Introducing frequency representation into convolution neural networks for medical image segmentation via twin-Kernel Fourier convolution

Tang, Xianlun; Peng, Jiangping; Zhong, Bing; Li, Jie; Yan, Zhenfu

doi:10.1016/j.cmpb.2021.106110

Cited by 14 publications

(6 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our approach, we contemplate a strategy for image detail recovery, whereby we introduce the adoption of an upsampling methodology rooted in the frequency domain representation [33]. This strategy selectively reconstitutes image details during the restoration of image details, embodying a distinctive attribute within the upsampling procedure.…”

Section: Spectrum Upsampling Block(sub)mentioning

confidence: 99%

See 1 more Smart Citation

MLU-Net: A Multi-Level Lightweight U-Net for Medical Image Segmentation Integrating Frequency Representation and MLP-Based Methods

Feng,

Wu,

Pei

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Medical image segmentation is a challenging and popular task in the field of medical image processing in recent decades. Most of the current mainstream segmentation networks are based on convolutional neural networks (CNNs) methods. Among them, encoding and decoding structures based on U-Net architecture and skip connection mechanism have made great progress in medical segmentation. However, these networks come with increased complexity and training difficulty as the accuracy of network segmentation continues to increase, and their ability remains to be improved for extracting feature information in specific information-intensive structure segmentation tasks, such as brain tumors. In addition, the high training cost raises the application threshold of medical image segmentation. To address these issues, we introduce a frequency representation approach that can effectively reduce the loss of feature during encoding and decoding of segmentation networks. Then a tokenized multi-layer perceptron (MLP) method is introduced to learn the space information. Frequency representation and tokenized MLP can greatly reduce the parameters and computational effort while achieving more accurate and efficient medical image segmentation. Therefore, a multi-level lightweight U-Net segmentation network named MLU-Net is proposed to perform segmentation tasks of medical images quickly. In brain tumor segmentation experiments under equivalent preprocessing conditions, our network achieves substantial efficiency gains with parameter and computational workload reductions to 1/39 and 1/61 of U-Net's, while simultaneously demonstrating superior performance, enhancing the Dice and Intersection over Union (IoU) metrics by 3.37% and 3.30%, respectively. In addition, we perform experiments on dermatologic data and still achieve segmentation performance that outperforms comparable networks. These experiments show that the proposed network is characterized by lightweight and high accuracy, which is contributing to the exploration of clinical medicine scenarios. INDEX TERMSMedical image segmentation; convolution neural networks; frequency representation; MLP-based; brain tumor segmentation; computer-aided diagnosis.

show abstract

Section: Spectrum Upsampling Block(sub)mentioning

confidence: 99%

“…achieved in the spatial domain. In this segment, we embrace an alternative strategy for upsampling, which involves the introduction of a method based on frequency domain representation [33], thereby substituting conventional techniques such as interpolation and transposed convolution.…”

Section: Algorithm 2 Spectrum Upsampingmentioning

confidence: 99%

MLU-Net: A Multi-Level Lightweight U-Net for Medical Image Segmentation Integrating Frequency Representation and MLP-Based Methods

Feng,

Wu,

Pei

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…In recent years, the application of high-frequency and low-frequency features in images have become the main research direction, and high-frequency and low-frequency features can also be called local information and global information. These algorithms 30 – 32 use different methods to separate global and local features. The difference between local and global components is that global information contains the global shape and structure of the image, while local information pays more attention to the texture change of the image.…”

Section: Related Workmentioning

confidence: 99%

“…In recent years, the application of high-frequency and low-frequency features in images have become the main research direction, and high-frequency and low-frequency features can also be called local information and global information. These algorithms [30][31][32] MBSNet draws on the concept of high and low-frequency information capture and combination, but the difference is that we use dilated convolution and average pooling operations to obtain global features, and only supplement local information with global information in the encoder stage, while local information does not combine global information. This is done to learn more about pure semantic information and reduce network complexity.…”

Section: Related Workmentioning

confidence: 99%

A novel medical image segmentation approach by using multi-branch segmentation network based on local and global information synchronous learning

Jin

Peng

et al. 2023

Sci Rep

View full text Add to dashboard Cite

In recent years, there have been several solutions to medical image segmentation, such as U-shaped structure, transformer-based network, and multi-scale feature learning method. However, their network parameters and real-time performance are often neglected and cannot segment boundary regions well. The main reason is that such networks have deep encoders, a large number of channels, and excessive attention to local information rather than global information, which is crucial to the accuracy of image segmentation. Therefore, we propose a novel multi-branch medical image segmentation network MBSNet. We first design two branches using a parallel residual mixer (PRM) module and dilate convolution block to capture the local and global information of the image. At the same time, a SE-Block and a new spatial attention module enhance the output features. Considering the different output features of the two branches, we adopt a cross-fusion method to effectively combine and complement the features between different layers. MBSNet was tested on five datasets ISIC2018, Kvasir, BUSI, COVID-19, and LGG. The combined results show that MBSNet is lighter, faster, and more accurate. Specifically, for a $$320 \times 320$$ 320 × 320 input, MBSNet’s FLOPs is 10.68G, with an F1-Score of $$85.29\%$$ 85.29 % on the Kvasir test dataset, well above $$78.73\%$$ 78.73 % for UNet++ with FLOPs of 216.55G. We also use the multi-criteria decision making method TOPSIS based on F1-Score, IOU and Geometric-Mean (G-mean) for overall analysis. The proposed MBSNet model performs better than other competitive methods. Code is available at https://github.com/YuLionel/MBSNet.

show abstract

“…• Additional inputs: In addition to color space transformations, recent works incorporate more focused and domain-specific inputs to the segmentation models, such as Fourier domain representation using the discrete Fourier transform (Tang et al, 2021b) and inputs based on the physics of skin illumination and imaging (Abhishek et al, 2020).…”

Section: Image Preprocessingmentioning

confidence: 99%

A Survey on Deep Learning for Skin Lesion Segmentation

Mirikharaji¹,

Barata²,

Kumar³

et al. 2022

Preprint

View full text Add to dashboard Cite

Skin cancer is a major public health problem that could benefit from computer-aided diagnosis to reduce the burden of this common disease. Skin lesion segmentation from images is an important step toward achieving this goal. However, the presence of natural and artificial artifacts (e.g., hair and air bubbles), intrinsic factors (e.g., lesion shape and contrast), and variations in image acquisition conditions make skin lesion segmentation a challenging task. Recently, various researchers have explored the applicability of deep learning models to skin lesion segmentation. In this survey, we cross-examine 134 research papers that deal with deep learning based segmentation of skin lesions. We analyze these works along several dimensions, including input data (datasets, preprocessing, and synthetic data generation), model design (architecture, modules, and losses), and evaluation aspects (data annotation requirements and segmentation performance). We discuss these dimensions both from the viewpoint of select seminal works, and from a systematic viewpoint, examining how those choices have influenced current trends, and how their limitations should be addressed. We summarize all examined works in a comprehensive table to facilitate comparisons.

show abstract

Introducing frequency representation into convolution neural networks for medical image segmentation via twin-Kernel Fourier convolution

Cited by 14 publications

References 19 publications

MLU-Net: A Multi-Level Lightweight U-Net for Medical Image Segmentation Integrating Frequency Representation and MLP-Based Methods

MLU-Net: A Multi-Level Lightweight U-Net for Medical Image Segmentation Integrating Frequency Representation and MLP-Based Methods

A novel medical image segmentation approach by using multi-branch segmentation network based on local and global information synchronous learning

A Survey on Deep Learning for Skin Lesion Segmentation

Contact Info

Product

Resources

About