17 September 2024 in IEEE Transactions on Nanobioscience
The features of the sublingual veins, including swelling, varicose patterns, and cyanosis, are pivotal in differentiating symptoms and selecting treatments in Traditional Chinese Medicine (TCM) tongue diagnosis. These features serve as a crucial reflection of the human blood circulation status. Nevertheless, the automatic and precise extraction of sublingual vein features remains a formidable challenge, constrained by the scarcity of datasets for sublingual images and the interference of noise from non-tongue and non-sublingual vein elements. In this paper, we present an innovative tongue feature extraction method that relies on focusing specifically on segmenting the sublingual vein rather than the entire tongue base. To achieve this, we have developed a sublingual vein segmentation framework utilizing a Polyp-PVT network, effectively eliminating noise from the surrounding regions of the sublingual vein. Furthermore, we pioneer the utilization of a transformer-based approach, such as the Swin-Transformer network, to extract sublingual vein features, leveraging the remarkable capabilities of transformer networks. To complement our methodology, we have constructed a comprehensive dataset of sublingual vein images, facilitating the segmentation and classification of sublingual veins. Experimental results have demonstrated that our tongue feature extraction method, coupled with sublingual vein segmentation, significantly outperforms existing tongue feature extraction techniques.
26 September 2024 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
The area of impervious surfaces serves as a critical metric to gauge urbanization levels and evaluate ecological health in a given region. However, in some areas with low-density impervious surfaces, these impervious surfaces are often small in size and distributed scatteredly, making them easily mistaken for the background. Therefore, accurately extracting these small and scattered impervious surfaces remains a significant challenge. In our previous work, TCA-Net pioneered the application of transformers for extracting impervious surfaces. However, owing to the limitations of transformers, TCA-Net struggled to precisely identify small, scattered impervious surfaces. In many cases, some minor roads extracted are discontinuous and incomplete. To enhance the transformer's performance in extracting impervious surfaces, we introduce MSTCA-Net, a dual-branch network. MSTCA-Net incorporates a multi-scale transformer that preserves local details while capturing global context, and a Unet branch augmented with a coordinate attention mechanism, which captures intricate details while minimizing information redundancy. Experimental results show that MSTCA-Net proposed in this work can greatly outperform the traditional CNN models and our previous work, especially in extracting small and scattered impervious surfaces.
15 April 2025 in IEEE Transactions on Computational Social Systems
Colorectal cancer (CRC) is a prevalent malignancy with significant social and healthcare implications, ranking among the top causes of cancer-related mortality worldwide. In this computational social systems context, we address the challenge of accurately segmenting CRC lesions from colonoscopy images, which is pivotal for early cancer detection and treatment. The complexity of intestinal environments and variations in medical expertise contribute to the high rate of undetected or misdiagnosed lesions, underscoring the need for advanced computational models. This study presents ColoSegNet, a novel self-supervised deep learning framework designed to enhance the accuracy and effectiveness of CRC diagnosis. By leveraging a comprehensive and annotated colorectal lesion segmentation dataset (CLSD), ColoSegNet incorporates a temporal correlation module to extract critical features from colonoscopy video frames, significantly improving the segmentation of colorectal lesions. Furthermore, ColoSegNet employs a masked autoencoder (MAE) module for self-supervised image reconstruction, preserving the original image integrity and facilitating precise segmentation. Comparative assessments against established models such as UNet, PraNet, and Deeplab V3 demonstrate ColoSegNet’s superior performance in detailed feature representation and overall segmentation accuracy. This research not only contributes to the field of medical imaging but also to computational social systems, by capturing inherent data patterns and integrating specialized modules for feature representation in a healthcare context. Our findings provide valuable insights into the early and accurate detection of CRC, a critical issue given the disease’s high incidence and mortality rates, and its impact on social systems.
23 July 2025 in Interdisciplinary Sciences: Computational Life Sciences