Cuiming Zou

Yuyang Sun, Cuiming Zou

In this paper, an advanced fracture detection framework, FracDetNet, is proposed to address challenges in medical imaging, as accurate fracture detection is essential for enhancing diagnostic efficiency in clinical practice. Despite recent advancements, existing methods still struggle with detecting subtle and morphologically diverse fractures due to variable imaging angles and suboptimal image quality. To overcome these limitations, FracDetNet integrates Dual-Focus Attention (DFA) and Multi-scale Calibration (MC). Specifically, the DFA module effectively captures detailed local features and comprehensive global context through combined global and local attention mechanisms. Additionally, the MC adaptively refines feature representations to enhance detection performance. Experimental evaluations on the publicly available GRAZPEDWRI-DX dataset demonstrate state-of-the-art performance, with FracDetNet achieving a mAP$_{50-95}$ of 40.0\%, reflecting a \textbf{7.5\%} improvement over the baseline model. Furthermore, the mAP$_{50}$ reaches 63.9\%, representing an increase of \textbf{4.2\%}, with fracture-specific detection accuracy also enhanced by \textbf{2.9\%}.

Yuyang Sun, Junchuan Yu, Cuiming Zou

Fracture detection plays a critical role in medical imaging analysis, traditional fracture diagnosis relies on visual assessment by experienced physicians, however the speed and accuracy of this approach are constrained by the expertise. With the rapid advancements in artificial intelligence, deep learning models based on the YOLO framework have been widely employed for fracture detection, demonstrating significant potential in improving diagnostic efficiency and accuracy. This study proposes an improved YOLO-based model, termed Fracture-YOLO, which integrates novel Critical-Region-Selector Attention (CRSelector) and Scale-Aware (ScA) heads to further enhance detection performance. Specifically, the CRSelector module utilizes global texture information to focus on critical features of fracture regions. Meanwhile, the ScA module dynamically adjusts the weights of features at different scales, enhancing the model's capacity to identify fracture targets at multiple scales. Experimental results demonstrate that, compared to the baseline model, Fracture-YOLO achieves a significant improvement in detection precision, with mAP50 and mAP50-95 increasing by 4 and 3, surpassing the baseline model and achieving state-of-the-art (SOTA) performance.

Cuiming Zou, Kit Ian Kou

Rotation moment invariants have been of great interest in image processing and pattern recognition. This paper presents a novel kind of rotation moment invariants based on the Slepian functions, which were originally introduced in the method of separation of variables for Helmholtz equations. They were first proposed for time series by Slepian and his coworkers in the 1960s. Recent studies have shown that these functions have an good performance in local approximation compared to other approximation basis. Motivated by the good approximation performance, we construct the Slepian-based moments and derive the rotation invariant. We not only theoretically prove the invariance, but also discuss the experiments on real data. The proposed rotation invariants are robust to noise and yield decent performance in facial expression classification.