VL-AcneSeg：一种用于区域感知痤疮病变分割的视觉-语言框架
VL-AcneSeg: A Vision-Language Framework for Region-Aware Acne Lesion Segmentation
浏览论文内容
中文总结 AI 辅助
VL-AcneSeg利用CLIP和区域级文本提示实现全脸痤疮病变分割，在内部数据集上取得最高Dice和IoU，且无需位置信息，并能在外部数据上零样本可靠运行，为临床外客观评估提供基础。
中文摘要 AI 辅助
痤疮评估对于临床决策至关重要，然而传统的分级和计数方法具有主观性，且未能考虑病变大小。尽管基于面积的评估已成为一种有前景的替代方案，但痤疮分割仍依赖于通用架构。为解决这一差距，我们提出了VL-AcneSeg，一种用于痤疮病变分割的多模态框架，该框架利用CLIP和区域级文本提示来整合空间先验，使得病变能够在全脸范围内被定位。由于区域级提示指示了哪些面部区域包含病变，我们报告了一个单一的全局提示（无需此类信息）作为我们的主要设置。在我们的内部临床数据集上，VL-AcneSeg在该协议下取得了0.5082的Dice分数和0.3407的IoU，这是所有比较方法中最高的，包括近期本身被给予区域级提示的视觉-语言分割方法；区域级提示将这些指标提升至0.5296和0.3602。此外，由我们的分割导出的病变面积测量与IGA评分的相关性达到了与专家注释相当的水平（Pearson r = 0.719对比0.658）。值得注意的是，我们的框架在外部验证数据集上保持了一致的性能，即使在不加控制的智能手机图像上也能可靠地执行，无需额外的训练或微调。通过将无需病变位置信息的协议与基于面积的严重程度估计相结合，这项工作为临床之外的客观痤疮评估奠定了基础。我们的实现公开可用，网址为：此https URL。
英文摘要
Acne assessment is crucial for clinical decision-making, yet traditional grading and counting are subjective and fail to account for lesion size. While area-based assessment has emerged as a promising alternative, acne segmentation has continued to rely on general-purpose architectures. To address this gap, we propose VL-AcneSeg, a multimodal framework for acne lesion segmentation that leverages CLIP and region-level text prompts to incorporate spatial priors, enabling lesions to be localized across the whole face. Because region-level prompts indicate which facial areas contain lesions, we report a single global prompt, which requires no such information, as our primary setting. On our internal clinical dataset, VL-AcneSeg achieves a Dice score of 0.5082 and an IoU of 0.3407 under this protocol, the highest among all compared methods, including recent vision-language segmentation methods that are themselves given region-level prompts; region-level prompting raises these to 0.5296 and 0.3602. Moreover, lesion area measurements derived from our segmentation correlate with IGA scores at a level comparable to expert annotations (Pearson r = 0.719 versus 0.658). Notably, our framework maintains consistent performance across external validation datasets, performing reliably even on uncontrolled smartphone images without requiring additional training or fine-tuning. By pairing a protocol that requires no lesion-location information with area-based severity estimation, this work provides a foundation for objective acne assessment outside the clinic. Our implementation is publicly available at: https://github.com/sukjuoh/VL-AcneSeg
发表机构
- Dongguk University（东国大学）
- InSkin Lab Inc.（InSkin Lab 公司）
机构由 AI 辅助整理，请以论文原文为准。
