轻量级模型MonoUNet实现超声下膝软骨自动分割，适合临床便携设备
MonoUNet: A Robust Tiny Neural Network for Automated Knee Cartilage Segmentation on Point-of-Care Ultrasound Devices
- 用精简版U-Net加可训练相位特征提取模块提升模型鲁棒性
- 分割精度达Dice 92.6%-94.8%，参数量减少10至700倍
- 适合在便携超声设备上部署，支持膝关节退行性病变监测
目标：开发一种高效紧凑的深度学习模型，用于点对点超声（POCUS）设备上的膝软骨自动分割。方法：提出MonoUNet，一个高度精简的分割模型，包含（i）极度压缩的U-Net主干网络，（ii）可训练的单生块以提取多尺度局部相位特征，（iii）门控机制将这些特征注入编码器阶段，降低对超声图像外观变化的敏感性。在多中心、多设备的膝软骨超声数据集上评估分割性能，使用Dice分数和平均表面距离（MASD）。通过Bland-Altman分析评估模型与人工标注结果（厚度和回声强度）的一致性，使用组内相关系数（ICC$_{2,k}$）评估可靠性。结果：总体上，MonoUNet优于现有轻量级分割模型，平均Dice分数为92.62%~94.82%，MASD为0.133~0.254 mm。相比现有轻量模型，参数量减少10倍至700倍，计算成本降低14倍至2000倍。模型输出与人工结果一致性高：平均厚度的ICC$_{2,k}$=0.96，偏倚为2.00%（0.047 mm）；回声强度的ICC$_{2,k}$=0.99，偏倚为0.80%（0.328 a.u.）。结论：引入可训练局部相位特征能显著提升紧凑神经网络在不同采集条件下的鲁棒性，有助于在POCUS设备上实现膝骨关节炎的可扩展超声评估与监测。代码已公开于https://github.com/alvinkimbowa/monounet。
原文摘要 · Abstract (English)
Objective: To develop a robust and compact deep learning model for automated knee cartilage segmentation on point-of-care ultrasound (POCUS) devices. Methods: We propose MonoUNet, a novel, highly compact segmentation model consisting of (i) an aggressively reduced U-Net backbone, (ii) a trainable monogenic block that extracts multi-scale local phase features from the input, and (iii) a gating mechanism that injects these features into the encoder stages to reduce sensitivity to variations in ultrasound image appearance. MonoUNet segmentation performance was evaluated on a multi-site, multi-device knee cartilage ultrasound dataset using Dice score and mean average surface distance (MASD). Agreement between MonoUNet and manual cartilage outcomes (thickness and echo intensity) was assessed using Bland-Altman analysis with 95% limits of agreement, and reliability was assessed using intraclass correlation coefficient (ICC$_{2,k}$). Results: Overall, MonoUNet outperformed existing lightweight segmentation models, with average Dice scores ranging from 92.62% to 94.82% and MASD values between 0.133 mm and 0.254 mm. MonoUNet reduces the number of parameters by 10x--700x and computational cost by 14x--2000x relative to existing lightweight models. MonoUNet cartilage outcomes showed excellent reliability and agreement with the manual outcomes: intraclass correlation coefficients (ICC$_{2,k})$=0.96 and bias=2.00% (0.047 mm) for average thickness, and ICC$_{2,k}$=0.99 and bias=0.80% (0.328 a.u.) for echo intensity. Conclusion: Incorporating trainable local phase features improves the robustness of highly compact neural networks for knee cartilage segmentation across varying acquisition settings and could support scalable ultrasound-based assessment and monitoring of knee osteoarthritis using POCUS devices. The code is publicly available at https://github.com/alvinkimbowa/monounet.
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。