Macular Hole and Cystoid Macular Edema Joint Segmentation by Two-Stage Network and Entropy Minimization

Ye, Lei; Zhu, Weifang; Bao, Dengsen; Feng, Shuanglang; Chen, Xinjian

doi:10.1007/978-3-030-59722-1_71

Cited by 3 publications

(1 citation statement)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the rise of the convolutional neural network (CNN), it has been used in more and more lesion segmentation tasks in OCT images, such as for segmentation of retinal edema (Feng et al 2020), retinal layer and fluid (Roy et al 2017), subretinal fluid and pigment epithelial detachment (Gao et al 2019, Hu et al 2019, macular hole and cystoid macular edema (Ye et al 2020). Its excellent capability of feature extraction results in superior segmentation performance.…”

Section: Introductionmentioning

confidence: 99%

Segmentation of retinal detachment and retinoschisis in OCT images based on complementary multi-class segmentation networks

et al. 2023

View full text Add to dashboard Cite

Retinal detachment (RD) and retinoschisis (RS) are the main complications leading to vision loss in high myopia. Accurate segmentation of RD and RS, including its subcategories (outer, middle, and inner retinoschisis) in optical coherence tomography (OCT) images is of great clinical significance in the diagnosis and management of high myopia. For this multi-class segmentation task, we propose a novel framework named complementary multi-class segmentation networks (CMC-Net). Based on domain knowledge, a three-class segmentation path (TSP) and a five-class segmentation path (FSP) are designed, and their outputs are integrated through additional decision fusion layers to achieve improved segmentation in a complementary manner. In TSP, a cross-fusion global feature module (CFGF) is adopted to achieve global receptive field. In FSP, a novel three-dimensional contextual information perception module (TCIP) is proposed to capture long-range contexts, and a classification branch is designed to provide useful features for segmentation. A new category loss is also proposed in FSP to help better identify the lesion categories. Experiment results show that the proposed method achieves superior performance for joint segmentation of RD and the three subcategories of RS, with an average Dice coefficient of 84.83%.

show abstract