A Deep Learning-Based Approach for Breast BI-RADS Prediction on Shear Wave Elastography Images

How to Cite:Shabanzadeh A, Moradi S, Gity P(, Ghelich Oghli M. A Deep Learning-Based Approach for Breast BI-RADS Prediction on Shear Wave Elastography Images. I J Radiol. 2019;16(Special Issue):e99141. doi: https://doi.org/10.5812/iranjradiol.99141

Abstract

Background:

Breast cancer is the most common type of cancer among women. About one of every eight women is diagnosed with breast cancer during her lifetime. Malignant tissue is stiffer than normal and benign tissues. This stiffness could be evaluated by elastography. The American College of Radiology (ACR) has published a quality assurance tool named Breast Imaging-Reporting and Data System (BI-RADS) to standardize breast cancer reporting. Although it was originally designed to use with mammography, it now contains several features for various imaging modalities. Among technologies, shear wave elastography (SWE) has shown promising results in breast lesion classification.

Objectives:

In this paper, we present the capability of the convolutional neural network in the prediction of B-RADS using SWE images.

Methods:

A comprehensive dataset of SWE images of breast tissue was provided using Esaote MyLab^™ 9 and Aupersonic Aixplorer systems. Two hundred images related to breasts with different BI-RADS stages were gathered from the Cancer Institute, Imam Khomeini Medical Center (UICC). The data augmentation with a factor of 10 was applied to the prepared dataset. Some patients had multiple lesions and for each lesion, one or two images were acquired and stored in DICOM standards. The gold standard for the evaluation of the proposed algorithm was a biopsy, which was performed on all the examined lesions. A novel convolutional neural network was applied to the dataset to extract the visual features of images. The architecture was based on Densenet architecture, which was modified for our purpose. We used the network in both pre-training and end-to-end training strategies and the results were compared. The network was pre-trained on the Imagenet dataset due to the lack of a sufficient dataset. On the other hand, with data augmentation, the network underwent a full training strategy. Finally, the classification layer was a softmax layer, which was used to decide on the benignity or malignancy of the lump. The training and testing procedures for tumor classiﬁcation were employed with ﬁve-fold cross-validation. The entire dataset was randomly divided into ﬁve equal-sized subsets on the premise that multiple images acquired from the same patient were assigned to the same subset. Four subsets together were used for training and the remaining one for testing and this process was repeated ﬁve times such that each subset was used once as the test set.

Results:

The processing hardware had a 12 GB RAM, a GPU-based graphics card with 2496 CUDA cores (Tesla K80), and an Intel Xeon CPU. The network implementation was done in the Python environment with Tensorflow r1.12 and Keras 2.2.4. The results of the proposed methods were satisfying in both pre-training and end-to-end training approaches. We used various evaluation metrics including precision, recall, F1-score, ROC curve, and training time for both strategies. The precision, recall, and F1-score were 0.93, 0.95, and 0.94 for the Densenet architecture trained from scratch and 0.97, 0.94, and 0.95 for the transfer learning approach (see Table 1). The ROC curve was plotted for both approaches and the area under the curves (AUCs) were calculated. The transfer learning approach yielded an AUC of 0.98, whereas this parameter was 0.94 for the fully-trained approach (see Figure 1). Finally, the training time of transfer learning approach was one-fifth the time of training from scratch, as it was anticipated.

Conclusion:

The results showed the superiority of the transfer learning approach in tumor classification. Higher statistical metrics with lower training time makes this approach more compatible with SWE images.

To see figure and table please refer to the PDF file.

Clinical Application of Shear Wave Elastography in Breast Masses

Jin Young Chang,

Jin Hee Moon,

Sung Hye Koh,

Sun-Young Park,

Kwan Seop Lee

Chang JY, Moon JH, Hye Koh S, Park S, Seop Lee K. Clinical Application of Shear Wave Elastography in Breast Masses. I J Radiol. 2017;14(1):e13486. doi: https://doi.org/10.5812/iranjradiol.39585

Oct

2018

Comparison of the Diagnostic Performance of Breast Ultrasound and CAD Using BI-RADS Descriptors and Quantitative Variables

Yumi Kim,

Bong Joo Kang,

Jung Min Lee,

Sung Hun Kim

Kim Y, Kang BJ, Lee JM, Kim SH. Comparison of the Diagnostic Performance of Breast Ultrasound and CAD Using BI-RADS Descriptors and Quantitative Variables. I J Radiol. 2019;16(1):e67729. doi: https://doi.org/10.5812/iranjradiol.67729

Jul

2015

Ensemble Supervised Classification Method Using the Regions of Interest and Grey Level Co-Occurrence Matrices Features for Mammograms Data

Hossein Yousefibanaem,

Alireza Mehri Dehnavi,

Makhtum Shahnazi

Yousefibanaem H, Mehri Dehnavi A, Shahnazi M. Ensemble Supervised Classification Method Using the Regions of Interest and Grey Level Co-Occurrence Matrices Features for Mammograms Data. I J Radiol. 2015;12(3):e91069. doi: https://doi.org/10.5812/iranjradiol.11656

Aug

2013

Interobserver and Intraobserver Agreement of Sonographic BIRADS Lexicon in the Assessment of Breast Masses

Eda Elverici,

Betul Zengin,

Ayse Nurdan Barca,

Pinar Didem Yilmaz,

Aysegul Alimli,

Levent Araz

Elverici E, Zengin B, Nurdan Barca A, Didem Yilmaz P, Alimli A, et al. Interobserver and Intraobserver Agreement of Sonographic BIRADS Lexicon in the Assessment of Breast Masses. I J Radiol. 2013;10(3):122-127. doi: https://doi.org/10.5812/iranjradiol.10708

Apr

2022

Comparing Data Mining Algorithms for Breast Cancer Diagnosis

Mostafa Shanbehzadeh,

Raoof Nopour,

Leila Erfannia,

Morteza Amraei,

Nahid Mehrabi,

Mehrnaz Mashoufi

Shanbehzadeh M, Nopour R, Erfannia L, Amraei M, Mehrabi N, et al. Comparing Data Mining Algorithms for Breast Cancer Diagnosis. Shiraz E-Med J. 2022;23(7):e120140. doi: https://doi.org/10.5812/semj-120140

Import into EndNote Import into BibTex

Crossmark

Checking

Share on

Comments

Number of Comments:0

Cited by

Scopus by DOI: 0
Last Update: 3 weeks ago
Scopus by Title: 0
Last Update: 3 weeks ago
Scopus by Title (Ref): 0
Last Update: 3 weeks ago
CrossRef: 0
Last Update: 3 days ago

Metrics

Licensing and reuse information

Ordering Reprints

Articles are published under the Creative Commons license stated on each article. No permission or royalty fee is required for uses permitted by that license. CCC handles optional bulk and customized reprint orders. Any quotation covers production and delivery services only, not copyright permission. > Request Reprints from CCC

Search Relations

Author(s):

Ali Shabanzadeh:[PubMed][Scholar]
Shakiba Moradi:[PubMed][Scholar]
Parvaneh (Masoumeh) Gity:[PubMed][Scholar]
Mostafa Ghelich Oghli:[PubMed][Scholar]

An Innovative Journal in the Field of Radiology

Outlines

A Deep Learning-Based Approach for Breast BI-RADS Prediction on Shear Wave Elastography Images

Abstract

Background:

Objectives:

Methods:

Results:

Conclusion:

Similar Articles

Clinical Application of Shear Wave Elastography in Breast Masses

Comparison of the Diagnostic Performance of Breast Ultrasound and CAD Using BI-RADS Descriptors and Quantitative Variables

Ensemble Supervised Classification Method Using the Regions of Interest and Grey Level Co-Occurrence Matrices Features for Mammograms Data

Interobserver and Intraobserver Agreement of Sonographic BIRADS Lexicon in the Assessment of Breast Masses

Comparing Data Mining Algorithms for Breast Cancer Diagnosis

Crossmark

Checking

Last Update: 3 weeks ago

Last Update: 3 weeks ago

Last Update: 3 weeks ago

Last Update: 3 days ago