2018
DOI: 10.3390/sym10100519
|View full text |Cite
|
Sign up to set email alerts
|

Synthetic Medical Images Using F&BGAN for Improved Lung Nodules Classification by Multi-Scale VGG16

Abstract: Lung cancer is one of the highest causes of cancer-related death in both men and women. Therefore, various diagnostic methods for lung nodules classification have been proposed to implement the early detection. Due to the limited amount and diversity of samples, these methods encounter some bottlenecks. In this paper, we intend to develop a method to enlarge the dataset and enhance the performance of pulmonary nodules classification. We propose a data augmentation method based on generative adversarial network… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

1
37
0
4

Year Published

2019
2019
2024
2024

Publication Types

Select...
3
2
2

Relationship

0
7

Authors

Journals

citations
Cited by 73 publications
(42 citation statements)
references
References 26 publications
(52 reference statements)
1
37
0
4
Order By: Relevance
“…To increase the efficiency, we simplify the process into two steps by using the SSD network. More precisely, we just need a convolutional neural network such as VGG16 [29] as a model system to identify the gesture features and then proceed with hand segmentation and gesture classification simultaneously by the SSD network.…”
Section: Related Workmentioning
confidence: 99%
“…To increase the efficiency, we simplify the process into two steps by using the SSD network. More precisely, we just need a convolutional neural network such as VGG16 [29] as a model system to identify the gesture features and then proceed with hand segmentation and gesture classification simultaneously by the SSD network.…”
Section: Related Workmentioning
confidence: 99%
“…Já Onishi et al [9] e Zhao et al [10], a proximidadeé mais tangível. Onishi et al [9] utiliza uma Wasserstein GAN (WGAN) para gerar cortes de imagens sintéticas de nódulos de CT usadas para pré-treinamento de uma CNN profunda que classifica nódulos pulmonares e tendo o ajuste fino feito com as imagens originais dos nódulos.…”
Section: A Trabalhos Relacionadosunclassified
“…Essa abordagem gerou um ganho de quase 30% naárea sobre a curva ROC em relação ao caso sem pré-treinamento [9]. Zhao et al [10] utiliza sua própria abordagem: a Forward and Backward GAN (F&BGAN). O modelo proposto pelos autores gera cortes de imagens de CT de nódulos malignos e benignos demonstrando a capacidade das imagens sintéticas na melhora da performance de uma classificador M-VGG16.…”
Section: A Trabalhos Relacionadosunclassified
See 2 more Smart Citations