Deep-learning based multiclass retinal fluid segmentation and detection in optical coherence tomography images using a fully convolutional neural network.
Medical Image Analysis(2019)
摘要
•A novel deep learning based framework was proposed for multiclass retinal fluid segmentation and detection in OCT images. A fully convolutional neural network was applied for fluid segmentation followed by a random forest classifier to improve the accuracy.•Additional pixel-wise spatial information from layer segmentation was introduced for fully convolutional neural network based fluid segmentation followed by random forest classification to rule out false positive regions and determine the fluid presence in each volume.•The proposed framework won the first place in the Retinal OCT Fluid Challenge in the 2017 Medical Image Computing and Computer Assisted InterventionsConference (MICCAI) on both segmentation and detection tasks.
更多查看译文
关键词
Retinal fluid,Optical coherence tomography,Fully convolutional network,Multiclass segmentation and detection
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络