Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Apr 25:10:885212.
doi: 10.3389/fpubh.2022.885212. eCollection 2022.

Multichannel DenseNet Architecture for Classification of Mammographic Breast Density for Breast Cancer Detection

Shivaji D Pawar  1   2 , Kamal K Sharma  3 , Suhas G Sapate  4 , Geetanjali Y Yadav  5 , Roobaea Alroobaea  6 , Sabah M Alzahrani  6 , Mustapha Hedabou  7
Affiliations

Multichannel DenseNet Architecture for Classification of Mammographic Breast Density for Breast Cancer Detection

Shivaji D Pawar et al. Front Public Health. .

Abstract

Percentage mammographic breast density (MBD) is one of the most notable biomarkers. It is assessed visually with the support of radiologists with the four qualitative Breast Imaging Reporting and Data System (BIRADS) categories. It is demanding for radiologists to differentiate between the two variably allocated BIRADS classes, namely, "BIRADS C and BIRADS D." Recently, convolution neural networks have been found superior in classification tasks due to their ability to extract local features with shared weight architecture and space invariance characteristics. The proposed study intends to examine an artificial intelligence (AI)-based MBD classifier toward developing a latent computer-assisted tool for radiologists to distinguish the BIRADS class in modern clinical progress. This article proposes a multichannel DenseNet architecture for MBD classification. The proposed architecture consists of four-channel DenseNet transfer learning architecture to extract significant features from a single patient's two a mediolateral oblique (MLO) and two craniocaudal (CC) views of digital mammograms. The performance of the proposed classifier is evaluated using 200 cases consisting of 800 digital mammograms of the different BIRADS density classes with validated density ground truth. The classifier's performance is assessed with quantitative metrics such as precision, responsiveness, specificity, and the area under the curve (AUC). The concluding preliminary outcomes reveal that this intended multichannel model has delivered good performance with an accuracy of 96.67% during training and 90.06% during testing and an average AUC of 0.9625. Obtained results are also validated qualitatively with the help of a radiologist expert in the field of MBD. Proposed architecture achieved state-of-the-art results with a fewer number of images and with less computation power.

Keywords: BIRADS Density Classification; DenseNet; breast cancer; deep learning; mammographic breast density; multichannel architecture.

PubMed Disclaimer

Conflict of interest statement

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Figures

Figure 1
Figure 1
The proposed multichannel architecture for mammographic breast density classification.
Figure 2
Figure 2
BIRADS classification-(A) fatty-class A (B) fat with some fibro glandular tissue -class B (C) heterogeneous dense-class C (D) extremely dense-class D (Image courtesy: Densebreast-info.org).
Figure 3
Figure 3
Input raw images- (A) Left_MLO (B) Left_CC (C) Right_MLO (D) Right_CC.
Figure 4
Figure 4
Output Images after segmentation and cropping - (A) Left_MLO (B) Left_CC (C) Right_MLO (D) Right_CC.
Figure 5
Figure 5
Contrast enhancement of input images.
Figure 6
Figure 6
Conversion of grayscale image appears as an RGB.
Figure 7
Figure 7
The proposed multichannel Dense-Net Framework for BIRADS classification.
Figure 8
Figure 8
The architecture of dense layer.
Figure 9
Figure 9
The distribution of image data.
Figure 10
Figure 10
Training phase performance of the model (A) model accuracy and (B) model loss.
Figure 11
Figure 11
Validation results of the proposed model in phase-II (A) model accuracy (B) model loss.
Figure 12
Figure 12
(A) The Heat map (B) and the ROC curve of the proposed model.
See this image and copyright information in PMC

References

    1. Advani P, Moreno-Aspitia A. Current strategies for the prevention of breast cancer. Breast Cancer Targets Therapy. (2014) 6:59–71. 10.2147/BCTT.S39114 - DOI - PMC - PubMed
    1. Kamangar F, Dores GM, Anderson WF. Patterns of cancer incidence, mortality, and prevalence across five continents: defining priorities to reduce cancer disparities in different geographic regions of the world. J Clin Oncol. (2006) 24:2137–50. 10.1200/JCO.2005.05.2308 - DOI - PubMed
    1. Sapate S, Talbar S, Mahajan A, Sable N, Desai S, Thakur M. Breast cancer diagnosis using abnormalities on ipsilateral views of digital mammograms. Biocybern Biomed Eng. (2020) 40:290–305. 10.1016/j.bbe.2019.04.008 - DOI
    1. Iwendi C, Bashir AK, Peshkar A, Sujatha R, Chatterjee J, Pasupulet S, et al. . COVID-19 patient health prediction using boosted random forest algorithm. Front Public Health. (2020). 8:218–25. 10.3389/fpubh.2020.00357 - DOI - PMC - PubMed
    1. Dhanamjayulu C, Nizhal U, Maddikunta P, Gadekallu T, Iwendi C, Wei C, et al. . Identification of malnutrition and prediction of BMI from facial images using real-time image processing and machine learning. IET Image Process. (2021) 16:647–58. 10.1049/ipr2.12222 - DOI