Medical Frequency Domain Learning: Consider Inter-class and Intra-class Frequency for Medical Image Segmentation and Classification

Huang, Yonghao; Zhou, Chuan; Chen, Leiting; Chen, Junjing; Lan, Shanlin

doi:10.1109/bibm52615.2021.9669443

Cited by 7 publications

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the spatial domain, the boundaries between segmented objects and the background often exhibit blurriness, making it challenging to accurately identify them. However, in the frequency domain, by using Fourier transform, the shape and texture information contained in different frequency components can be combined to better separate the objects of interest (Azad et al 2021, Huang et al 2021, Zhong et al 2022. Furthermore, multi-axis aggregation facilitates effective global and local information interaction (Zhao et al 2021, Zhengzhong et al 2022.…”

Section: Fsrabmentioning

confidence: 99%

FreqSNet: a multiaxial integration of frequency and spatial domains for medical image segmentation

Liu,

Lin,

Liu

2024

Phys. Med. Biol.

View full text Add to dashboard Cite

Objective. In recent years, convolutional neural networks, which typically focus on extracting spatial domain features, have shown limitations in learning global contextual information. However, frequency domain can offer a global perspective that spatial domain methods often struggle to capture. To address this limitation, we propose FreqSNet, which leverages both frequency and spatial features for medical image segmentation. Approach. To begin, we propose a frequency-space representation aggregation block (FSRAB) to replace conventional convolutions. FSRAB contains three frequency domain branches to capture global frequency information along different axial combinations, while a convolutional branch is designed to interact information across channels in local spatial features. Secondly, the multiplex expansion attention block extracts long-range dependency information using dilated convolutional blocks, while suppressing irrelevant information via attention mechanisms. Finally, the introduced Feature Integration Block enhances feature representation by integrating semantic features that fuse spatial and channel positional information. Main results. We validated our method on 5 public datasets, including BUSI, CVC-ClinicDB, CVC-ColonDB, ISIC-2018, and Luna16. On these datasets, our method achieved Intersection over Union (IoU) scores of 75.46%, 87.81%, 79.08%, 84.04%, and 96.99%, and Hausdorff distance values of 22.22 mm, 13.20 mm, 13.08 mm, 13.51 mm, and 5.22 mm, respectively. Compared to other state-of-the-art methods, our FreqSNet achieves better segmentation results. Significance. Our method can effectively combine frequency domain information with spatial domain features, enhancing the segmentation performance and generalization capability in medical image segmentation tasks.

show abstract

Section: Fsrabmentioning

confidence: 99%

FreqSNet: a multiaxial integration of frequency and spatial domains for medical image segmentation

Liu,

Lin,

Liu

2024

Phys. Med. Biol.

View full text Add to dashboard Cite

show abstract

“…Few-Shot Semantic Segmentation: This task was originally proposed in [68]. Most works after that follow the metric learning paradigm [14] with various novelties from improved support-query matching [47,72,95] to better optimization [46,104], memory modules [90,93], graph neural networks [84,92,99], and more [28,42,45,52,53,78,98,106]. Some methods generate representative support prototypes with attention mechanism [20,100], adaptive prototype learning [41,57,73], or various prototype generation techniques [49,54,86,94].…”

Section: Related Workmentioning

confidence: 99%

Learning Expressive Prompting With Residuals for Vision Transformers

Das¹,

Dukler²,

Ravichandran³

et al. 2023

Preprint

View full text Add to dashboard Cite

Prompt learning is an efficient approach to adapt transformers by inserting learnable set of parameters into the input and intermediate representations of a pre-trained model. In this work, we present Expressive Prompts with Residuals (EXPRES) which modifies the prompt learning paradigm specifically for effective adaptation of vision transformers (ViT). Our method constructs downstream representations via learnable "output" tokens (shallow prompts), that are akin to the learned class tokens of the ViT. Further for better steering of the downstream representation processed by the frozen transformer, we introduce residual learnable tokens that are added to the output of various computations. We apply EXPRES for image classification and few-shot semantic segmentation, and show our method is capable of achieving state of the art prompt tuning on 3/3 categories of the VTAB benchmark. In addition to strong performance, we observe that our approach is an order of magnitude more prompt efficient than existing visual prompting baselines. We analytically show the computational benefits of our approach over weight space adaptation techniques like finetuning. Lastly we systematically corroborate the architectural design of our method via a series of ablation experiments.

show abstract