Xu Xiayu, Wang Hualin, Lu Yulei, Zhang Hanze, Tan Tao, Xu Feng, Lei Jianqin
The Key Laboratory of Biomedical Information Engineering of Ministry of Education, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an 710049, PR China; Bioinspired Engineering and Biomechanics Center (BEBC), Xi'an Jiaotong University, Xi'an 710049, PR China.
The Key Laboratory of Biomedical Information Engineering of Ministry of Education, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an 710049, PR China; Bioinspired Engineering and Biomechanics Center (BEBC), Xi'an Jiaotong University, Xi'an 710049, PR China.
Artif Intell Med. 2025 Apr;162:103096. doi: 10.1016/j.artmed.2025.103096. Epub 2025 Feb 21.
Age-related macular degeneration (AMD) is the leading cause of irreversible vision loss among people over 50 years old, which manifests in the retina through various changes of retinal layers and pathological lesions. The accurate segmentation of optical coherence tomography (OCT) image features is crucial for the identification and tracking of AMD. Although the recent developments in deep neural network have brought profound progress in this area, accurately segmenting retinal layers and pathological lesions remains a challenging task because of the interaction between these two tasks.
In this study, we propose a three-branch, hierarchical multi-task framework that enables joint segmentation of seven retinal layers and three types of pathological lesions. A regression guidance module is introduced to provide explicit shape guidance between sub-tasks. We also propose a cross-dataset learning strategy to leverage public datasets with partial labels. The proposed framework was evaluated on a clinical dataset consisting of 140 OCT B-scans with pixel-level annotations of seven retinal layers and three types of lesions. Additionally, we compared its performance with the state-of-the-art methods on two public datasets.
Comprehensive ablation showed that the proposed hierarchical architecture significantly improved performance for most retinal layers and pathological lesions, achieving the highest mean DSC of 76.88 %. The IRF also achieved the best performance with a DSC of 68.15 %. Comparative studies demonstrated that the hierarchical multi-task architecture could significantly enhance segmentation accuracy and outperform state-of-the-art methods.
The proposed framework could also be generalized to other medical image segmentation tasks with interdependent relationships.
年龄相关性黄斑变性（AMD）是50岁以上人群不可逆视力丧失的主要原因，其在视网膜上表现为视网膜各层的各种变化和病理损害。光学相干断层扫描（OCT）图像特征的准确分割对于AMD的识别和跟踪至关重要。尽管深度神经网络的最新发展在该领域取得了显著进展，但由于这两项任务之间的相互作用，准确分割视网膜层和病理损害仍然是一项具有挑战性的任务。
在本研究中，我们提出了一种三分支分层多任务框架，能够对七个视网膜层和三种病理损害进行联合分割。引入了回归引导模块，以在子任务之间提供明确的形状引导。我们还提出了一种跨数据集学习策略，以利用带有部分标签的公共数据集。所提出的框架在一个临床数据集上进行了评估，该数据集由140幅OCT B扫描图像组成，具有七个视网膜层和三种病变的像素级注释。此外，我们在两个公共数据集上比较了其与现有最先进方法的性能。
全面的消融实验表明，所提出的分层架构显著提高了大多数视网膜层和病理损害的分割性能，平均DSC最高达到76.88%。内界膜（IRF）的DSC也达到了最佳性能，为68.15%。比较研究表明，分层多任务架构可以显著提高分割精度，优于现有最先进的方法。
所提出的框架也可以推广到具有相互依赖关系的其他医学图像分割任务中。
