Feedback U-Net for Cell Image Segmentation

Eisuke Shibuya, Kazuhiro Hotta; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2020, pp. 974-975

Human brain is a layered structure, and performs not only a feedforward process from a lower layer to an upper layer but also a feedback process from an upper layer to a lower layer. This layer is a collection of neurons, and neural network is a mathematical model of the function of neurons. Although neural network imitates the human brain, everyone uses only feedforward process from the lower layer to the upper layer, and feedback process from the upper layer to the lower layer is not used. Therefore, in this paper we propose Feedback U-Net using Convolutional LSTM, which is segmentation method using Convolutional LSTM and feedback process. The output of U-net gave feedback to the input. By using Convolutional LSTM, the feature of the second lap by feedback is extracted based on the feature acquired in the first lap. On both of the Drosophila cell image and Mouse cell image datasets, our method outperformed conventional U-Net which uses only feedforward process.