RDCNet: Instance segmentation with a minimalist recurrent residual network

Instance segmentation is a key step for quantitative microscopy. While several machine learning based methods have been proposed for this problem, most of them rely on computationally complex models that are trained on surrogate tasks. Building on recent developments towards end-to-end trainable instance segmentation, we propose a minimalist recurrent network called recurrent dilated convolutional network (RDCNet), consisting of a shared stacked dilated convolution (sSDC) layer that iteratively refines its output and thereby generates interpretable intermediate predictions. It is light-weight and has few critical hyperparameters, which can be related to physical aspects such as object size or density.We perform a sensitivity analysis of its main parameters and we demonstrate its versatility on 3 tasks with different imaging modalities: nuclear segmentation of H&E slides, of 3D anisotropic stacks from light-sheet fluorescence microscopy and leaf segmentation of top-view images of plants. It achieves state-of-the-art on 2 of the 3 datasets.

[1]  Didier Stricker,et al.  SDC – Stacked Dilated Convolution: A Unified Descriptor Network for Dense Matching Tasks , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Yuanyuan Wang,et al.  Dual U-Net for the Segmentation of Overlapping Glioma Nuclei , 2019, IEEE Access.

[3]  Thomas Neff,et al.  Instance Segmentation and Tracking with Cosine Embeddings and Recurrent Hourglass Networks , 2018, MICCAI.

[4]  Andrea Vedaldi,et al.  Semi-convolutional Operators for Instance Segmentation , 2018, ECCV.

[5]  Hao Chen,et al.  A Multi-Organ Nucleus Segmentation Challenge , 2020, IEEE Transactions on Medical Imaging.

[6]  Peyman Moghadam,et al.  Deep Leaf Segmentation Using Synthetic Data , 2018, BMVC.

[7]  Jian Sun,et al.  Identity Mappings in Deep Residual Networks , 2016, ECCV.

[8]  Ross B. Girshick,et al.  Mask R-CNN , 2017, 1703.06870.

[9]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[10]  Long Chen,et al.  Instance Segmentation of Biomedical Images with an Object-Aware Embedding Learned with Local Constraints , 2019, MICCAI.

[11]  Eugene W. Myers,et al.  Cell Detection with Star-convex Polygons , 2018, MICCAI.

[12]  Eugene W. Myers,et al.  Star-convex Polyhedra for 3D Object Detection and Segmentation in Microscopy , 2019, 2020 IEEE Winter Conference on Applications of Computer Vision (WACV).

[13]  Yang Wang,et al.  Optimizing Intersection-Over-Union in Deep Neural Networks for Image Segmentation , 2016, ISVC.

[14]  Richard S. Zemel,et al.  End-to-End Instance Segmentation with Recurrent Attention , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Jia Deng,et al.  Stacked Hourglass Networks for Human Pose Estimation , 2016, ECCV.

[16]  Luc Van Gool,et al.  Semantic Instance Segmentation with a Discriminative Loss Function , 2017, ArXiv.

[17]  Luc Van Gool,et al.  Instance Segmentation by Jointly Optimizing Spatial Embeddings and Clustering Bandwidth , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Aleksandar Vakanski,et al.  Bending Loss Regularized Network for Nuclei Segmentation in Histopathology Images , 2020, 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI).

[19]  Pascal Fua,et al.  Recurrent U-Net for Resource-Constrained Segmentation , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[20]  Christian Payer,et al.  Segmenting and tracking cell instances with cosine embeddings and recurrent hourglass networks , 2019, Medical Image Anal..