FlyNet 2.0: drosophila heart 3D (2D+time) segmentation in optical coherence microscopy images using a convolutional long short-term memory neural network
FlyNet 2.0: drosophila heart 3D (2D+time) segmentation in optical coherence microscopy images using a convolutional long short-term memory neural network
复制标题
DOI：
10.1364/boe.385968
复制
发表时间：
2020-03-01
影响因子：
3.4
通讯作者：
Zhou, Chao
中科院分区：
文献类型：
--
作者：
Dong, Zhao;Men, Jing;Zhou, Chao
集成卷积长短期记忆（LSTM）的自定义卷积神经网络（CNN）在光学相干显微镜（OCM）系统获得的果蝇心脏横截面视频中实现了精确的3D （2D +时间）分割。我们之前的FlyNet 1.0模型利用常规cnn从单个视频帧中提取2D空间信息，而FlyNet 2.0的卷积LSTM同时利用空间和时间信息来进一步提高分割性能。为了训练和测试FlyNet 2.0，我们使用了100个数据集，包括500,000张蝇心OCM图像。在三个发育阶段和两种心跳情况下的OCM视频被分割，达到了92%的交叉结合（IOU）准确率。这种增加分割精度允许形态学和动态心脏参数更好地量化。(C) 2020年美国光学学会根据OSA开放获取出版协议的条款
A custom convolutional neural network (CNN) integrated with convolutional long short-term memory (LSTM) achieves accurate 3D (2D + time) segmentation in cross-sectional videos of the Drosophila heart acquired by an optical coherence microscopy (OCM) system. While our previous FlyNet 1.0 model utilized regular CNNs to extract 2D spatial information from individual video frames, convolutional LSTM, FlyNet 2.0, utilizes both spatial and temporal information to improve segmentation performance further. To train and test FlyNet 2.0, we used 100 datasets including 500,000 fly heart OCM images. OCM videos in three developmental stages and two heartbeat situations were segmented achieving an intersection over union (IOU) accuracy of 92%. This increased segmentation accuracy allows morphological and dynamic cardiac parameters to be better quantified. (C) 2020 Optical Society of America under the terms of the OSA Open Access Publishing Agreement