HHBSNet: A Global Channel–Spatial Attention and Multi‐Scale Dilated Convolution Network for Automatic Melasma Segmentation

Shange Wang¹Lin Xu¹Linshuai Zhang¹Yujie Zhang¹Chen Li²Marcin Grzegorzek³Jing Guo^4*Tao Jiang^1*

• ¹School of Intelligent Medicine, Chengdu University of Traditional Chinese Medicine, Chengdu, China
• ²Northeastern University College of Medicine and Biological Information Engineering, Shenyang, China
• ³Institute of Medical Informatics, Technische Hochschule Lubeck, Lübeck, Germany
• ⁴Chengdu University of Traditional Chinese Medicine, Chengdu, China

Objective: Melasma is a common acquired facial hyperpigmentation disorder characterized by symmetrical brown patches, often occurring in the zygomatic region, forehead, and upper lip. Its blurred boundaries, color similarity to normal skin, and irregular morphology—combined with lighting variability and skin reflections—pose significant challenges for automated lesion segmentation. This study aims to develop an effective and lightweight deep learning model tailored for accurate melasma segmentation. Methods: We propose a novel lightweight segmentation network, HHBSNet, specifically designed for melasma lesion analysis. The model incorporates a Global Channel-Spatial Attention (GCSA) module that jointly leverages channel and spatial attention to suppress lighting interference and enhance feature discrimination in low-contrast, irregular boundaries. In addition, a Multiscale Cavity Fusion (MCF) module is introduced to extend the receptive field via multi-dilation rates, enabling effective capture of lesions at various scales without reducing resolution. The network further integrates local-global semantic fusion and adopts a combined loss strategy of cross-entropy and focal loss to address class imbalance. Results: HHBSNet was evaluated on a self-constructed dataset comprising 501 practical facial melasma images. Quantitative results demonstrate that HHBSNet outperforms existing mainstream This is a provisional file, not the final typeset article segmentation methods, achieving a mean Intersection over Union (Miou) of 79.69%, accuracy (ACC) of 96.68%, F-score of 88.10%, recall of 88.18%, and precision of 87.80%. Conclusions: The proposed HHBSNet demonstrates superior segmentation performance and robustness in handling melasma's challenging visual characteristics. Its lightweight structure and strong generalization ability suggest promising potential for application in computer-aided diagnosis and large-scale clinical screening of facial pigmentary disorders.