A comparative study of semi- and self-supervised semantic segmentation of biomedical microscopy data

11/11/2020

∙

In recent years, Convolutional Neural Networks (CNNs) have become the state-of-the-art method for biomedical image analysis. However, these networks are usually trained in a supervised manner, requiring large amounts of labelled training data. These labelled data sets are often difficult to acquire in the biomedical domain. In this work, we validate alternative ways to train CNNs with fewer labels for biomedical image segmentation using. We adapt two semi- and self-supervised image classification methods and analyse their performance for semantic segmentation of biomedical microscopy images.

READ FULL TEXT

A comparative study of semi- and self-supervised semantic segmentation of biomedical microscopy data

Leveraging Self-supervised Denoising for Image Segmentation

Three Ways to Improve Semantic Segmentation with Self-Supervised Depth Estimation

Convolution Neural Networks for Semantic Segmentation: Application to Small Datasets of Biomedical Images

Semantic Segmentation of Neuronal Bodies in Fluorescence Microscopy Using a 2D+3D CNN Training Strategy with Sparsely Annotated Data

Region Growing with Convolutional Neural Networks for Biomedical Image Segmentation

Clumped Nuclei Segmentation with Adjacent Point Match and Local Shape based Intensity Analysis for Overlapped Nuclei in Fluorescence In-Situ Hybridization Images

BT-Unet: A self-supervised learning framework for biomedical image segmentation using Barlow Twins with U-Net models

A comparative study of semi- and self-supervised semantic segmentation of biomedical microscopy data

Related Research

Leveraging Self-supervised Denoising for Image Segmentation

Three Ways to Improve Semantic Segmentation with Self-Supervised Depth Estimation

Convolution Neural Networks for Semantic Segmentation: Application to Small Datasets of Biomedical Images

Semantic Segmentation of Neuronal Bodies in Fluorescence Microscopy Using a 2D+3D CNN Training Strategy with Sparsely Annotated Data

Region Growing with Convolutional Neural Networks for Biomedical Image Segmentation

Clumped Nuclei Segmentation with Adjacent Point Match and Local Shape based Intensity Analysis for Overlapped Nuclei in Fluorescence In-Situ Hybridization Images

BT-Unet: A self-supervised learning framework for biomedical image segmentation using Barlow Twins with U-Net models