2018
DOI: 10.1016/j.cmpb.2017.11.019
|View full text |Cite
|
Sign up to set email alerts
|

A new near-term breast cancer risk prediction scheme based on the quantitative analysis of ipsilateral view mammograms

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
3
0

Year Published

2019
2019
2024
2024

Publication Types

Select...
5
1

Relationship

0
6

Authors

Journals

citations
Cited by 8 publications
(3 citation statements)
references
References 38 publications
0
3
0
Order By: Relevance
“…The study showed that increasing the number of filters in the convolutional layer can significantly improve microcalcification classification accuracy. Sun et al 26 developed and test a new near‐term breast cancer risk prediction scheme based on the quantitative analysis of the ipsilateral view of the negative screening mammograms. The results showed that the AUC of this model for breast cancer diagnosis is 0.737 ± 0.052, indicating that deep learning has great potential in developing a risk prediction model for early breast cancer.…”
Section: Discussionmentioning
confidence: 99%
“…The study showed that increasing the number of filters in the convolutional layer can significantly improve microcalcification classification accuracy. Sun et al 26 developed and test a new near‐term breast cancer risk prediction scheme based on the quantitative analysis of the ipsilateral view of the negative screening mammograms. The results showed that the AUC of this model for breast cancer diagnosis is 0.737 ± 0.052, indicating that deep learning has great potential in developing a risk prediction model for early breast cancer.…”
Section: Discussionmentioning
confidence: 99%
“…Moreover, it has been shown that there is no apparent increase in the risk of developing a contralateral B-cancer according to the histology of primary cancer [31,32]. A quantitative analysis of homolateral views of mammograms would provide useful information regarding B-cancer risk over the short term [16][17][18]. In France, since post-diagnostic follow-up is usually carried out outside the BCSP, this study cannot predict on the evolution of the radiological abnormality in the contralateral breast after B-cancer diagnosis.…”
Section: Discussionmentioning
confidence: 99%
“…Statistical modelling was already predicted the occurrence of B-cancer or its prognosis from previous radiological ndings. A few studies converged towards a positive association between the risk score calculated on previous mammograms and imagedetected B-cancer at screening mammograms [15][16][17][18]. In addition to the reduced sample size, these studies did not describe the B-cancer risk according to the nding age of each radiological abnormality.…”
Section: Introductionmentioning
confidence: 99%