Skip to main content

Advertisement

SpringerLink
Log in

Fully automatic classification of breast lesions on multi-parameter MRI using a radiomics model with minimal number of stable, interpretable features

  • Breast Radiology
  • Published:
La radiologia medica Aims and scope Submit manuscript

Abstract

Purpose

To build an automatic computer-aided diagnosis (CAD) pipeline based on multiparametric magnetic resonance imaging (mpMRI) and explore the role of different imaging features in the classification of breast cancer.

Materials and methods

A total of 222 histopathology-confirmed breast lesions, together with their BI-RADS scores, were included in the analysis. The cohort was randomly split into training (159) and test (63) cohorts, and another 50 lesions were collected as an external cohort. An nnUNet-based lesion segmentation model was trained to automatically segment lesion ROI, from which radiomics features were extracted for diffusion-weighted imaging (DWI), T2-weighted imaging (T2WI), and contrast-enhanced (DCE) pharmacokinetic parametric maps. Models based on combinations of sequences were built using support vector machine (SVM) and logistic regression (LR). Also, the performance of these sequence combinations and BI-RADS scores were compared. The Dice coefficient and AUC were calculated  to evaluate the segmentation and classification results. Decision curve analysis (DCA) was used to assess clinical utility.

Results

The segmentation model achieved a Dice coefficient of 0.831 in the test cohort. The radiomics model used only three features from diffusion coefficient (ADC) images, T2WI, and DCE-derived kinetic mapping, and achieved an AUC of 0.946 [0.883–0.990], AUC of 0.842 [0.6856–0.998] in the external cohort, which was higher than the BI-RADS score with an AUC of 0.872 [0.752–0.975]. The joint model using both radiomics score and BI-RADS score achieved the highest test AUC of 0.975 [0.935–1.000], with a sensitivity of 0.920 and a specificity of 0.923.

Conclusion

Three radiomics features can be used to construct an automatic radiomics-based pipeline to improve the diagnosis of breast lesions and reduce unnecessary biopsies, especially when using jointly with BI-RADS scores.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

Code availability

Software may be obtained from https://github.com/salan668/FAE.

Abbreviations

DCE:

Dynamic contrast-enhanced

DWI:

Diffusion-weighted imaging

T1WI:

T1-weighted imaging

T2WI:

T2-weighted imaging

ADC:

Apparent diffusion coefficient

BI-RADS:

Breast Imaging Reporting and Data System

T1Wpre :

T1WI before the contrast injection

T1Wpost90s :

T1WI scanned 90s after the contrast injection

T1WIpost5min :

T1WI scanned 5 min after the contrast injection

SER:

Early signal enhancement ratio

IH:

Intensity histogram features

GLCM:

Gray level co-occurrence matrices

LR:

Logistic regression

SVM:

Support vector machine

SEP:

Second enhancement percentage

SEN:

Sensitivity

SPE:

Specificity

ACC:

Accuracy

AUC:

Area under the ROC curve

95% CI:

95% confidence intervals

mpMRI:

multiparametric MRI

References

  1. Sung H, Ferlay J, Siegel RL et al (2021) Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin. https://doi.org/10.3322/caac.21660

    Article  PubMed  Google Scholar 

  2. Byers T, Wender RC, Jemal A et al (2016) The American Cancer Society challenge goal to reduce US cancer mortality by 50% between 1990 and 2015: Results and reflections. CA Cancer J Clin 66:359–369. https://doi.org/10.3322/caac.21348

    Article  PubMed  Google Scholar 

  3. Deike-Hofmann K, Koenig F, Paech D et al (2019) Abbreviated MRI protocols in breast cancer diagnostics. J Magn Reson Imaging 49:647–658. https://doi.org/10.1002/jmri.26525

    Article  PubMed  Google Scholar 

  4. Hooley RJ, Scoutt LM, Philpotts LE (2013) Breast ultrasonography: state of the art. Radiology 268:642–659. https://doi.org/10.1148/radiol.13121606

    Article  PubMed  Google Scholar 

  5. Sung JS, Stamler S, Brooks J et al (2016) Breast cancers detected at screening MR imaging and mammography in patients at high risk: method of detection reflects tumor histopathologic results. Radiology 280:716–722. https://doi.org/10.1148/radiol.2016151419

    Article  PubMed  Google Scholar 

  6. Mann RM, Cho N, Moy L (2019) Breast MRI: State of the art. Radiology 292:520–536. https://doi.org/10.1148/radiol.2019182947

    Article  PubMed  Google Scholar 

  7. Mann RM, Hooley R, Barr RG et al (2020) Novel approaches to screening for breast cancer. Radiology 297:266–285. https://doi.org/10.1148/radiol.2020200172

    Article  PubMed  Google Scholar 

  8. Morris EA, Comstock CE, Lee CH (2013) ACR BI-RADS® Atlas, breast imaging reporting and data system. ACR BI-RADS® Magnetic Resonance Imaging, 5th edn.

  9. Chan H-P, Samala RK, Hadjiiski LM (2020) CAD and AI for breast cancer—recent development and challenges. Br J Radiol 93:20190580. https://doi.org/10.1259/bjr.20190580

    Article  PubMed  Google Scholar 

  10. Gillies RJ, Kinahan PE, Hricak H (2016) Radiomics: images are more than pictures, they are data. Radiology 278:563–577. https://doi.org/10.1148/radiol.2015151169

    Article  PubMed  Google Scholar 

  11. Lambin P, Rios-Velazquez E, Leijenaar R et al (2012) Radiomics: extracting more information from medical images using advanced feature analysis. Eur J Cancer 48:441–446. https://doi.org/10.1016/j.ejca.2011.11.036

    Article  PubMed  PubMed Central  Google Scholar 

  12. Daimiel Naranjo I, Gibbs P, Reiner JS et al (2021) Radiomics and machine learning with multiparametric breast MRI for improved diagnostic accuracy in breast cancer diagnosis. Diagnostics (Basel). https://doi.org/10.3390/diagnostics11060919

    Article  PubMed  Google Scholar 

  13. Hao W, Gong J, Wang S et al (2020) Application of MRI Radiomics-Based Machine Learning Model to Improve Contralateral BI-RADS 4 Lesion Assessment. Front Oncol 10:531476. https://doi.org/10.3389/fonc.2020.531476

    Article  PubMed  PubMed Central  Google Scholar 

  14. Parekh VS, Jacobs MA (2017) Integrated radiomic framework for breast cancer and tumor biology using advanced machine learning and multiparametric MRI. NPJ Breast Cancer 3:43. https://doi.org/10.1038/s41523-017-0045-3

    Article  PubMed  PubMed Central  Google Scholar 

  15. Parekh VS, Jacobs MA (2020) Multiparametric radiomics methods for breast cancer tissue characterization using radiological imaging. Breast Cancer Res Treat 180:407–421. https://doi.org/10.1007/s10549-020-05533-5

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  16. Zhang Q, Peng Y, Liu W et al (2020) Radiomics based on multimodal MRI for the differential diagnosis of benign and malignant breast lesions. J Magn Reson Imaging 52:596–607. https://doi.org/10.1002/jmri.27098

    Article  PubMed  Google Scholar 

  17. Tsarouchi MI, Vlachopoulos GF, Karahaliou AN et al (2020) Multi-parametric MRI lesion heterogeneity biomarkers for breast cancer diagnosis. Phys Med 80:101–110. https://doi.org/10.1016/j.ejmp.2020.10.007

    Article  PubMed  Google Scholar 

  18. van Smeden M, de Groot JAH, Moons KGM et al (2016) No rationale for 1 variable per 10 events criterion for binary logistic regression analysis. BMC Med Res Methodol 16:163. https://doi.org/10.1186/s12874-016-0267-3

    Article  PubMed  PubMed Central  Google Scholar 

  19. Qiao M, Suo S, Cheng F et al (2021) Three-dimensional breast tumor segmentation on DCE-MRI with a multilabel attention-guided joint-phase-learning network. Comput Med Imaging Graph 90:101909. https://doi.org/10.1016/j.compmedimag.2021.101909

    Article  PubMed  Google Scholar 

  20. Isensee F, Jaeger PF, Kohl SAA et al (2021) nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat Methods 18:203–211. https://doi.org/10.1038/s41592-020-01008-z

    Article  CAS  PubMed  Google Scholar 

  21. Qiao M, Li C, Suo S et al (2020) Breast DCE-MRI radiomics: a robust computer-aided system based on reproducible BI-RADS features across the influence of datasets bias and segmentation methods. Int J Comput Assist Radiol Surg 15:921–930. https://doi.org/10.1007/s11548-020-02177-0

    Article  PubMed  Google Scholar 

  22. Jiang Z, Yin J (2020) Performance evaluation of texture analysis based on kinetic parametric maps from breast DCE-MRI in classifying benign from malignant lesions. J Surg Oncol 121:1181–1190. https://doi.org/10.1002/jso.25901

    Article  PubMed  Google Scholar 

  23. Mongan J, Moy L, Kahn CE (2020) Checklist for artificial intelligence in medical imaging (CLAIM): a guide for authors and reviewers. Radiology: Artificial Intelligence 2:e200029. https://doi.org/10.1148/ryai.2020200029

    PubMed  PubMed Central  Google Scholar 

  24. Collins GS, Reitsma JB, Altman DG et al (2015) Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement. BMJ 350:g7594. https://doi.org/10.1136/bmj.g7594

    Article  PubMed  Google Scholar 

  25. Lambin P, Leijenaar RTH, Deist TM et al (2017) Radiomics: the bridge between medical imaging and personalized medicine. Nat Rev Clin Oncol 14:749–762. https://doi.org/10.1038/nrclinonc.2017.141

    Article  PubMed  Google Scholar 

  26. Zwanenburg A, Vallieres M, Abdalah MA et al (2020) the image biomarker standardization initiative: standardized quantitative radiomics for high-throughput image-based phenotyping. Radiology 295:328–338. https://doi.org/10.1148/radiol.2020191145

    Article  PubMed  Google Scholar 

  27. Koo TK, Li MY (2016) A guideline of selecting and reporting intraclass correlation coefficients for reliability research. J Chiropr Med 15:155–163. https://doi.org/10.1016/j.jcm.2016.02.012

    Article  PubMed  PubMed Central  Google Scholar 

  28. Hastie T, Tibshirani R, Friedman JH (2009) The elements of statistical learning: Data mining, inference, and prediction, 2nd edn. Springer Series in Statistics. Springer, New York

    Book  Google Scholar 

  29. Song Y, Zhang J, Zhang YD et al (2020) FeAture Explorer (FAE): A tool for developing and comparing radiomics models. PLoS One 15:e0237587. https://doi.org/10.1371/journal.pone.0237587

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  30. Garreta R, Moncecchi G (2013) Learning scikit-learn: machine learning in Python, 1st edn. Community experience distilled. Packt Publishing, Birmingham

    Google Scholar 

  31. Pötsch N, Dietzel M, Kapetas P et al (2021) An A.I. classifier derived from 4D radiomics of dynamic contrast-enhanced breast MRI data: potential to avoid unnecessary breast biopsies. European Radiol. https://doi.org/10.1007/s00330-021-07787-z

    Article  Google Scholar 

  32. Ji Y, Li H, Edwards AV et al (2019) Independent validation of machine learning in diagnosing breast Cancer on magnetic resonance imaging within a single institution. Cancer Imaging 19:64. https://doi.org/10.1186/s40644-019-0252-2

    Article  PubMed  PubMed Central  Google Scholar 

  33. Shang S, Sun J, Yue Z et al (2021) Multi-parametric MRI based radiomics with tumor subregion partitioning for differentiating benign and malignant soft-tissue tumors. Biomed Signal Process Control 67:102522. https://doi.org/10.1016/j.bspc.2021.102522

    Article  Google Scholar 

  34. Zhou J, Zhang Y, Chang K-T et al (2020) Diagnosis of benign and malignant breast lesions on DCE-MRI by using radiomics and deep learning with consideration of peritumor tissue. J Magn Reson Imaging 51:798–809. https://doi.org/10.1002/jmri.26981

    Article  PubMed  Google Scholar 

  35. Jiang Z, Yin J (2020) Performance evaluation of texture analysis based on kinetic parametric maps from breast DCE-MRI in classifying benign from malignant lesions. J Surg Oncol. https://doi.org/10.1002/jso.25901

    Article  PubMed  Google Scholar 

  36. Karahaliou A, Vassiou K, Arikidis NS et al (2010) Assessing heterogeneity of lesion enhancement kinetics in dynamic contrast-enhanced MRI for breast cancer diagnosis. Br J Radiol 83:296–309. https://doi.org/10.1259/bjr/50743919

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  37. Jin G, An N, Jacobs MA et al (2010) The role of parallel diffusion-weighted imaging and apparent diffusion coefficient (ADC) map values for evaluating breast lesions: preliminary results. Acad Radiol 17:456–463. https://doi.org/10.1016/j.acra.2009.12.004

    Article  PubMed  PubMed Central  Google Scholar 

  38. Daimiel Naranjo I, Lo Gullo R, Saccarelli C et al (2021) Diagnostic value of diffusion-weighted imaging with synthetic b-values in breast tumors: comparison with dynamic contrast-enhanced and multiparametric MRI. Eur Radiol 31:356–367. https://doi.org/10.1007/s00330-020-07094-z

    Article  PubMed  Google Scholar 

  39. Yuen S, Uematsu T, Kasami M et al (2007) Breast carcinomas with strong high-signal intensity on T2-weighted MR images: pathological characteristics and differential diagnosis. J Magn Reson Imaging 25:502–510. https://doi.org/10.1002/jmri.20845

    Article  PubMed  Google Scholar 

  40. Lee H-J, Nguyen A-T, Ki SY et al (2021) Classification of MR-detected additional lesions in patients with breast cancer using a combination of radiomics analysis and machine learning. Front Oncol 11:744460. https://doi.org/10.3389/fonc.2021.744460

    Article  PubMed  PubMed Central  Google Scholar 

  41. Perre SV, Duron L, Milon A et al (2021) Radiomic analysis of HTR-DCE MR sequences improves diagnostic performance compared to BI-RADS analysis of breast MR lesions. Eur Radiol 31:4848–4859. https://doi.org/10.1007/s00330-020-07519-9

    Article  CAS  PubMed  Google Scholar 

Download references

Acknowledgements

We are very grateful for the external data support provided by Dr. Guoguang Wang.

Funding

This work was supported, in part, by the National Natural Science Grant number: 61731009 and Xing-Fu-Zhi-Hua Foundation of East China Normal University.

Author information

Author notes

  1. Jing Zhang and Chenao Zhan have contributed equally to this work.

Authors and Affiliations

  1. Shanghai Key Laboratory of Magnetic Resonance, East China Normal University, Shanghai, China

    Jing Zhang, Chenxiu Zhang & Guang Yang

  2. Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei, China

    Chenao Zhan & Tao Ai

  3. MR Scientific Marketing, Siemens Healthineers Ltd, Shanghai, China

    Yang Song & Xu Yan

  4. MR Collaboration, Siemens Healthineers Ltd, Guangzhou, China

    Yihao Guo

Authors
  1. Jing Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Chenao Zhan
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Chenxiu Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yang Song
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Xu Yan
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Yihao Guo
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Tao Ai
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Guang Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

JZ was involved in investigation, methodology, project administration, software, validation, visualization, and writing—original draft. CZ was involved in conceptualization, data curation, methodology, project administration, investigation, and writing—review & editing. CZ was involved in validation, visualization, and writing—review & editing. YS was involved in software, validation, visualization, and writing—review & editing. XY was involved in investigation, software, and writing—review & editing. YG and TA were involved writing—review & editing. GY was involved in investigation, project administration, supervision, funding acquisition, and writing—review & editing.

Corresponding author

Correspondence to Guang Yang.

Ethics declarations

Conflict of interest

The authors have no relevant financial or non-financial interests to disclose.

Consent to participate

All authors agreed with the content of the present paper and consent to submit.

Ethics approval

This retrospective study was approved by the Ethics Committee of Wuhan Tongji Hospital, and the study was conducted according to the guidelines of the Declaration of Helsinki.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (PDF 486 KB)

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zhang, J., Zhan, C., Zhang, C. et al. Fully automatic classification of breast lesions on multi-parameter MRI using a radiomics model with minimal number of stable, interpretable features. Radiol med 128, 160–170 (2023). https://doi.org/10.1007/s11547-023-01594-w

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11547-023-01594-w

Keywords

Search

Navigation