) is crucial for their ability to fulfill their role in the blood. Decreased RBC deformability is associated with various pathological conditions. This study explores the application of machine learning to predict the elasticity of RBCs using both image data and detailed physical measurements derived from simulations. We simulated RBC behavior in a microfluidic channel. The simulation results provided the basis for generating data on which we applied machine learning techniques. We analyzed the surface-area-to-volume ratio of RBCs as an indicator of elasticity, employing statistical methods to differentiate between healthy and diseased RBCs. The Kolmogorov–Smirnov test confirmed significant differences between healthy and diseased RBCs, though distinctions among different types of diseased RBCs were less clear. We used decision tree models, including random forests and gradient boosting, to classify RBC elasticity based on predictors derived from simulation data. The comparison of the results with our previous work on deep neural networks shows improved classification accuracy in some scenarios. The study highlights the potential of machine learning to automate and enhance the analysis of RBC elasticity, with implications for clinical diagnostics.

Institute of Mathematics of the Czech Academy of Sciences

The elasticity of red blood cells (RBCs) is crucial for their ability to fulfill their role in the blood. Decreased RBC deformability is associated with various pathological conditions. This study explores the application of machine learning to predict the elasticity of RBCs using both image data and detailed physical measurements derived from simulations. We simulated RBC behavior in a microfluidic channel. The simulation results provided the basis for generating data on which we applied machine learning techniques. We analyzed the surface-area-to-volume ratio of RBCs as an indicator of elasticity, employing statistical methods to differentiate between healthy and diseased RBCs. The Kolmogorov–Smirnov test confirmed significant differences between healthy and diseased RBCs, though distinctions among different types of diseased RBCs were less clear. We used decision tree models, including random forests and gradient boosting, to classify RBC elasticity based on predictors derived from simulation data. The comparison of the results with our previous work on deep neural networks shows improved classification accuracy in some scenarios. The study highlights the potential of machine learning to automate and enhance the analysis of RBC elasticity, with implications for clinical diagnostics.

Precise registration of high-resolution SAR and optical imagery is necessary for realizing the full potential and benefits of multimodal image analysis. However, two significant challenges presently exist. First, there is a lack of annotated datasets and benchmarks available for high-resolution SAR optical image registration. Second, an assessment of efficient and reliable image registration methods that can precisely align these modalities is lacking. Here, we present a holistic description of the SpaceNet 9 Challenge and its results. We present a description of the dataset and baseline algorithm along with the results of the challenge including a description of the winning algorithms. We release the SpaceNet 9 dataset along with open-sourcing the winning algorithms and baseline. The objective of SpaceNet 9 was to compute a dense displacement map that indicates the shift needed to align pixels in an optical image to the pixels in a SAR image. The challenge launched in April 2025 and was active for approximately two months. The top five solutions reduced image alignment error from approximately 34 meters to under 13 meters for public and private test data, with the best results obtaining a registration error of only 8.5 and 6.7 meters on the public testing and private testing dataset, respectively. Usage of pretrained image matching models, robust outlier rejection with RANSAC, and estimating local displacement were common among the top solutions. The results of this challenge provide insight into high-resolution SAR-optical image registration and offer opportunities for future benchmarking in this domain. The baseline algorithm, winning solutions, and datasets are available at https://spacenet.ai/sn9-challenge/.