Rationale and Objectives
To evaluate a weakly supervised deep learning approach to breast Magnetic Resonance
Imaging (MRI) assessment without pixel level segmentation in order to improve the
specificity of breast MRI lesion classification.
Materials and Methods
In this IRB approved study, the dataset consisted of 278,685 image slices from 438
patients. The weakly supervised network was based on the Resnet-101 architecture.
Training was implemented using the Adam optimizer and a final SoftMax score threshold
of 0.5 was used for two class classification (malignant or benign). 278,685 image
slices were combined into 92,895 3-channel images. 79,871 (85%) images were used for
training and validation while 13,024 (15%) images were separated for testing. Of the
testing dataset, 11,498 (88%) were benign and 1531 (12%) were malignant. Model performance
was assessed.
Results
The weakly supervised network achieved an AUC of 0.92 (SD ± 0.03) in distinguishing
malignant from benign images. The model had an accuracy of 94.2% (SD ± 3.4) with a
sensitivity and specificity of 74.4% (SD ± 8.5) and 95.3% (SD ± 3.3) respectively.
Conclusion
It is feasible to use a weakly supervised deep learning approach to assess breast
MRI images without the need for pixel-by-pixel segmentation yielding a high degree
of specificity in lesion classification.
Key Words
To read this article in full you will need to make a payment
Purchase one-time access:
Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online accessOne-time access price info
- For academic or personal research use, select 'Academic and Personal'
- For corporate R&D use, select 'Corporate R&D Professionals'
Subscribe:
Subscribe to Academic RadiologyAlready a print subscriber? Claim online access
Already an online subscriber? Sign in
Register: Create an account
Institutional Access: Sign in to ScienceDirect
References
- Breast cancer statistics, 2017, racial disparity in mortality by state.CA Cancer J Clin. 2017; 67: 439-448
- Dynamic Breast MR Imaging: are signal intensity time course data useful for differential diagnosis of enhancing lesions?.Radiology. 1999; 211: 101-110
- Outcomes of screening mammography by frequency, breast density, and postmenopausal hormone therapy.JAMA Intern Med. 2013; 173: 807
- Individual and combined effects of age, breast density, and hormone replacement therapy use on the accuracy of screening mammography.Ann Intern Med. 2003; 138: 168
- Radiomic versus convolutional neural networks analysis for classification of contrast-enhancing lesions at multiparametric breast mri.Radiology. 2019; 290: 290-297
- Computer-aided diagnosis in breast DCE-MRI—Quantification of the heterogeneity of breast lesions.Eur J Radiol. 2012; 81: 1532-1538
- Supplemental MRI screening for women with extremely dense breast tissue.N Engl J Med. 2019; 381: 2091-2102
- Comparison of Abbreviated Breast MRI vs. Digital Breast Tomosynthesis for Breast Cancer Detection Among Women With Dense Breasts Undergoing Screening.JAMA. 2020; 323: 746
- Contrast-enhanced MRI of the breast: accuracy, value, controversies, solutions.Eur J Radiol. 1997; 24: 94-108
- Background parenchymal enhancement at breast MR imaging: normal patterns, diagnostic challenges, and potential for false-positive and false-negative interpretation.Radiographics. 2014; 34: 234-247
- Clinical-grade computational pathology using weakly supervised deep learning on whole slide images.Nat Med. 2019; 25: 1301-1309
- Breast Magnetic Resonance Imaging.Radiol Clin N. 2014; 52: 585-589
- Artificial Intelligence for Breast MRI in 2008–2018: A Systematic Mapping Review.Am J Roentgenol. 2019; 212: 280-292
- Risk factors for axillary lymph node metastases in clinical stage T1-2N0M0 breast cancer patients.Medicine (Baltimore). 2019; 98: e17481
- Axillary lymph node evaluation utilizing convolutional neural networks using mri dataset.J Digit Imaging. 2018; 31: 851-856
- Locally Advanced Breast Cancer: MR imaging for prediction of response to neoadjuvant chemotherapy—results from ACRIN 6657/I-SPY TRIAL.Radiology. 2012; 263: 663-672
- Weakly supervised 3D deep learning for breast cancer classification and localization of the lesions in MR images.J Magn Reson Imaging. 2019; 50: 1144-1151
- Design characteristics of studies reporting the performance of artificial intelligence algorithms for diagnostic analysis of medical images: results from recently published papers.Korean J Radiol. 2019; 20: 405
- Detection of breast cancer with addition of annual screening ultrasound or a single screening mri to mammography in women with elevated breast cancer risk.JAMA. 2012; 307: 1394
Article info
Publication history
Published online: June 06, 2021
Accepted:
March 31,
2021
Received in revised form:
March 29,
2021
Received:
October 20,
2020
Footnotes
Work originated from Columbia University Medical Center. No disclosures. No conflict of interest.
Identification
Copyright
© 2021 The Association of University Radiologists. Published by Elsevier Inc. All rights reserved.
