Real-time retinal layer segmentation of OCT volumes with GPU accelerated inferencing using a compressed, low-latency neural network
Real-time retinal layer segmentation of OCT volumes with GPU accelerated inferencing using a compressed, low-latency neural network
复制标题
DOI：
10.1364/boe.395279
复制
发表时间：
2020-07-01
影响因子：
3.4
通讯作者：
Jian, Yifan
中科院分区：
文献类型：
--
作者：
Borkovkina, Svetlana;Camino, Acner;Jian, Yifan
光学相干断层扫描（OCT）中视网膜层的分割是OCT图像分析中用于筛查、诊断和评估视网膜疾病进展的重要步骤。实时分割与高速OCT体积采集一起允许渲染任意视网膜层的正面OCT，其可用于提高高质量扫描的良率，在图像引导手术期间提供实时反馈，以及补偿自适应光学（AO）OCT中的像差而不使用波前传感器。我们在这里展示了前所未有的八个视网膜层边界的实时OCT分割，通过3个级别的优化实现：1）修改后的低复杂性神经网络结构，2）使用TensorRT的神经网络压缩创新方案，以及3）专用GPU硬件加速计算。使用压缩网络U-NetRT进行推理需要3.5 ms，在不降低准确性的情况下，将传统U-Net推理的速度提高了21倍。从数据采集到推理的整个流水线的延迟仅为41 ms，这是通过并行批处理实现的。该系统和方法允许在连续模式扫描中实时更新任意视网膜层和神经丛的正面OCT和OCTA可视化。据我们所知，我们的工作是第一次展示具有嵌入式人工智能（AI）的眼科成像仪，提供实时反馈。(C)2020年美国光学学会根据OSA开放获取出版协议的条款
Segmentation of retinal layers in optical coherence tomography (OCT) is an essential step in OCT image analysis for screening, diagnosis, and assessment of retinal disease progression. Real-time segmentation together with high-speed OCT volume acquisition allows rendering of en face OCT of arbitrary retinal layers, which can be used to increase the yield rate of high-quality scans, provide real-time feedback during image-guided surgeries, and compensate aberrations in adaptive optics (AO) OCT without using wavefront sensors. We demonstrate here unprecedented real-time OCT segmentation of eight retinal layer boundaries achieved by 3 levels of optimization: 1) a modified, low complexity, neural network structure, 2) an innovative scheme of neural network compression with TensorRT, and 3) specialized GPU hardware to accelerate computation. Inferencing with the compressed network U-NetRT took 3.5 ms, improving by 21 times the speed of conventional U-Net inference without reducing the accuracy. The latency of the entire pipeline from data acquisition to inferencing was only 41 ms, enabled by parallelized batch processing. The system and method allow real-time updating of en face OCT and OCTA visualizations of arbitrary retinal layers and plexuses in continuous mode scanning. To the best our knowledge, our work is the first demonstration of an ophthalmic imager with embedded artificial intelligence (AI) providing real-time feedback. (C) 2020 Optical Society of America under the terms of the OSA Open Access Publishing Agreement