2019
DOI: 10.1155/2019/2717454
|View full text |Cite
|
Sign up to set email alerts
|

Breast Microcalcification Diagnosis Using Deep Convolutional Neural Network from Digital Mammograms

Abstract: Mammography is successfully used as an effective screening tool for cancer diagnosis. A calcification cluster on mammography is a primary sign of cancer. Early researches have proved the diagnostic value of the calcification, yet their performance is highly dependent on handcrafted image descriptors. Characterizing the calcification mammography in an automatic and robust way remains a challenge. In this paper, the calcification was characterized by descriptors obtained from deep learning and handcrafted descri… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

1
59
0

Year Published

2019
2019
2023
2023

Publication Types

Select...
9
1

Relationship

0
10

Authors

Journals

citations
Cited by 112 publications
(60 citation statements)
references
References 36 publications
1
59
0
Order By: Relevance
“…In [6], micro-calcification in breast tissue was determined by using Deep Convolution Neural Network. They characterized microcalcifications by descriptors obtained from deep learning and handcrafted descriptors.…”
Section: Literature Reviewmentioning
confidence: 99%
“…In [6], micro-calcification in breast tissue was determined by using Deep Convolution Neural Network. They characterized microcalcifications by descriptors obtained from deep learning and handcrafted descriptors.…”
Section: Literature Reviewmentioning
confidence: 99%
“…A previous study has found that MC in malignant lesions tends to be smaller, more numerous, and occur in the milk ducts and other related structures in the breast and follow the anatomy of the duct. 3 There are several possible causes of calcification, including the development of scar tissue after biopsy or surgery, fluid accumulation, epithelial proliferation, tissue necrosis, and inflammation. Inflammation has been previously linked to poor breast cancer prognosis and disease progression, possibly due to the recruitment of macrophages that promote tumor growth and proteinases which decrease the extracellular matrix.…”
Section: Introductionmentioning
confidence: 99%
“…Jung et al [ 36 ] proposed a mass detection on mammograms based on a deep learning object detector called RetinaNet with good results. The method by Cai et al [ 37 ] is focused on the study of calcification clusters as early sign of cancer; they characterized calcification with descriptors obtained from deep learning and handcrafted descriptors. Richa et al [ 38 ] showed comparisons between different CNN architectures such as VGG16, ResNet50, and IcenptionV3 for the purpose of mass detection in mammograms.…”
Section: Introductionmentioning
confidence: 99%