Deep Learning Techniques for Medical Image Segmentation: Achievements and Challenges

Abstract

Deep learning-based image segmentation is by now firmly established as a robust tool in image segmentation. It has been widely used to separate homogeneous areas as the first and critical component of diagnosis and treatment pipeline. In this article, we present a critical appraisal of popular methods that have employed deep-learning techniques for medical image segmentation. Moreover, we summarize the most common challenges incurred and suggest possible solutions.

Keywords

Artificial intelligenceDeep learningComputer scienceSegmentationPipeline (software)Image segmentationHomogeneousSegmentation-based object categorizationImage (mathematics)Critical appraisalScale-space segmentationComponent (thermodynamics)Computer visionPattern recognition (psychology)Machine learningMedicineMathematicsPathology

MeSH Terms

Deep LearningDiagnostic ImagingHumansImage ProcessingComputer-Assisted

Affiliated Institutions

University of Technology Sydney AU

Related Publications

Deep Learning for Single Image Super-Resolution: A Brief Review

Wenming Yang , Xuechen Zhang , Yapeng Tian +3 more

Single image super-resolution (SISR) is a notoriously challenging ill-posed\nproblem, which aims to obtain a high-resolution (HR) output from one of its\nlow-resolution (LR) ver...

2019 IEEE Transactions on Multimedia 1101 citations

An overview of deep learning in medical imaging focusing on MRI

Alexander Selvikvåg Lundervold , Alexander Selvikvåg Lundervold , Arvid Lundervold +3 more

What has happened in machine learning lately, and what does it mean for the future of medical image analysis? Machine learning has witnessed a tremendous amount of attention ove...

2018 Zeitschrift für Medizinische Physik 1819 citations

Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?

Nima Tajbakhsh , J. Shin , Suryakanth Gurudu +4 more

Training a deep convolutional neural network (CNN) from scratch is difficult because it requires a large amount of labeled training data and a great deal of expertise to ensure ...

2016 IEEE Transactions on Medical Imaging 2961 citations

Data augmentation for improving deep learning in image classification problem

Agnieszka Mikołajczyk , Michał Grochowski

These days deep learning is the fastest-growing field in the field of Machine Learning (ML) and Deep Neural Networks (DNN). Among many of DNN structures, the Convolutional Neura...

2018 2018 International Interdisciplinary ... 1623 citations

UNet 3+: A Full-Scale Connected UNet for Medical Image Segmentation

Huimin Huang , Lanfen Lin , Ruofeng Tong +6 more

Recently, a growing interest has been seen in deep learning-based semantic segmentation. UNet, which is one of deep learning networks with an encoder-decoder architecture, is wi...

2020 ICASSP 2020 - 2020 IEEE International... 2398 citations

Publication Info

Year: 2019
Type: review
Volume: 32
Issue: 4
Pages: 582-596
Citations: 1523
Access: Closed

External Links

Download PDF (Free) View on DOI.org PubMed Semantic Scholar

Social Impact

Altmetric

Deep Learning Techniques for Medical Image Segmentation: Achievements and Challenges

PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

1523

OpenAlex

Influential

Cite This

APA Style

                            
                                
                                    Mohammad Hesam Hesamian, 
                                
                                    Wenjing Jia, 
                                
                                    Xiangjian He
                                
                                et al.
                            
                            (2019). 
                            Deep Learning Techniques for Medical Image Segmentation: Achievements and Challenges. 
                            Journal of Digital Imaging
                            , 32
                            (4)
                            , 582-596.
                            https://doi.org/10.1007/s10278-019-00227-x
                        

Identifiers

DOI: 10.1007/s10278-019-00227-x
PMID: 31144149
PMCID: PMC6646484

Data Quality

Data completeness: 86%