Yang Fan, Chen Pu, Lin Shiqi, Zhan Tianming, Hong Xunning, Chen Yunjie
School of Mathematics and Statistics, Nanjing University of Information Science and Technology, Nanjing, Jiangsu, China.
School of Computer Science, Nanjing Audit University, Nanjing, Jiangsu, China.
PLoS One. 2025 Jan 3;20(1):e0316089. doi: 10.1371/journal.pone.0316089. eCollection 2025.
Optical Coherence Tomography (OCT) offers high-resolution images of the eye's fundus. This enables thorough analysis of retinal health by doctors, providing a solid basis for diagnosis and treatment. With the development of deep learning, deep learning-based methods are becoming more popular for fundus OCT image segmentation. Yet, these methods still encounter two primary challenges. Firstly, deep learning methods are sensitive to weak edges. Secondly, the high cost of annotating medical image data results in a lack of labeled data, leading to overfitting during model training. To tackle these challenges, we introduce the Multi-Task Attention Mechanism Network with Pruning (MTAMNP), consisting of a segmentation branch and a boundary regression branch. The boundary regression branch utilizes an adaptive weighted loss function derived from the Truncated Signed Distance Function(TSDF), improving the model's capacity to preserve weak edge details. The Spatial Attention Based Dual-Branch Information Fusion Block links these branches, enabling mutual benefit. Furthermore, we present a structured pruning method grounded in channel attention to decrease parameter count, mitigate overfitting, and uphold segmentation accuracy. Our method surpasses other cutting-edge segmentation networks on two widely accessible datasets, achieving Dice scores of 84.09% and 93.84% on the HCMS and Duke datasets.
光学相干断层扫描（OCT）可提供眼底的高分辨率图像。这使得医生能够对视网膜健康进行全面分析，为诊断和治疗提供坚实的基础。随着深度学习的发展，基于深度学习的方法在眼底OCT图像分割中越来越受欢迎。然而，这些方法仍然面临两个主要挑战。首先，深度学习方法对弱边缘敏感。其次，医学图像数据标注成本高昂，导致缺乏标注数据，从而在模型训练期间导致过拟合。为了解决这些挑战，我们引入了带剪枝的多任务注意力机制网络（MTAMNP），它由一个分割分支和一个边界回归分支组成。边界回归分支利用从截断符号距离函数（TSDF）导出的自适应加权损失函数，提高了模型保留弱边缘细节的能力。基于空间注意力的双分支信息融合模块将这些分支连接起来，实现互利共赢。此外，我们提出了一种基于通道注意力的结构化剪枝方法，以减少参数数量、减轻过拟合并保持分割精度。我们的方法在两个广泛使用的数据集上超越了其他前沿分割网络，在HCMS和杜克数据集上分别达到了84.09%和93.84%的Dice分数。
