PraNet-V2用双重监督反向注意力提升医学图像分割精度
PraNet-V2: Dual-Supervised Reverse Attention for Medical Image Segmentation
- 引入双监督反向注意力模块，融合背景信息与语义特征
- 在4个结肠镜数据集上实现高精度分割，多类别任务表现更优
- 可嵌入主流模型，显著提升前景分割效果，适合医疗影像研究者
精准的医学图像分割对诊断和治疗至关重要。此前提出的PraNet-V1通过反向注意力（RA）模块利用背景信息提升息肉分割性能，但在多类别分割任务中表现不足。为此，我们提出PraNet-V2，相较V1可有效处理更广泛的分割任务。其核心是双监督反向注意力（DSRA）模块，包含显式背景监督、独立背景建模及语义增强的注意力融合。PraNet-V2在四个息肉分割数据集上表现优异。此外，将DSRA模块集成至三个先进语义分割模型中，迭代优化前景分割结果，平均Dice分数最高提升1.36%。代码已开源：https://github.com/ai4colonoscopy/PraNet-V2/tree/main/binary_seg/jittor。
原文摘要 · Abstract (English)
Accurate medical image segmentation is essential for effective diagnosis and treatment. Previously, PraNet-V1 was proposed to enhance polyp segmentation by introducing a reverse attention (RA) module that utilizes background information. However, PraNet-V1 struggles with multi-class segmentation tasks. To address this limitation, we propose PraNet-V2, which, compared to PraNet-V1, effectively performs a broader range of tasks including multi-class segmentation. At the core of PraNet-V2 is the Dual-Supervised Reverse Attention (DSRA) module, which incorporates explicit background supervision, independent background modeling, and semantically enriched attention fusion. Our PraNet-V2 framework demonstrates strong performance on four polyp segmentation datasets. Additionally, by integrating DSRA to iteratively enhance foreground segmentation results in three state-of-the-art semantic segmentation models, we achieve up to a 1.36% improvement in mean Dice score. Code is available at: https://github.com/ai4colonoscopy/PraNet-V2/tree/main/binary_seg/jittor.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。