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
. 2024 May 15:10:20552076241251660.
doi: 10.1177/20552076241251660. eCollection 2024 Jan-Dec.

Malignancy pattern analysis of breast ultrasound images using clinical features and a graph convolutional network

Sidratul Montaha  1 , Sami Azam  2 , Md Rahad Islam Bhuiyan  2 , Sadia Sultana Chowa  2 , Md Saddam Hossain Mukta  3 , Mirjam Jonkman  2
Affiliations

Malignancy pattern analysis of breast ultrasound images using clinical features and a graph convolutional network

Sidratul Montaha et al. Digit Health. .

Abstract

Objective: Early diagnosis of breast cancer can lead to effective treatment, possibly increase long-term survival rates, and improve quality of life. The objective of this study is to present an automated analysis and classification system for breast cancer using clinical markers such as tumor shape, orientation, margin, and surrounding tissue. The novelty and uniqueness of the study lie in the approach of considering medical features based on the diagnosis of radiologists.

Methods: Using clinical markers, a graph is generated where each feature is represented by a node, and the connection between them is represented by an edge which is derived through Pearson's correlation method. A graph convolutional network (GCN) model is proposed to classify breast tumors into benign and malignant, using the graph data. Several statistical tests are performed to assess the importance of the proposed features. The performance of the proposed GCN model is improved by experimenting with different layer configurations and hyper-parameter settings.

Results: Results show that the proposed model has a 98.73% test accuracy. The performance of the model is compared with a graph attention network, a one-dimensional convolutional neural network, and five transfer learning models, ten machine learning models, and three ensemble learning models. The performance of the model was further assessed with three supplementary breast cancer ultrasound image datasets, where the accuracies are 91.03%, 94.37%, and 89.62% for Dataset A, Dataset B, and Dataset C (combining Dataset A and Dataset B) respectively. Overfitting issues are assessed through k-fold cross-validation.

Conclusion: Several variants are utilized to present a more rigorous and fair evaluation of our work, especially the importance of extracting clinically relevant features. Moreover, a GCN model using graph data can be a promising solution for an automated feature-based breast image classification system.

Keywords: Breast ultrasound image; clinical features; ensemble learning; graph attention network; graph convolutional network.

PubMed Disclaimer

Conflict of interest statement

The authors declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.

Figures

Figure 1.
Figure 1.
Sample images of the dataset for class benign and malignant.
Figure 2.
Figure 2.
Methodology pipeline of the study.
Figure 3.
Figure 3.
Solidity of the tumor comparing the convex hull and tumor edge.
Figure 4.
Figure 4.
SIFT extreme points extraction from the tumor.
Figure 5.
Figure 5.
Deriving eclipse ratio of the tumor.
Figure 6.
Figure 6.
Deriving width/height ratio of the tumor.
Figure 7.
Figure 7.
Transition of tumor margin evaluation through deriving pixel brightness.
Figure 8.
Figure 8.
Visualization of ANOVA test results.
Figure 9.
Figure 9.
Feature impact analysis based on feature ranking using SVM.
Figure 10.
Figure 10.
Representation of the graphs with nodes, edges, and edge weights.
Figure 11.
Figure 11.
Representation of the FFN layer with optimized FFN layers and nine skip connections.
Figure 12.
Figure 12.
Proposed GCN architecture after ablation study.
Figure 13.
Figure 13.
Confusion metrics of the proposed GCN model.
Figure 14.
Figure 14.
Accuracy and loss curves of our proposed GCN model.
Figure 15.
Figure 15.
Performance of the model for 5-fold cross-validation.
Figure 16.
Figure 16.
Performance comparison of the GCN with transfer learning models.
See this image and copyright information in PMC

References

    1. Zhang S., Xie W., Li W., Wang L., Feng C., “GAMB-GNN: Graph Neural Networks learning from gene structure relations and Markov Blanket ranking for cancer classification in microarray data,” Chemometrics and Intelligent Laboratory Systems, vol. 232, Jan. 2023, doi: 10.1016/j.chemolab.2022.104713. - DOI
    1. Ragab D. A., Sharkas M., Marshall S., Ren J., “Breast cancer detection using deep convolutional neural networks and support vector machines,” PeerJ, vol. 2019, no. 1, 2019, doi: 10.7717/peerj.6201. - DOI - PMC - PubMed
    1. Gradishar W. J. et al., “Breast cancer, version 3.2020,” JNCCN Journal of the National Comprehensive Cancer Network, vol. 18, no. 4, pp. 452–478, Apr. 2020, doi: 10.6004/jnccn.2020.0016. - PubMed
    1. Myers E. R. et al., “Benefits and harms of breast cancer screening: A systematic review,” JAMA - Journal of the American Medical Association, vol. 314, no. 15. American Medical Association, pp. 1615–1634, Oct. 20, 2015. doi: 10.1001/jama.2015.13183. - PubMed
    1. Brinati D., Campagner A., Ferrari D., Locatelli M., Banfi G., Cabitza F., “Detection of COVID-19 Infection from Routine Blood Exams with Machine Learning: A Feasibility Study,” J Med Syst, vol. 44, no. 8, Aug. 2020, doi: 10.1007/s10916-020-01597-4. - DOI - PMC - PubMed

LinkOut - more resources