Accurate identification of the endometrial region is critical for the early detection of endometrial lesions. However, current detection models still face two major challenges when processing endometrial imaging data: (1) In complex and noisy environments, recognition accuracy remains limited, partly due to the insufficient exploitation of color information within the images; (2) Traditional Two-dimensional PCA-based (2DPCA-based) feature selection methods have limited capacity to capture and represent key characteristics of the endometrial region. To address these challenges, this paper proposes a novel algorithm named Feature-Level Image Fusion and Improved Swarm Intelligence Optimization Algorithm (FLFSI), which integrates a learning guided binary particle swarm optimization (BPSO) strategy with an image feature selection and reconstruction framework to enhance the detection of endometrial regions in clinical ultrasound images. Specifically, FLFSI contributes to improving feature selection accuracy and image reconstruction quality, thereby enhancing the overall performance of region recognition tasks. First, we enhance endometrial image representation by incorporating feature engineering techniques that combine structural and color information, thereby improving reconstruction quality and emphasizing critical regional features. Second, the BPSO algorithm is introduced into the feature selection stage, improving the accuracy of feature selection and its global search ability while effectively reducing the impact of redundant features. Furthermore, we refined the BPSO design to accelerate convergence and enhance optimization efficiency during the selection process. The proposed FLFSI algorithm can be integrated into mainstream detection models such as YOLO11 and YOLOv12. When applied to YOLO11, FLFSI achieves 96.6% Box mAP and 87.8% Mask mAP. With YOLOv12, it further improves the Mask mAP to 88.8%, demonstrating excellent cross-model adaptability and robust detection performance. Extensive experimental results validate the effectiveness and broad applicability of FLFSI in enhancing endometrial region detection for clinical ultrasound image analysis.
UAV target detection refers to the use of computer vision algorithms to automatically identify specific objects in aerial images captured by UAV cameras. Due to the high-altitude viewpoint, these images often contain numerous small targets, which are easily missed. Existing methods are typically based on either CNN architectures or attention mechanisms. The former has insufficient global perception capabilities, making it difficult to identify small targets, while the latter requires excessive memory consumption, resulting in slow inference speed. Moreover, region-partitioned attention mechanisms often fail to effectively exchange information across different blocks, leading to inadequate extraction of small-object features. To address these issues, we propose EST-YOLO (Efficient Small Target YOLO), a network with frequency--spatial perception capabilities. First, we design a lightweight backbone, named SGGNet, which introduces a spectral-guided ghost feature generation mechanism to enable frequency-aware and low-cost feature extraction while reducing model parameters. Second, we design PFSA-FMamba (Progressive Frequency-Spatial Attention with Frequency Mamba), which first divides the feature map into blocks to ensure real-time performance, and then performs Mamba-based frequency modeling together with spatial attention to strengthen the focus on small-object regions and improve detection accuracy. Finally, we introduce a Small Object Detection Head (SODP2), which replaces the deep, low-resolution branch with a shallow, high-resolution one to preserve fine-grained spatial details of small targets while reducing redundant computation. With 49.62% fewer parameters, EST-YOLO achieves 9.98% and 5.29% higher mAP50 on VisDrone and UAVDT, respectively, compared with YOLOv12.