Ensemble Processing and Synthetic Image Generation for Abnormally Shaped Nuclei Segmentation
Preprint
Abstract
Abnormalities in biological cell nuclei morphology are correlated with cell cycle stages, disease states, and various external stimuli. There have been many deep learning approaches that have described nuclei segmentation and analysis of nuclear morphology. One problem with many deep learning methods is acquiring large amounts of annotated nuclei data, which is generally expensive to obtain. In this paper, we propose a system to segment abnormally shaped nuclei with a limited amount of training data. We first generate specific shapes of synthetic nuclei groundtruth. We randomly sample these synthetic groundtruth images into training sets to train several Mask R-CNNs. We design an ensemble strategy to combine or fuse segmentation results from the Mask R-CNNs. We also design an oval nuclei removal by StarDist to reduce the false positives and improve the overall segmentation performance. Our experiments indicate that our method outperforms other methods in segmenting abnormally shaped nuclei.Keywords
This publication has 13 references indexed in Scilit:
- Ensemble deep learning: A reviewEngineering Applications of Artificial Intelligence, 2022
- Polycomb represses a gene network controlling puberty via modulation of histone demethylase Kdm6b expressionScientific Reports, 2021
- Cellpose: a generalist algorithm for cellular segmentationNature Methods, 2020
- Nuclear Morphology and the Biology of Cancer CellsActa Cytologica, 2020
- Star-convex Polyhedra for 3D Object Detection and Segmentation in Microscopy2020
- Automatic Nucleus Segmentation with Mask-RCNN2019
- Cell Detection with Star-Convex Polygons2018
- Elastic deformations for data augmentation in breast cancer mass detection2018
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- A Threshold Selection Method from Gray-Level HistogramsIEEE Transactions on Systems, Man, and Cybernetics, 1979