.png){kind=icon}
返回
Convolutional Feature Descriptor Selection for Mammogram Classification
.png){kind=icon}
PRE
AI
DOI：10.1109/JBHI.2022.3233535.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Breast cancer was the most commonly diagnosed cancer among women worldwide in 2020. Recently, several deep learning-based classification approaches have been proposed to screen breast cancer in mammograms. However, most of these approaches require additional detection or segmentation annotations. Meanwhile, some other image-level label-based methods often pay insufficient attention to lesion areas, which are critical for diagnosis. This study designs a novel deep-learning method for automatically diagnosing breast cancer in mammography, which focuses on the local lesion areas and only utilizes image-level classification labels. In this study, we propose to select discriminative feature descriptors from feature maps instead of identifying lesion areas using precise annotations. And we design a novel adaptive convolutional feature descriptor selection (AFDS) structure based on the distribution of the deep activation map. Specifically, we adopt the triangle threshold strategy to calculate a specific threshold for guiding the activation map to determine which feature descriptors (local areas) are discriminative. Ablation experiments and visualization analysis indicate that the AFDS structure makes the model easier to learn the difference between malignant and benign/normal lesions. Furthermore, since the AFDS structure can be regarded as a highly efficient pooling structure, it can be easily plugged into most existing convolutional neural networks with negligible effort and time consumption. Experimental results on two publicly available INbreast and CBIS-DDSM datasets indicate that the proposed method performs satisfactorily compared with state-of-the-art methods.
Keyword:
Mammography
Lesions
Breast cancer
Feature extraction
Task analysis
Annotations
Image segmentation
Discriminative representation
feature descriptor
activation map
mammogram classification
期刊
IF:
6.8
论文数:
4.7K
被引数:
2.0W
机构
引用论文
分享收藏INbreast: Toward a Full-field Digital Mammographic Database乳房: 迈向全视野数字乳腺摄影数据库.png)
ACADEMIC RADIOLOGY
OAAI
ACADEMIC RADIOLOGYIF3.9
OAAI分享收藏分享收藏A METHOD OF COMPARING THE AREAS UNDER RECEIVER OPERATING CHARACTERISTIC CURVES DERIVED FROM THE SAME CASES一种比较相同情况下接收器工作特性曲线下面积的方法RADIOLOGY
RADIOLOGYIF15.2
PREAI
分享收藏The evolving epidemic of breast cancer in sub-Saharan Africa: Results from the African Cancer Registry Network撒哈拉以南非洲地区乳腺癌流行病的演变: 非洲癌症登记网络的结果OAAI
OAAI分享收藏
查看更多内容