Enhancing Skin Cancer Detection Through Category Representation and Fusion of Pre-Trained Models

Published: Jan. 1, 2025

Language: Английский

---

Segmentation of skin layers on HFUS images using the attention mechanism

Computer Methods and Programs in Biomedicine, Journal Year: 2025, Volume and Issue: 263, P. 108668 - 108668

Published: Feb. 21, 2025

Language: Английский

---

Improved Grain Boundary Reconstruction Method Based on Channel Attention Mechanism

Materials, Journal Year: 2025, Volume and Issue: 18(2), P. 253 - 253

Published: Jan. 8, 2025

The grain size of metal materials has a significant impact on their macroscopic properties. However, original metallographic images often suffer from issues such as substantial noise, missing boundaries, low contrast, and blurred edges. These challenges hinder the accurate extraction complete limiting precision measurement material performance prediction. Therefore, effectively reconstructing incomplete boundaries is particularly crucial. This paper proposes boundary reconstruction method based an improved channel attention mechanism. A generative adversarial network (GAN) serves backbone, with custom-designed module embedded in generator. Combined global context mechanism, captures contextual information image, enhancing network's semantic understanding accuracy for regions boundaries. During image process, leverages long-range feature correlations within significantly improving performance. To address Mode Collapse observed during experiments, loss function optimized using Focal Loss, balancing ratio positive negative samples robustness. Compared other modules, enhances network. Experimental results demonstrate that this outperforms comparable modules terms MIoU (86.25%), Accuracy (95.06%), Precision (86.54%). mechanism not only improves but also generalization ability provides reliable technical support characterization microstructure prediction materials.

Language: Английский

---

ARCUNet: enhancing skin lesion segmentation with residual convolutions and attention mechanisms for improved accuracy and robustness

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: March 18, 2025

Skin lesion segmentation presents significant challenges due to the high variability in size, shape, color, and texture presence of artifacts like hair, shadows, reflections, which complicate accurate boundary delineation. To address these challenges, we proposed ARCUNet, a semantic model including residual convolutions attention techniques improve accuracy skin segmentation, By incorporating mechanisms, ARCUNet enhances feature learning, stabilizes training, sharpens focus on boundaries for improved accuracy. Residual ensure better gradient flow faster convergence, while mechanisms refine selection by emphasizing critical regions suppressing irrelevant details. The was tested ISIC 2016, 2017, 2018 datasets with outstanding results measures 98.12%, 96.45%, 98.19%, Dice 94.68%, 91.21%, 95.34%, Jaccard 91.14%, 88.33%, 93.53%, respectively. These findings signify ability segment lesions accurately thus as an effective tool computerized disease diagnosis.

Language: Английский

---

A Review of U‐Net‐Based Deep Learning Models for Skin Lesion Segmentation

International Journal of Imaging Systems and Technology, Journal Year: 2025, Volume and Issue: 35(3)

Published: May 1, 2025

ABSTRACT Automated skin lesion segmentation is crucial for early and accurate cancer diagnosis. Deep learning, particularly U‐Net, has revolutionized the field of automatic segmentation. This review comprehensively examines U‐Net its variants employed automated It outlines foundational architecture explores diverse architectural innovations, including attention mechanisms, advanced skip connections, residual dilated convolutions, transformer models, hybrid models. The highlights how these adaptations address inherent challenges in segmentation, data limitations heterogeneity. also discusses commonly used datasets, evaluation metrics, compares model performance computational cost. Finally, it addresses existing future research directions to advance

Language: Английский

---

Remote Sensing Image Denoising Based on Feature Interaction Complementary Learning

Remote Sensing, Journal Year: 2024, Volume and Issue: 16(20), P. 3820 - 3820

Published: Oct. 14, 2024

Optical remote sensing images are of considerable significance in a plethora applications, including feature recognition and scene semantic segmentation. However, the quality is compromised by influence various types noise, which has detrimental impact on their practical applications aforementioned fields. Furthermore, intricate texture characteristics inherent to present significant hurdle removal noise restoration image details. In order address these challenges, we propose interaction complementary learning (FICL) strategy for denoising. terms, network comprised four main components: predictor (NP), reconstructed (RIP), module (FIM), fusion module. The combination modules serves not only complete prediction results NP RIP, but also achieve deep coupling two predictors. Consequently, advantages can be combined, thereby enhancing denoising capability model. comprehensive experimentation both synthetic Gaussian datasets real-world demonstrated that FICL achieved favorable outcomes, emphasizing efficacy robustness proposed framework.

Language: Английский

---

Spatiotemporal Meteorological Prediction Based on Fully Convolutional Neural Network

IEEE Transactions on Geoscience and Remote Sensing, Journal Year: 2024, Volume and Issue: 62, P. 1 - 18

Published: Jan. 1, 2024

Language: Английский

---