Zhaoke Huang

Deep learning segmentation and fluorescence imaging techniques allow the cellular morphology of living embryos to be constructed spatiotemporally. These development processes involve numerous molecules distributed at the subcellular scale, such as cell adhesion (E-cadherin), which accumulate at cell-cell interfaces to regulate intercellular connections. However, quantifying molecular distributions within specific subcellular regions across the entire embryo, where cell movement and molecular redistribution occur rapidly, is challenging due to the need for simultaneous cell morphology reconstruction and lineage tracing due to photobleaching and phototoxicity. We report a transformer-based pipeline, CTransformer, that establishes a 4D cellular morphology map before the 550-cell (late) stage. CTransformer constructed 4D cellular morphology atlases, reaching 80% accuracy at the 550-cell stage. Through this advanced architecture, we use only one channel to reconstruct cell morphology and achieve cell tracing. With each cell’s morphology as a reference, the distribution of specific molecules throughout the cell body and at cell interfaces can be quantitatively measured in another fluorescence channel. We apply this methodology to track E-cadherin during embryonic development of the worm Caenorhabditis elegans, from fertilization to gastrulation. Our results reveal that E-cadherin is tightly regulated across individual embryos, both within single cells and at cell-cell interfaces, displaying an anterior-posterior gradient and cell- and lineage-specific patterns. Furthermore, its spatiotemporal heterogeneity influences cell mechanics and embryonic morphogenesis, helping explain how C. elegans achieves stereotypical developmental patterns at cellular resolution. In summary, CTransformer offers a high-throughput approach for measuring molecular distributions at subcellular resolution, providing valuable knowledge for cellular and developmental biology, biophysics, and bioinformatics.

Accurate and scalable indoor localization for uncrewed aerial vehicles (UAVs) is essential for Internet of Things (IoT) applications such as autonomous logistics, infrastructure inspection, and emergency response in GPS-denied environments. However, traditional methods often struggle with cost, deployment complexity, and sensitivity to environmental dynamics, limiting their practicality for large-scale IoT scenarios. This article presents a method in which channel state information (CSI) from low-cost IoT sensors enables robust, device-free 3-D UAV localization while optimizing accuracy, sensor adaptability, and data efficiency. We propose CiUAV, leveraging CSI captured by ESP32-S3 sensors, with a robust CSI signal enhancement (RCSE) framework integrating dynamic automatic gain control (AGC) compensation (DAC) and adaptive noise suppression and outlier removal (ANSOR), alongside a sensor-in-sample (SiS) multiobjective optimization (MOO) model for adaptive multisensor fusion. Experimental evaluations in realistic indoor settings achieve a 3-D root-mean-squared error (RMSE) of 0.2659 m, outperforming baselines by up to 35% in accuracy and 50% in data efficiency. CiUAV offers a lightweight, scalable, and infrastructure-compatible solution for future IoT-enabled UAV systems.

The application of unmanned aerial vehicles (UAVs) in urban environments introduces complex challenges to path planning due to dynamic targets, changing environmental con ditions, and stringent safety requirements. To address these issues, this paper proposes an Evolving Collaborative Differential Evolution (ECDE) algorithm specifically designed for dynamic multi-objective UAV path planning. ECDE integrates an adaptive hyperparameter tuning mechanism, a robust change detection strategy, and a collaborative learning strategy to effectively balance multiple conflicting objectives, such as minimizing path length, energy consumption, noise pollution, and collision risk. Comprehensive experimental evaluations are conducted under various scenarios, including static environments, dynamic targets, and risk-adaptive urban navigation. The results demonstrate that ECDE consistently achieves superior global optimization performance and adaptability compared to state-of-the-art multi objective optimization methods, thereby significantly enhancing UAV operational effectiveness in complex, real-world urban scenarios.

Ellipse detection plays a crucial role in computer vision and measurement systems, yet existing methods often struggle with handling spatially distant arc segments, high computational complexity, and sensitivity to noise and complex geometries. In this paper, we propose a novel ellipse detection method that addresses these limitations through global arc compatibility analysis and adaptive co-clustering. We develop a probabilistic framework to represent ellipse distributions associated with detected arc segments, using Jensen-Shannon (JS) divergence to quantify arc compatibilities across the entire image. Moreover, we design an adaptive co-clustering algorithm based on Singular Value Decomposition (SVD) that efficiently groups compatible arcs while automatically estimating the number of ellipses present. This approach significantly improves detection accuracy in complex scenarios, as demonstrated by our experiments on synthetic and real-world datasets, including applications in industrial quality control and optical calibration systems. Compared to state-of-the-art methods, our algorithm achieves a 10% improvement in accuracy and 15% in recall on synthetic images, excelling particularly in detecting small and occluded ellipses. Our method provides a robust, efficient solution for ellipse detection, enhancing measurement precision across diverse imaging conditions.

Cellular segmentation in fluorescence images is challenging due to the uneven intensity distribution and distinguishable cell morphology. Existing segmentation models consider the changing cell shape and size very few. We propose a novel multi-scale parallel Swin Transformer fusion network (MSPSTF-Net) for cellular segmentation integrating cell morphological information. Multi-scale parallel Swin Transformer (MSPST) module is designed, consisting of 4 parallel branches at different scales. Each branch contains a self-attention block, which is responsible for learning features at a specific scale and capturing scale-specific information. Moreover, a multi-scale parallel feature fusion (MSPFF) module and a global feature fusion (GFF) module are designed to effectively fuse the multi-scale morphological features. We compare the proposed MSPSTF-Net with existing advanced models on three biological cellular datasets in three metrics, F1 score, AJI, and PQ, while the comprehensive results show that MSPSTF-Net has higher segmentation performance and better generalization ability. Compared to the second place, our method MSPSTF-Net achieves an average improvement of 1.091%, 2.268%, and 1.698% across three metrics on three datasets.