Search Results (4)

Skin cancer is a prevalent type of malignancy on a global scale, and the early and accurate diagnosis of this condition is of utmost importance for the survival of patients. The clinical assessment of cutaneous lesions is a crucial aspect of medical practice, although it encounters several obstacles, such as prolonged waiting time and misinterpretation. The intricate nature of skin lesions, coupled with variations in appearance and texture, presents substantial barriers to accurate classification. As such, skilled clinicians often struggle to differentiate benign moles from early malignant tumors in skin images. Although deep learning-based approaches such as convolution neural networks have made significant improvements, their stability and generalization continue to experience difficulties, and their performance in accurately delineating lesion borders, capturing refined spatial connections among features, and using contextual information for classification is suboptimal. To address these limitations, we propose a novel approach for skin lesion classification that combines snake models of active contour (AC) segmentation, ResNet50 for feature extraction, and a capsule network with a fusion of lightweight attention mechanisms to attain the different feature channels and spatial regions within feature maps, enhance the feature discrimination, and improve accuracy. We employed the stochastic gradient descent (SGD) optimization algorithm to optimize the model’s parameters. The proposed model is implemented on publicly available datasets, namely, HAM10000 and ISIC 2020. The experimental results showed that the proposed model achieved an accuracy of 98% and AUC-ROC of 97.3%, showcasing substantial potential in terms of effective model generalization compared to existing state-of-the-art (SOTA) approaches. These results highlight the potential for our approach to reshape automated dermatological diagnosis and provide a helpful tool for medical practitioners. Full article

Traditional villages are historically, culturally, scientifically and aesthetically valuable, and a beautiful landscape is the primary embodiment of a traditional village environment. Urbanization and modernization have had a great impact on village landscapes. As an important aspect of traditional village landscapes, creating beautiful public spaces is an effective way to attract tourists and improve the well-being of residents. Landscape aesthetic activities are the result of the interaction between landscape objects and aesthetic subjects. Research on the relationship between the form of traditional village public spaces and subjective aesthetic preferences has long been neglected. This research examined 31 public spaces in traditional villages in the Dongshan and Xishan areas in Lake Taihu, Suzhou. An index system of public spatial forms in traditional villages was created, basic data of spatial forms were collected using a hand-held 3D laser scanner, and the value of the spatial forms index was calculated using R language. The scenic beauty estimation (SBE) method was improved, with the estimation of the beauty of the scenic environment based on VR panorama rather than traditional photo media. Parameter screening was performed using correlation analysis and full subset regression analysis, and four models were used to fit the SBE scores and grades. The results show that the majority of public spaces had lower than average SBE scores, and the four key indicators of average contour upper height, solid-space ratio, vegetation cover, and comprehensive closure predicted SBE. In addition, the linear model (R² = 0.332, RMSE = 64.774) had the most accurate SBE level prediction and the stochastic forest model (R² = 0.405, RMSE = 63.311) was better at predicting specific SBE scores. The model provides managers, designers, and researchers with a method for the quantitative evaluation of visual landscape preferences and quantitative landscape spatial forms and provides a reference for the protection and renewal of traditional village landscapes. Full article

Image segmentation is a process that densely classifies image pixels into different regions corresponding to real world objects. However, this correspondence is not always exact in images since there are many uncertainty factors, e.g., recognition hesitation, imaging equipment, condition, and atmosphere environment. To achieve the segmentation result with low uncertainty and reduce the influence on the subsequent procedures, e.g., image parsing and image understanding, we propose a novel stochastic active contour model based on intuitionistic fuzzy set, in which the hesitation degree is leveraged to model the recognition uncertainty in image segmentation. The advantages of our model are as follows. (1) Supported by fuzzy partition, our model is robust against image noise and inhomogeneity. (2) Benefiting from the stochastic process, our model easily crosses saddle points of energy functional. (3) Our model realizes image segmentation with low uncertainty and co-produces the quantitative uncertainty degree to the segmentation results, which is helpful to improve reliability of intelligent image systems. The associated experiments suggested that our model could obtain competitive segmentation results compared to the relevant state-of-the-art active contour models and could provide segmentation with a pixel-wise uncertainty degree. Full article

The dynamics of cellular aggregates is driven by the interplay of mechanochemical processes and cellular activity. Although deterministic models may capture mechanical features, local chemical fluctuations trigger random cell responses, which determine the overall evolution. Incorporating stochastic cellular behavior in macroscopic models of biological media is a challenging task. Herein, we propose hybrid models for bacterial biofilm growth, which couple a two phase solid/fluid mixture description of mechanical and chemical fields with a dynamic energy budget-based cellular automata treatment of bacterial activity. Thin film and plate approximations for the relevant interfaces allow us to obtain numerical solutions exhibiting behaviors observed in experiments, such as accelerated spread due to water intake from the environment, wrinkle formation, undulated contour development, and the appearance of inhomogeneous distributions of differentiated bacteria performing varied tasks. Full article