Published on Wed Nov 27 2019

Leveraging Self-supervised Denoising for Image Segmentation

Mangal Prakash, Tim-Oliver Buchholz, Manan Lalit, Pavel Tomancak, Florian Jug, Alexander Krull

Deep learning (DL) has arguably emerged as the method of choice for the detection and segmentation of biological structures in microscopy images. DL typically needs copious amounts of annotated training data that is typically not available and excessively expensive to generate.

0
0
0
Abstract

Deep learning (DL) has arguably emerged as the method of choice for the detection and segmentation of biological structures in microscopy images. However, DL typically needs copious amounts of annotated training data that is for biomedical projects typically not available and excessively expensive to generate. Additionally, tasks become harder in the presence of noise, requiring even more high-quality training data. Hence, we propose to use denoising networks to improve the performance of other DL-based image segmentation methods. More specifically, we present ideas on how state-of-the-art self-supervised CARE networks can improve cell/nuclei segmentation in microscopy data. Using two state-of-the-art baseline methods, U-Net and StarDist, we show that our ideas consistently improve the quality of resulting segmentations, especially when only limited training data for noisy micrographs are available.

Tue Jul 30 2019
Computer Vision
Deep Learning architectures for generalized immunofluorescence based nuclear image segmentation
Deep Neural Networks can learn the implicit transformation of a nuclear image into a probability map. The use of post-processing steps to turn the probability map into a labeled object mask is error-prone. Mask R-CNN, an architecture designed to address instance aware segmentation tasks, outperforms other architectures.
0
0
0
Wed Nov 13 2019
Computer Vision
Cost-efficient segmentation of electron microscopy images using active learning
Automated image analysis, particularly image segmentation, has not evolved at the same pace. State-of-the-art methods such as U-Net and DeepLab have improved segmentation performance substantially. Active learning is the subfield in machine learning that aims to mitigate this burden.
0
0
0
Mon Mar 22 2021
Computer Vision
Deep Neural Networks Learn Meta-Structures to Segment Fluorescence Microscopy Images
0
0
0
Thu Jun 20 2019
Machine Learning
Learning to segment microscopy images with lazy labels
Deep convolutional neural network for microscopy image segmentation. Annotation issues are circumvented by letting the network be trained on coarse labels combined with only a very small number of images.
0
0
0
Mon Oct 26 2020
Machine Learning
Semi supervised segmentation and graph-based tracking of 3D nuclei in time-lapse microscopy
We propose a novel weakly supervised method to improve the boundary of the 3D segmented nuclei utilizing an over-segmented image. The proposed algorithm achieves better segmentation performance compared to the state-of-the-art method in Cell Tracking Challenge (CTC) 2019.
0
0
0
Sun Apr 22 2018
Computer Vision
Micro-Net: A unified model for segmentation of various objects in microscopy images
The proposed network can be used to segment cells, nuclei and glands in fluorescence microscopy and histology images. The extra convolutional layers which bypass the max-pooling operation allow the network to train for variable input intensities and object size.
0
0
0