Medical Image Segmentation: A Comprehensive Review of Deep Learning-Based Methods

Tomography, Journal Year: 2025, Volume and Issue: 11(5), P. 52 - 52

Published: April 30, 2025

Medical image segmentation is a critical application of computer vision in the analysis medical images. Its primary objective to isolate regions interest images from background, thereby assisting clinicians accurately identifying lesions, their sizes, locations, and relationships with surrounding tissues. However, compared natural images, present unique challenges, such as low resolution, poor contrast, inconsistency, scattered target regions. Furthermore, accuracy stability results are subject more stringent requirements. In recent years, widespread Convolutional Neural Networks (CNNs) vision, deep learning-based methods for have become focal point research. This paper categorizes, reviews, summarizes current representative research status field segmentation. A comparative relevant experiments presented, along an introduction commonly used public datasets, performance evaluation metrics, loss functions Finally, potential future directions development trends this predicted analyzed.

Language: Английский

Sustainable Sewage Treatment Prediction Using Integrated KAN-LSTM with Multi-Head Attention

Sustainability, Journal Year: 2025, Volume and Issue: 17(10), P. 4417 - 4417

Published: May 13, 2025

The accurate prediction of sewage treatment indicators is crucial for optimizing management and supporting sustainable water use. This study proposes the KAN-LSTM model, a hybrid deep learning model combining Long short-term memory (LSTM) networks, Kolmogorov-Arnold Network (KAN) layers, multi-head attention. effectively captures complex temporal dynamics nonlinear relationships in data, outperforming conventional methods. We applied correlation analysis with time-lag consideration to select key indicators. then processes them through LSTM layers sequential dependencies, KAN enhanced modeling via learnable B-spline transformations, attention dynamic weighting features. combination handles patterns long-range dependencies effectively. Experiments showed model’s superior performance, achieving 95.13% R-squared score FOss (final sedimentation basin outflow suspended solid, one indicator our research predictions)and significantly improving accuracy. These advancements intelligent not only enhance sustainability but also demonstrate transformative potential approaches. methodology could be extended optimize predictive tasks aquaponic systems other smart aquaculture applications.

Language: Английский

A Comprehensive Review of Deep Learning Applications in Cotton Industry: From Field Monitoring to Smart Processing

Plants, Journal Year: 2025, Volume and Issue: 14(10), P. 1481 - 1481

Published: May 15, 2025

Cotton is a vital economic crop in global agriculture and the textile industry, contributing significantly to food security, industrial competitiveness, sustainable development. Traditional technologies such as spectral imaging machine learning improved cotton cultivation processing, yet their performance often falls short complex agricultural environments. Deep (DL), with its superior capabilities data analysis, pattern recognition, autonomous decision-making, offers transformative potential across value chain. This review highlights DL applications seed quality assessment, pest disease detection, intelligent irrigation, harvesting, fiber classification et al. enhances accuracy, efficiency, adaptability, promoting modernization of production precision agriculture. However, challenges remain, including limited model generalization, high computational demands, environmental adaptability issues, costly annotation. Future research should prioritize lightweight, robust models, standardized multi-source datasets, real-time optimization. Integrating multi-modal data—such remote sensing, weather, soil information—can further boost decision-making. Addressing these will enable play central role driving intelligent, automated, transformation industry.

Language: Английский