Key points are not available for this paper at this time.
ABSTRACT Accurate lesion segmentation in medical image analysis is critical for diagnosis and treatment planning. However, traditional U‐shaped architectures often struggle with large variation in lesion size and blurred boundaries. To address these challenges, a model called SFIF‐Net has been proposed in this study. In particular, SFIF‐Net strengthens feature interaction through four key components: a Hierarchical Feature Aggregation (HFA) module to enable cross‐layer feature fusion guidance; a Layer‐wise Feature Aggregation (LWFA) module in skip connections for dynamic multiscale fusion; an Interactive Feature Fusion (IFF) module equipped with a Spectral Feature Migration (SFM) component in the decoder to restore fine boundaries via spatial‐frequency fusion and a Multiscale Feature Enhancement (MFE) module applied across stages to improve multilevel feature learning. Experiments have been conducted on four public datasets, which are ISIC2018, BUSI, GlaS and CVC‐ClinicDB, and four metrics (Dice, mIoU, HD95 and Specificity) are used for evaluating the model performance. Experimental results show that SFIF‐Net outperforms other popular models. It achieves the highest average Dice score across all four datasets, outperforming the second‐best models by 1.02%, 1.22%, 0.06% and 0.06%, respectively. The source code is available at https://github.com/shen123shen/SFIF‐Net‐main .
Shen et al. (Fri,) studied this question.