2018
DOI: 10.1007/s13755-018-0057-x
|View full text |Cite
|
Sign up to set email alerts
|

Transfer learning based histopathologic image classification for breast cancer detection

Abstract: Breast cancer is one of the leading cancer type among women in worldwide. Many breast cancer patients die every year due to the late diagnosis and treatment. Thus, in recent years, early breast cancer detection systems based on patient's imagery are in demand. Deep learning attracts many researchers recently and many computer vision applications have come out in various environments. Convolutional neural network (CNN) which is known as deep learning architecture, has achieved impressive results in many applica… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
129
0
2

Year Published

2019
2019
2024
2024

Publication Types

Select...
7
2
1

Relationship

1
9

Authors

Journals

citations
Cited by 283 publications
(131 citation statements)
references
References 10 publications
0
129
0
2
Order By: Relevance
“…The current study fine-tuned this by using pretrained CNN models based on transfer learning. The reason for using pretrained CNN models is that they are faster and easier than training a CNN model with randomly initialized weights [35]. In addition, the fine-tuning process is based on transferring new layers instead of the last three layers of the pretrained networks to our classification task, as shown in Figure 2.…”
Section: Transfer Learningmentioning
confidence: 99%
“…The current study fine-tuned this by using pretrained CNN models based on transfer learning. The reason for using pretrained CNN models is that they are faster and easier than training a CNN model with randomly initialized weights [35]. In addition, the fine-tuning process is based on transferring new layers instead of the last three layers of the pretrained networks to our classification task, as shown in Figure 2.…”
Section: Transfer Learningmentioning
confidence: 99%
“…In future works, the deep learning achievements will be investigated on the EEG rhythms (Deniz et al, 2018). Besides, the achievements of all EEG channels will be investigated in the deep learning fashion.…”
Section: Discussionmentioning
confidence: 99%
“…For this work, the last three layers are replaced: a fully-connected layer, a softmax layer, and a classification output layer. The main purpose of using pre-trained CNN models is related to the fast and easy training of a CNN using randomly initialized weights [29], as well achievement of lower training error than ANNs that are not pre-trained [30].…”
Section: Data Trainingmentioning
confidence: 99%