convolutional neural networks (CNNs) show great potential in medical image segmentation tasks, and can provide reliable basis for disease diagnosis and clinical research. However, CNNs exhibit general limitations on modeling explicit long-range relation, and existing cures, resorting to building deep encoders along with aggressive downsampling operations, leads to loss of localized details. Transformer has naturally excellent ability to model the global features and long-range correlations of the input information, which is strongly complementary to the inductive bias of CNNs. In this paper, a novel Bi-directional Multi-scale Cascaded Segmentation Network, BMCS-Net, is proposed to improve the performance of medical segmentation tasks by aggregating these features obtained from Transformers and CNNs branches. Specifically, a novel feature integration technique, termed as Two-stream Cascaded Feature Aggregation (TCFA) module, is designed to fuse features in two-stream branches, and solve the problem of gradual dilution of global information in the network. Besides, a Multi-Scale Expansion-Aware (MSEA) module based on the convolution of feature perception and expansion is introduced to capture context information, and further compensate for the loss of details. Extensive experiments demonstrated that BMCS-Net has an excellent performance on both skin and Polyp segmentation datasets.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.compbiomed.2024.108939 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
A method for named entity recognition in social media texts with syntactically enhanced multiscale feature fusion.
Sci Rep
November 2024
Institute of Geospatial Information, Information Engineering University, Zhengzhou, 450001, China.
Social media data are characterized by significant noise and non-standardization, thereby posing challenges for existing methods in recognizing named entities owing to the entity sparsity and insufficient semantic richness. Thus, to deal with these issues, this study proposes SEMFF-NER, a named entity recognition (NER) method in social media texts that integrates multi-scale features and syntactic information. First, global features are extracted using a Transformer-based encoder (XLNET) with embedded dependency syntactic relations to enhance semantic representation.
View Article and Find Full Text PDFA Bi-Directionally Fused Boundary Aware Network for Skin Lesion Segmentation.
IEEE Trans Image Process
November 2024
It is quite challenging to visually identify skin lesions with irregular shapes, blurred boundaries and large scale variances. Convolutional Neural Network (CNN) extracts more local features with abundant spatial information, while Transformer has the powerful ability to capture more global information but with insufficient spatial details. To overcome the difficulties in discriminating small or blurred skin lesions, we propose a Bi-directionally Fused Boundary Aware Network (BiFBA-Net).
View Article and Find Full Text PDFIV-YOLO: A Lightweight Dual-Branch Object Detection Network.
Sensors (Basel)
September 2024
Institute of Electronic Science and Technology, University of Electronic Science and Technology of China, Chengdu 611731, China.
With the rapid growth in demand for security surveillance, assisted driving, and remote sensing, object detection networks with robust environmental perception and high detection accuracy have become a research focus. However, single-modality image detection technologies face limitations in environmental adaptability, often affected by factors such as lighting conditions, fog, rain, and obstacles like vegetation, leading to information loss and reduced detection accuracy. We propose an object detection network that integrates features from visible light and infrared images-IV-YOLO-to address these challenges.
View Article and Find Full Text PDFMFAM-AD: an anomaly detection model for multivariate time series using attention mechanism to fuse multi-scale features.
PeerJ Comput Sci
August 2024
State Key Laboratory of Public Big Data, College of Computer Science and Technology, Guizhou University, Guiyang, China.
Article Synopsis
- Multivariate time series anomaly detection is crucial in fields like IT, finance, and medicine, but existing models struggle with capturing complex, multi-scale patterns, leading to lower accuracy in detecting anomalies.
- To tackle this challenge, the MFAM-AD model combines convolutional neural networks (CNNs) and bi-directional long short-term memory (Bi-LSTM) to improve detection by integrating temporal dependencies and multi-scale features effectively.
- Experimental results show that MFAM-AD outperforms or closely matches state-of-the-art models, achieving higher F1 scores on several datasets, which confirms its effectiveness for real-world anomaly detection applications.
BMCS-Net: A Bi-directional multi-scale cascaded segmentation network based on transformer-guided feature Aggregation for medical images.
Comput Biol Med
September 2024
School of Electronic and Information Engineering, Zhongyuan University of Technology, Zhengzhou, 450007, China.
convolutional neural networks (CNNs) show great potential in medical image segmentation tasks, and can provide reliable basis for disease diagnosis and clinical research. However, CNNs exhibit general limitations on modeling explicit long-range relation, and existing cures, resorting to building deep encoders along with aggressive downsampling operations, leads to loss of localized details. Transformer has naturally excellent ability to model the global features and long-range correlations of the input information, which is strongly complementary to the inductive bias of CNNs.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!