Jianuo Huang^1,2, Bohan Lai², Weiye Qiu³, Caixu Xu⁴, Jie He^1,5,*

CMC-Computers, Materials & Continua, Vol.82, No.3, pp. 4841-4862, 2025, DOI:10.32604/cmc.2025.059733 - 06 March 2025

Abstract The self-attention mechanism of Transformers, which captures long-range contextual information, has demonstrated significant potential in image segmentation. However, their ability to learn local, contextual relationships between pixels requires further improvement. Previous methods face challenges in efficiently managing multi-scale features of different granularities from the encoder backbone, leaving room for improvement in their global representation and feature extraction capabilities. To address these challenges, we propose a novel Decoder with Multi-Head Feature Receptors (DMHFR), which receives multi-scale features from the encoder backbone and organizes them into three feature groups with different granularities: coarse, fine-grained, and full set.… More >

Rifat Sarker Aoyon¹, Ismail Hossain², M. Abdullah-Al-Wadud³, Jia Uddin^4,*

CMES-Computer Modeling in Engineering & Sciences, Vol.142, No.3, pp. 2617-2640, 2025, DOI:10.32604/cmes.2025.060917 - 03 March 2025

Abstract This research introduces a unique approach to segmenting breast cancer images using a U-Net-based architecture. However, the computational demand for image processing is very high. Therefore, we have conducted this research to build a system that enables image segmentation training with low-power machines. To accomplish this, all data are divided into several segments, each being trained separately. In the case of prediction, the initial output is predicted from each trained model for an input, where the ultimate output is selected based on the pixel-wise majority voting of the expected outputs, which also ensures data privacy.… More >

Xuemei Yang¹, Yuting Zhou², Shiqi Liu¹, Junping Yin^2,3,*

CMC-Computers, Materials & Continua, Vol.82, No.2, pp. 3281-3307, 2025, DOI:10.32604/cmc.2024.057991 - 17 February 2025

Abstract Aiming at the problems of information loss and the relationship between features and target tasks in multimodal medical image segmentation, a multimodal medical image segmentation algorithm based on feature decoupling and information bottleneck theory is proposed in this paper. Based on the reversible network, the bottom-up learning method for different modal information is constructed, which enhances the features’ expression ability and the network’s learning ability. The feature fusion module is designed to balance multi-directional information flow. To retain the information relevant to the target task to the maximum extent and suppress the information irrelevant to… More >

Shorouq Alshawabkeh, Li Wu^*, Daojun Dong, Yao Cheng, Liping Li

CMC-Computers, Materials & Continua, Vol.82, No.1, pp. 561-577, 2025, DOI:10.32604/cmc.2024.057213 - 03 January 2025

Abstract Detecting pavement cracks is critical for road safety and infrastructure management. Traditional methods, relying on manual inspection and basic image processing, are time-consuming and prone to errors. Recent deep-learning (DL) methods automate crack detection, but many still struggle with variable crack patterns and environmental conditions. This study aims to address these limitations by introducing the MaskerTransformer, a novel hybrid deep learning model that integrates the precise localization capabilities of Mask Region-based Convolutional Neural Network (Mask R-CNN) with the global contextual awareness of Vision Transformer (ViT). The research focuses on leveraging the strengths of both architectures… More >

Hengyang Liu¹, Yang Yuan^1,*, Pengcheng Ren¹, Chengyun Song¹, Fen Luo²

CMC-Computers, Materials & Continua, Vol.82, No.1, pp. 543-560, 2025, DOI:10.32604/cmc.2024.056478 - 03 January 2025

Abstract Existing semi-supervised medical image segmentation algorithms use copy-paste data augmentation to correct the labeled-unlabeled data distribution mismatch. However, current copy-paste methods have three limitations: (1) training the model solely with copy-paste mixed pictures from labeled and unlabeled input loses a lot of labeled information; (2) low-quality pseudo-labels can cause confirmation bias in pseudo-supervised learning on unlabeled data; (3) the segmentation performance in low-contrast and local regions is less than optimal. We design a Stochastic Augmentation-Based Dual-Teaching Auxiliary Training Strategy (SADT), which enhances feature diversity and learns high-quality features to overcome these problems. To be more… More >

Guojun Chen^*, Tao Cui, Yongjie Hou, Huihui Li

CMC-Computers, Materials & Continua, Vol.81, No.3, pp. 3969-3987, 2024, DOI:10.32604/cmc.2024.056093 - 19 December 2024

Abstract Existing glass segmentation networks have high computational complexity and large memory occupation, leading to high hardware requirements and time overheads for model inference, which is not conducive to efficiency-seeking real-time tasks such as autonomous driving. The inefficiency of the models is mainly due to employing homogeneous modules to process features of different layers. These modules require computationally intensive convolutions and weight calculation branches with numerous parameters to accommodate the differences in information across layers. We propose an efficient glass segmentation network (EGSNet) based on multi-level heterogeneous architecture and boundary awareness to balance the model performance… More >

Yen-Jen Lai¹, I-Ling Chang^1,*

The International Conference on Computational & Experimental Engineering and Sciences, Vol.31, No.1, pp. 1-1, 2024, DOI:10.32604/icces.2024.012918

Abstract Biomechanical research reveals that the geometric shapes and dynamic behaviors of organ tissues play a pivotal role in determining their mechanical properties. Recent advancements in time-correlated imaging technologies, such as Computed Tomography (4D-CT) and Magnetic Resonance Imaging (4D-MRI), have enabled the non-invasive capture of both geometric data and dynamic information over time. However, the manual segmentation of these extensive datasets proves to be laborious and expensive. This study introduces an automated workflow designed for image segmentation and classification within 4D-CT scans, with a specific focus on the bone structures surrounding the Trapeziometacarpal (TMC) joint in More >

Haemin Jung¹, Heesung Park², Hae Sun Jung³, Kwangyon Lee^4,*

CMC-Computers, Materials & Continua, Vol.81, No.2, pp. 2261-2279, 2024, DOI:10.32604/cmc.2024.057118 - 18 November 2024

Abstract The growing demand for energy-efficient solutions has led to increased interest in analyzing building facades, as buildings contribute significantly to energy consumption in urban environments. However, conventional image segmentation methods often struggle to capture fine details such as edges and contours, limiting their effectiveness in identifying areas prone to energy loss. To address this challenge, we propose a novel segmentation methodology that combines object-wise processing with a two-stage deep learning model, Cascade U-Net. Object-wise processing isolates components of the facade, such as walls and windows, for independent analysis, while Cascade U-Net incorporates contour information to… More >

Qianshuo Liu, Jun Zhao^*

Phyton-International Journal of Experimental Botany, Vol.93, No.10, pp. 2663-2681, 2024, DOI:10.32604/phyton.2024.056054 - 30 October 2024

Abstract Traditional machine vision algorithms have difficulty handling the interference of light and shadow changes, broken rows, and weeds in the complex growth circumstances of soybean fields, which leads to erroneous navigation route segmentation. There are additional shortcomings in the feature extractFion capabilities of the conventional U-Net network. Our suggestion is to utilize an improved U-Net-based method to tackle these difficulties. First, we use ResNet’s powerful feature extraction capabilities to replace the original U-Net encoder. To enhance the concentration on characteristics unique to soybeans, we integrate a multi-scale high-performance attention mechanism. Furthermore, to do multi-scale feature… More >

Tao Zhou^1,3, Yunfeng Pan^1,3,*, Huiling Lu², Pei Dang^1,3, Yujie Guo^1,3, Yaxing Wang^1,3

CMC-Computers, Materials & Continua, Vol.80, No.3, pp. 4813-4832, 2024, DOI:10.32604/cmc.2024.054685 - 12 September 2024

Abstract Multimodal lung tumor medical images can provide anatomical and functional information for the same lesion. Such as Positron Emission Computed Tomography (PET), Computed Tomography (CT), and PET-CT. How to utilize the lesion anatomical and functional information effectively and improve the network segmentation performance are key questions. To solve the problem, the Saliency Feature-Guided Interactive Feature Enhancement Lung Tumor Segmentation Network (Guide-YNet) is proposed in this paper. Firstly, a double-encoder single-decoder U-Net is used as the backbone in this model, a single-coder single-decoder U-Net is used to generate the saliency guided feature using PET image and… More >