Methods for the frugal labeler: Multi-class semantic segmentation on heterogeneous labels

Deep learning increasingly accelerates biomedical research, deploying neural networks for multiple tasks, such as image classification, object detection, and semantic segmentation. However, neural networks are commonly trained supervised on large-scale, labeled datasets. These prerequisites raise is...

Full description

Saved in:
Bibliographic Details
Published in:PloS one 2022-02, Vol.17 (2), p.e0263656-e0263656
Main Authors: Schutera, Mark, Rettenberger, Luca, Pylatiuk, Christian, Reischl, Markus
Format: Article
Language:English
Subjects:
Analysis
Automation
Biological Phenomena
Biology and Life Sciences
Biomedical engineering
Computer and Information Sciences
Data entry
Datasets
Deep Learning
Evaluation
Humans
Image classification
Image Interpretation, Computer-Assisted - methods
Image processing
Image Processing, Computer-Assisted - methods
Image segmentation
Labeling-machines
Labelling
Labels
Machine learning
Medical imaging
Medical research
Medicine and Health Sciences
Methods
Models, Theoretical
Neural networks
Neural Networks, Computer
Object recognition
Objective function
Physical Sciences
Semantic segmentation
Semantics
Social Sciences
Training
Transfer learning
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Deep learning increasingly accelerates biomedical research, deploying neural networks for multiple tasks, such as image classification, object detection, and semantic segmentation. However, neural networks are commonly trained supervised on large-scale, labeled datasets. These prerequisites raise issues in biomedical image recognition, as datasets are generally small-scale, challenging to obtain, expensive to label, and frequently heterogeneously labeled. Furthermore, heterogeneous labels are a challenge for supervised methods. If not all classes are labeled for an individual sample, supervised deep learning approaches can only learn on a subset of the dataset with common labels for each individual sample; consequently, biomedical image recognition engineers need to be frugal concerning their label and ground truth requirements. This paper discusses the effects of frugal labeling and proposes to train neural networks for multi-class semantic segmentation on heterogeneously labeled data based on a novel objective function. The objective function combines a class asymmetric loss with the Dice loss. The approach is demonstrated for training on the sparse ground truth of a heterogeneous labeled dataset, training within a transfer learning setting, and the use-case of merging multiple heterogeneously labeled datasets. For this purpose, a biomedical small-scale, multi-class semantic segmentation dataset is utilized. The heartSeg dataset is based on the medaka fish's position as a cardiac model system. Automating image recognition and semantic segmentation enables high-throughput experiments and is essential for biomedical research. Our approach and analysis show competitive results in supervised training regimes and encourage frugal labeling within biomedical image recognition.
ISSN:1932-6203
1932-6203
DOI:10.1371/journal.pone.0263656