[论文解读] MiniSeg: An Extremely Minimum Network for Efficient COVID-19 Segmentation
MiniSeg 是一个拥有 83K 参数的轻量级网络,使用注意力分层空间金字塔 (AHSP) 来快速、数据高效地分割胸部 CT 序列中的 COVID-19 受感染区域,在高效性与易重训性方面实现具有竞争力的准确性。
The rapid spread of the new pandemic, i.e., COVID-19, has severely threatened global health. Deep-learning-based computer-aided screening, e.g., COVID-19 infected CT area segmentation, has attracted much attention. However, the publicly available COVID-19 training data are limited, easily causing overfitting for traditional deep learning methods that are usually data-hungry with millions of parameters. On the other hand, fast training/testing and low computational cost are also necessary for quick deployment and development of COVID-19 screening systems, but traditional deep learning methods are usually computationally intensive. To address the above problems, we propose MiniSeg, a lightweight deep learning model for efficient COVID-19 segmentation. Compared with traditional segmentation methods, MiniSeg has several significant strengths: i) it only has 83K parameters and is thus not easy to overfit; ii) it has high computational efficiency and is thus convenient for practical deployment; iii) it can be fast retrained by other users using their private COVID-19 data for further improving performance. In addition, we build a comprehensive COVID-19 segmentation benchmark for comparing MiniSeg to traditional methods.
研究动机与目标
- 解决在有限标注数据下的 COVID-19 CT 分割挑战,以及对快速训练/推理的需求。
- 开发一个轻量但准确的分割模型,以降低过拟合和计算成本。
- 提出 AHSP 模块,在紧凑网络中实现有效的多尺度特征学习。
- 创建并基准化 COVID-19 分割数据集集合,以将 MiniSeg 与最先进的方法进行比较。
提出的方法
- 引入 AHSP:具有指数膨胀率的多分支膨胀深度可分离卷积,用于多尺度学习。
- 在各尺度之间进行分层特征融合,并采用注意力机制以突出相关结构、同时抑制噪声。
- 具有 Downsampler 块和嵌套跳跃连接的双路径编码器,以增强多尺度编码。
- 带有特征融合模块和渐进上采样的解码器,用于恢复细节,并附带深层监督。
- 高效的参数使用:K=4 个分支和分组运算以减少参数和 FLOPs,达到 83K 参数和高速。
- 在四个公开的 COVID-19 CT 分割数据集上进行数据增强训练;80 个 epoch,使用 Adam 和多项式学习率调度。
实验结果
研究问题
- RQ1在有限训练样本下,极其轻量的网络是否能够在 COVID-19 CT 数据上达到具有竞争力的分割精度?
- RQ2AHSP 模块是否在不扩大模型尺寸的情况下提升多尺度特征学习?
- RQ3在公开的 COVID-19 CT 数据集上,MiniSeg 在准确性、速度和参数效率方面与最先进的方法相比如何?
主要发现
- MiniSeg 具有 83K 参数,约比多数基线小两个数量级,推理速度也很快。
- AHSP 启用的多尺度学习在紧凑模型中提升了分割性能。
- 在多个数据集上,MiniSeg 提供了具有竞争力的 mIoU、灵敏度和 Dice 分数,同时维持高特异性和快速速度。
- For COVID-19-CT100: mIoU 82.15, SEN 84.95, SPC 97.72, DSC 75.91, HD 74.42.
- For COVID-19-P9: mIoU 85.31, SEN 90.60, SPC 99.15, DSC 80.06, HD 58.46.
- For COVID-19-P20: mIoU 84.49, SEN 85.06, SPC 99.05, DSC 76.27, HD 51.06.
- For COVID-19-P1110: mIoU 78.33, SEN 79.62, SPC 97.71, DSC 64.84, HD 71.69.
- MiniSeg 的帧率高达 516.3 fps,体现出卓越的效率。
更好的研究,从现在开始
从论文设计到论文写作,大幅缩短您的研究时间。
无需绑定信用卡
本解读由 AI 生成,并经人工编辑审核。