A Multi-scale CNN-CRF Framework for Environmental Microorganism Image Segmentation
This work addresses the need for efficient EM image segmentation to assist researchers in identifying microorganisms, representing an incremental improvement with specific gains in performance and resource usage.
The paper tackles the problem of segmenting Environmental Microorganism (EM) images by proposing a Multi-scale CNN-CRF (MSCC) framework, which reduces memory usage from 355 MB to 103 MB and improves segmentation metrics like Dice from 85.24% to 87.13% compared to state-of-the-art methods on 420 images.
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.