Variability and reproducibility in deep learning for medical image segmentation

Medical image segmentation is an important tool for current clinical applications. It is the backbone of numerous clinical diagnosis methods, oncological treatments and computer-integrated surgeries. A new class of machine learning algorithm, deep learning algorithms, outperforms the results of clas...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Scientific reports Ročník 10; číslo 1; s. 13724
Hlavní autoři: Renard, Félix, Guedria, Soulaimane, Palma, Noel De, Vuillerme, Nicolas
Médium: Journal Article
Jazyk:angličtina
Vydáno: London Nature Publishing Group UK 13.08.2020
Nature Publishing Group
Témata:
639/705/117
692/308
Algorithms
Artificial Intelligence
Computer Science
Deep Learning
Diagnostic Imaging - methods
Humanities and Social Sciences
Humans
Image Interpretation, Computer-Assisted - methods
Image processing
Image Processing, Computer-Assisted - methods
Learning algorithms
Literature reviews
Machine learning
Medical Imaging
multidisciplinary
Neural Networks, Computer
Reproducibility
Reproducibility of Results
Science
Science (multidisciplinary)
Segmentation
Surgery
ISSN:2045-2322, 2045-2322
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Medical image segmentation is an important tool for current clinical applications. It is the backbone of numerous clinical diagnosis methods, oncological treatments and computer-integrated surgeries. A new class of machine learning algorithm, deep learning algorithms, outperforms the results of classical segmentation in terms of accuracy. However, these techniques are complex and can have a high range of variability, calling the reproducibility of the results into question. In this article, through a literature review, we propose an original overview of the sources of variability to better understand the challenges and issues of reproducibility related to deep learning for medical image segmentation. Finally, we propose 3 main recommendations to address these potential issues: (1) an adequate description of the framework of deep learning, (2) a suitable analysis of the different sources of variability in the framework of deep learning, and (3) an efficient system for evaluating the segmentation results.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
PMCID: PMC7426407
ISSN:2045-2322
2045-2322
DOI:10.1038/s41598-020-69920-0