论文标题
环境微生物图像分段的多尺度CNN-CRF框架
A Multi-scale CNN-CRF Framework for Environmental Microorganism Image Segmentation
论文作者
论文摘要
为了帮助研究人员有效鉴定环境微生物（EMS），在本文中提出了用于EM图像分割的多尺度CNN-CRF（MSCC）框架。该框架中有两个部分：第一个是一种新型的像素级分割方法，使用新引入的卷积神经网络（CNN），即“ MU-NET-B3”，并具有密集的条件随机场（CRF）。第二个是一种基于VGG-16的贴片级分割方法，具有新颖的“缓冲”策略，进一步提高了EMS细节的分割质量。在实验中，与420张EM图像的最新方法相比，提出的MSCC方法将记忆需求从355 MB减少到103 MB，将整体评估指数（DICE，JACCARD，RESSER，RECERCE，ACRECE，准确性）从85.24％，77.42％，82.42％，82.27％和96.76％和87％和87％和87％，87.13％和87％，87.13％和87％，87.13％和87％，87.13％和87％，87.13％降至87.76％，87.13％，87.13％和87％和87％。分别为96.91％，并将体积重叠误差从22.58％减少到20.26％。因此，MSCC方法在EM分割字段中显示出巨大的潜力。
To assist researchers to identify Environmental Microorganisms (EMs) effectively, a Multiscale CNN-CRF (MSCC) framework for the EM image segmentation is proposed in this paper. There are two parts in this framework: The first is a novel pixel-level segmentation approach, using a newly introduced Convolutional Neural Network (CNN), namely, "mU-Net-B3", with a dense Conditional Random Field (CRF) postprocessing. The second is a VGG-16 based patch-level segmentation method with a novel "buffer" strategy, which further improves the segmentation quality of the details of the EMs. In the experiment, compared with the state-of-the-art methods on 420 EM images, the proposed MSCC method reduces the memory requirement from 355 MB to 103 MB, improves the overall evaluation indexes (Dice, Jaccard, Recall, Accuracy) from 85.24%, 77.42%, 82.27%, and 96.76% to 87.13%, 79.74%, 87.12%, and 96.91%, respectively, and reduces the volume overlap error from 22.58% to 20.26%. Therefore, the MSCC method shows great potential in the EM segmentation field.
