融合多尺度感知与模糊边界建模的息肉分割网络

打开文本图片集

中图分类号：TP391 文献标志码：A doi：10.12415/j.issn.1671-7872.25009

Polyp Segmentation Network Based on Multi-scale Feature Perception and Fuzzy Boundary Modeling

WANG Sunbin， SHI Liuwei， HUANG Jun （School of Computer Science & Technology， Anhui University of Technology， Maanshan 243032， China）

Abstract： Endoscopic image segmentation technology as a routine clinical diagnostic method， whose segmentation accuracy directly affects physicians’diagnosis and treatment decisions of lesion areas.In view of the limitations of existing methods in challnging scenarios such as poor image quality and blured lesion area boundaries，a polyp segmentation network integrating multi-scale feature perception and fuzzy boundary modeling was proposed. Firstly， the image was decomposed into sub-bands of diferent scales and frequencies through discrete wavelet transform to extract global structural and local detailed features，while an adaptive atention mechanism was employed to dynamically adjust the weights of each sub-band feature， achieving multi-scale feature perception. Secondly， a variational multi-sampling module wasutilized to map features into latent space for probability distribution modeling， where diversified latent space representations were generated through multiple reparameterized samplings， effectively smoothing blurred regions and improving boundary segmentation accuracy.Experiments were conducted on five public datasets （CVC-300，CVC-ClinicDB， Kvasir-SEG， CVC-ColonDB，ETIS-LaribPolyDB）and the nonpublic USTCAI dataset to validate the performance of the proposed method.The results demonstrate that the proposed method outperforms existing methods in both Dice coefcient and mIoU metrics.Particularly on the ETIS-LaribPolyDB dataset，mDice coefficient of 57.54% is achieved， surpassing the state-of-the-art method by 7.16% ， while on the CVC-ClinicDB dataset， an outstanding mDice coefficient of 91.88% is attained， exhibiting excellent segmentation performance and generalization capability in complex scenarios.By combining multi-scale feature perception with fuzzy boundary modeling techniques，the proposed method effectively addresses key challnges in endoscopic image segmentation， providing more accurate and reliable technical support for clinical diagnosis.

Keywords： polyp images; image segmentation; feature perception; fuzzy boundary; boundary modeling; attention mechanism; smart medical

结直肠癌作为全球高发的恶性肿瘤[1-2]，早期发现并切除息肉可显著降低其癌变风险。（剩余16120字）