Patient re-identification in medical imaging facilitates longitudinal studies, monitors treatment, and ensures patient privacy. Accurate patient re-identification enables clinicians to track patient progress, compare ...
详细信息
ISBN:
(数字)9798350376036
ISBN:
(纸本)9798350376043
Patient re-identification in medical imaging facilitates longitudinal studies, monitors treatment, and ensures patient privacy. Accurate patient re-identification enables clinicians to track patient progress, compare new imaging results with historical data, and ensure that the correct treatment plans are followed without compromising patient confidentiality. However, identifying similar patients presents significant challenges when dealing with low-quality images, like chest X-ray images, especially when the presence of medical equipment obscures key anatomical features. this paper introduces a Graph Matching Network-based approach for patient re-identification using chest X-ray data. By representing such images as graphs, where nodes correspond to key anatomical landmarks and edges represent spatial relationships, the Graph Matching Network can effectively model the complex dependencies within the images. In addition, we integrate superpixel as a representative feature extraction approach in a robust strategy to describe the images as a graph model. Our method is evaluated on a large-scale dataset of chest X-ray images, demonstrating its superior performance compared to other methods. Experimental results show that our approach improves the precision of patient matching by integrating a novel loss function based on the cosine distance of the graph embedding representation, enhancing its robustness against common challenges such as variations in image quality, patient posture, and imaging equipment.
Skin cancer is a disease that causes thousands of deaths each year. Early diagnosis and monitoring the progression of the disease are crucial factors for the treatment and health indicators of a society. this study pr...
详细信息
ISBN:
(数字)9798350376036
ISBN:
(纸本)9798350376043
Skin cancer is a disease that causes thousands of deaths each year. Early diagnosis and monitoring the progression of the disease are crucial factors for the treatment and health indicators of a society. this study presents an innovative approach for the detection, segmentation, and classification of melanomas in dermoscopic images using advanced Computer Vision and Artificial Intelligence (AI) methods. Specifically, it applies Large Language Model (LLM) solutions for pre-diagnosis results through generative AI. this work explores combinations of methods for melanoma detection and segmentation based on the YOLO and SAM architectures, achieving 99% accuracy, surpassing various studies in the literature. the classification phase is based on a pipeline integrating feature extraction and selecting the best combination for melanoma region classification, achieving an accuracy of 86.0%, also outperforming different studies in the literature.
Early detection of potentially malignant disorders such as oral epithelial dysplasia (OED) is important for preventing oral cancer. Semantic segmentation of nuclei in histopathological images provides relevant insight...
详细信息
ISBN:
(数字)9798350376036
ISBN:
(纸本)9798350376043
Early detection of potentially malignant disorders such as oral epithelial dysplasia (OED) is important for preventing oral cancer. Semantic segmentation of nuclei in histopathological images provides relevant insights for pathologists. CNN-based methods have shown promise in improving histological lesion detection and segmentation processes, but achieving results with significant values in terms accuracy metrics remains a challenging task. this paper presents an ensemble approach to enhance the performance of semantic segmentation for nuclei in OED histopathology images. Six CNN models were employed, and their outputs were associated using three ensemble strategies: simple averaging, weighted averaging, and majority voting. To further enhance model robustness, a data augmentation stage was assessed. the proposed ensemble, combined with an image augmentation strategy, achieved accuracy and Dice coefficient values of 93.41 % and 0.88, respectively, on OED images. Analysis of the OED grades showed values ranging from 91.14% to 95.24 % and 0.87 to 0.90 for accuracy and Dice coefficient, respectively. these values show an improvement over the CNN segmentation models. the analysis of segmentation performance withthe OED grade images is another significant contribution of this study that addresses a gap in the literature. A validation stage on three publicly available datasets demonstrated that our approach is on par with state-of-the-art methods.
Vision-based geolocation is a promising way to overcome the vulnerabilities of Global Navigation Satellite System (GNSS) methods, which are subject to signal degradation, intentional interference, and environmental ob...
详细信息
ISBN:
(数字)9798350376036
ISBN:
(纸本)9798350376043
Vision-based geolocation is a promising way to overcome the vulnerabilities of Global Navigation Satellite System (GNSS) methods, which are subject to signal degradation, intentional interference, and environmental obstacles. this paper presents a novel approach to Unmanned Aerial Vehicle (UAV) geolocation in long-range and high-altitude missions using satellite imagery. Our method is based on the matching of encoded vector representations in embedded space, demonstrating robust performance to changes in vegetation and landscape. the neural network is used to encode satellite images of a reference map into embedding representations. Image matching is performed in this embedded space using cross-correlation. We evaluated the accuracy and processing time of the proposed model by querying images along a 200 km northbound path at high altitude, covering an area larger than twenty thousand square kilometers. We also evaluated the network's generalization capability on an unknown map. Reference and query images are sourced from satellite images captured at different acquisition times to evaluate robustness due to appearance variations. the results demonstrate that the method can achieve up to 96.83% accuracy on a known map, while experiments on an unknown map averaged 90% accuracy. the processing time to match encoded images is 0.05 ms. these findings suggest the feasibility of integrating the method into more complex vision-based geolocation systems.
暂无评论