An Attention-Based Uncertainty Revising Network with Multi-Loss for Environmental Microorganism Segmentation

The presence of environmental microorganisms is inevitable in our surroundings, and segmentation is essential for researchers to identify, understand, and utilize the microorganisms; make use of their benefits; and prevent harm. However, the segmentation of environmental microorganisms is challenging because their vague margins are almost transparent compared with those of the environment. In this study, we propose a network with an uncertainty feedback module to find ambiguous boundaries and regions and an attention module to localize the major region of the microorganism. Furthermore, we apply a mid-pred module to output low-resolution segmentation results directly from decoder blocks at each level. This module can help the encoder and decoder capture details from different scales. Finally, we use multi-loss to guide the training. Rigorous experimental evaluations on the benchmark dataset demonstrate that our method achieves higher scores than other sophisticated network models (95.63% accuracy, 89.90% Dice, 81.65% Jaccard, 94.68% recall, 0.59 ASD, 2.24 HD95, and 85.58% precision) and outperforms them.