发布日期: 2025-11-21

更新日期: 2025-11-21

文章字数: 1.1k

阅读时长: 4 分

阅读次数:

⚠️ 以下所有内容总结都来自于大语言模型的能力，如有错误，仅供参考，谨慎使用
🔴 请注意：千万不要用于严肃的学术场景，只能用于论文阅读前的初筛！
💗 如果您觉得我们的项目对您有帮助 ChatPaperFree ，还请您给我们一些鼓励！⭐️ HuggingFace免费体验

2025-11-21 更新

When CNNs Outperform Transformers and Mambas: Revisiting Deep Architectures for Dental Caries Segmentation

Authors:Aashish Ghimire, Jun Zeng, Roshan Paudel, Nikhil Kumar Tomar, Deepak Ranjan Nayak, Harshith Reddy Nalla, Vivek Jha, Glenda Reynolds, Debesh Jha

Accurate identification and segmentation of dental caries in panoramic radiographs are critical for early diagnosis and effective treatment planning. Automated segmentation remains challenging due to low lesion contrast, morphological variability, and limited annotated data. In this study, we present the first comprehensive benchmarking of convolutional neural networks, vision transformers and state-space mamba architectures for automated dental caries segmentation on panoramic radiographs through a DC1000 dataset. Twelve state-of-the-art architectures, including VMUnet, MambaUNet, VMUNetv2, RMAMamba-S, TransNetR, PVTFormer, DoubleU-Net, and ResUNet++, were trained under identical configurations. Results reveal that, contrary to the growing trend toward complex attention based architectures, the CNN-based DoubleU-Net achieved the highest dice coefficient of 0.7345, mIoU of 0.5978, and precision of 0.8145, outperforming all transformer and Mamba variants. In the study, the top 3 results across all performance metrics were achieved by CNN-based architectures. Here, Mamba and transformer-based methods, despite their theoretical advantage in global context modeling, underperformed due to limited data and weaker spatial priors. These findings underscore the importance of architecture-task alignment in domain-specific medical image segmentation more than model complexity. Our code is available at: https://github.com/JunZengz/dental-caries-segmentation.

在全景射片中准确识别和分割龋齿对于早期诊断和治疗计划的制定至关重要。由于病变对比度低、形态多样和标注数据有限，自动分割仍然是一个挑战。本研究中，我们通过对DC1000数据集上卷积神经网络、视觉变压器和状态空间曼巴架构的自动化龋齿分割进行了首次全面基准测试。在相同配置下，我们训练了包括VMUnet、MambaUNet、VMUNetv2、RMAMamba-S、TransNetR、PVTFormer、DoubleU-Net和ResUNet++在内的12种最新架构。结果出乎意料，尽管复杂注意力机制架构的趋势日益显著，但基于CNN的DoubleU-Net在dice系数（0.7345）、mIoU（0.5978）和精确度（0.8145）方面取得了最高成绩，超过了所有变压器和曼巴变体。本研究中，所有性能指标的前三名均由CNN架构实现。其中，曼巴和基于变压器的方法，尽管在全局上下文建模方面具有理论优势，但由于数据有限和空间先验较弱而表现不佳。这些发现强调了在特定领域的医学图像分割中，任务与架构对齐比模型复杂性更重要。我们的代码可在以下网址找到：https://github.com/JunZengz/dental-caries-segmentation。

论文及项目相关链接

PDF 8 pages, 4 figures

摘要

本文研究了全景射片中牙齿龋坏的自动分割问题。通过对DC1000数据集的基准测试，对比了卷积神经网络、视觉变压器和状态空间mamba架构在牙齿龋坏分割上的表现。结果显示，CNN-based的DoubleU-Net表现最佳，其Dice系数达到了0.7345，mIoU为0.5978，精确度达到了0.8145。虽然复杂注意机制架构的趋势日益盛行，但在有限数据和较弱空间先验的条件下，Mamba和基于Transformer的方法表现欠佳。研究结果表明，对于特定领域的医学图像分割任务，模型架构与任务的匹配程度比模型复杂度更重要。

关键见解