# M3FPolypSegNet: Segmentation Network with Multi-frequency Feature Fusion for Polyp Localization in Colonoscopy Images

Source: [M3FPolypSegNet: Segmentation Network with Multi-frequency Feature Fusion for Polyp Localization in Colonoscopy Images](<https://www.sota2.com/research/paper/68fa70cd1e209131cea4d3f6>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T03:52:35.301Z

Authors: Ju-Hyeon Nam, Seo-Hyeong Park, Nur Suriza Syazwany, Yerim Jung, Yu-Han Im, Sang-Chul Lee

Published: 2023-10-09T09:01:53.000Z

## Abstract

Polyp segmentation is crucial for preventing colorectal cancer a common type of cancer. Deep learning has been used to segment polyps automatically, which reduces the risk of misdiagnosis. Localizing small polyps in colonoscopy images is challenging because of its complex characteristics, such as color, occlusion, and various shapes of polyps. To address this challenge, a novel frequency-based fully convolutional neural network, Multi-Frequency Feature Fusion Polyp Segmentation Network (M3FPolypSegNet) was proposed to decompose the input image into low/high/full-frequency components to use the characteristics of each component. We used three independent multi-frequency encoders to map multiple input images into a high-dimensional feature space. In the Frequency-ASPP Scalable Attention Module (F-ASPP SAM), ASPP was applied between each frequency component to preserve scale information. Subsequently, scalable attention was applied to emphasize polyp regions in a high-dimensional feature space. Finally, we designed three multi-task learning (i.e., region, edge, and distance) in four decoder blocks to learn the structural characteristics of the region. The proposed model outperformed various segmentation models with performance gains of 6.92% and 7.52% on average for all metrics on CVC-ClinicDB and BKAI-IGH-NeoPolyp, respectively.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Polyp Segmentation on CVC-ClinicDB 12 (test)](<https://www.sota2.com/research/sota/polyp-segmentation-on-cvc-clinicdb-12-test.md>): Polyp Segmentation; CVC-ClinicDB 12 (test); Accuracy: 98.83.

- [Polyp Segmentation on BKAI-IGH-NeoPolyps 13 (test)](<https://www.sota2.com/research/sota/polyp-segmentation-on-bkai-igh-neopolyps-13-test.md>): Polyp Segmentation; BKAI-IGH-NeoPolyps 13 (test); Accuracy: 98.91.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2310.05538>)

[PDF](<https://arxiv.org/pdf/2310.05538.pdf>)