Diagnostic Value of Radiomics and Machine Learning with Dynamic Contrast-enhanced Magnetic Resonance Imaging for Patients with Atypical Ductal Hyperplasia in Predicting Malignant Upgrade

Overview

Journal Breast Cancer Res Treat

Specialty Oncology

Date 2021 Jan 20

PMID 33471237

Citations 4

Authors

Roberto Lo Gullo

Kerri Vincenti

Carolina Rossi Saccarelli

Peter Gibbs

Michael J Fox

Isaac Daimiel

Danny F Martinez

Maxine S Jochelson

Elizabeth A Morris

Jeffrey S Reiner

Katja Pinker

Affiliations

Soon will be listed here.

Abstract

Purpose: To investigate whether radiomics features extracted from magnetic resonance imaging (MRI) of patients with biopsy-proven atypical ductal hyperplasia (ADH) coupled with machine learning can differentiate high-risk lesions that will upgrade to malignancy at surgery from those that will not, and to determine if qualitatively and semi-quantitatively assessed imaging features, clinical factors, and image-guided biopsy technical factors are associated with upgrade rate.

Methods: This retrospective study included 127 patients with 139 breast lesions yielding ADH at biopsy who were assessed with multiparametric MRI prior to biopsy. Two radiologists assessed all lesions independently and with a third reader in consensus according to the BI-RADS lexicon. Univariate analysis and multivariate modeling were performed to identify significant radiomic features to be included in a machine learning model to discriminate between lesions that upgraded to malignancy on surgery from those that did not.

Results: Of 139 lesions, 28 were upgraded to malignancy at surgery, while 111 were not upgraded. Diagnostic accuracy was 53.6%, specificity 79.2%, and sensitivity 15.3% for the model developed from pre-contrast features, and 60.7%, 86%, and 22.8% for the model developed from delta radiomics datasets. No significant associations were found between any radiologist-assessed lesion parameters and upgrade status. There was a significant correlation between the number of specimens sampled during biopsy and upgrade status (p = 0.003).

Conclusion: Radiomics analysis coupled with machine learning did not predict upgrade status of ADH. The only significant result from this analysis is between the number of specimens sampled during biopsy procedure and upgrade status at surgery.

Citing Articles

Navigating the Uncertainty of B3 Breast Lesions: Diagnostic Challenges and Evolving Management Strategies.

DArchi S, Carnassale B, Sanchez A, Accetta C, Belli P, De Lauretis F J Pers Med. 2025; 15(1).

PMID: 39852228 PMC: 11766555. DOI: 10.3390/jpm15010036.

Assessing Malignant Risk in B3 Breast Lesions: Clinical Insights and Implications.

DArchi S, Carnassale B, Accetta C, Belli P, De Lauretis F, Di Guglielmo E J Clin Med. 2025; 14(1.

PMID: 39797153 PMC: 11721960. DOI: 10.3390/jcm14010070.

Third International Consensus Conference on lesions of uncertain malignant potential in the breast (B3 lesions).

Elfgen C, Leo C, Kubik-Huch R, Muenst S, Schmidt N, Quinn C Virchows Arch. 2023; 483(1):5-20.

PMID: 37330436 PMC: 10326140. DOI: 10.1007/s00428-023-03566-x.

Multiparametric F-FDG PET/MRI-Based Radiomics for Prediction of Pathological Complete Response to Neoadjuvant Chemotherapy in Breast Cancer.

Umutlu L, Kirchner J, Bruckmann N, Morawitz J, Antoch G, Ting S Cancers (Basel). 2022; 14(7).

PMID: 35406499 PMC: 8996836. DOI: 10.3390/cancers14071727.

AI-enhanced breast imaging: Where are we and where are we heading?.

Bitencourt A, Daimiel Naranjo I, Gullo R, Rossi Saccarelli C, Pinker K Eur J Radiol. 2021; 142:109882.

PMID: 34392105 PMC: 8387447. DOI: 10.1016/j.ejrad.2021.109882.

References

Kiluk J, Acs G, Hoover S . High-risk benign breast lesions: current strategies in management. Cancer Control. 2007; 14(4):321-9. DOI: 10.1177/107327480701400402. View

Gulla S, Lancaster R, De los Santos J . High-Risk Breast Lesions and Current Management. Semin Roentgenol. 2018; 53(4):252-260. DOI: 10.1053/j.ro.2018.08.001. View

Forester N, Lowes S, Mitchell E, Twiddy M . High risk (B3) breast lesions: What is the incidence of malignancy for individual lesion subtypes? A systematic review and meta-analysis. Eur J Surg Oncol. 2018; 45(4):519-527. DOI: 10.1016/j.ejso.2018.12.008. View

McGhan L, Pockaj B, Wasif N, Giurescu M, McCullough A, Gray R . Atypical ductal hyperplasia on core biopsy: an automatic trigger for excisional biopsy?. Ann Surg Oncol. 2012; 19(10):3264-9. DOI: 10.1245/s10434-012-2575-0. View

Margenthaler J, Duke D, Monsees B, Barton P, Clark C, Dietz J . Correlation between core biopsy and excisional biopsy in breast high-risk lesions. Am J Surg. 2006; 192(4):534-7. DOI: 10.1016/j.amjsurg.2006.06.003. View

Tsuchiya K, Mori N, Schacht D, Sheth D, Karczmar G, Newstead G . Value of breast MRI for patients with a biopsy showing atypical ductal hyperplasia (ADH). J Magn Reson Imaging. 2017; 46(6):1738-1747. PMC: 6587185. DOI: 10.1002/jmri.25694. View

Bedei L, Falcini F, Sanna P, Casadei Giunchi D, Innocenti M, Vignutelli P . Atypical ductal hyperplasia of the breast: the controversial management of a borderline lesion: experience of 47 cases diagnosed at vacuum-assisted biopsy. Breast. 2005; 15(2):196-202. DOI: 10.1016/j.breast.2005.05.008. View

Sinn H, Kreipe H . A Brief Overview of the WHO Classification of Breast Tumors, 4th Edition, Focusing on Issues and Updates from the 3rd Edition. Breast Care (Basel). 2014; 8(2):149-54. PMC: 3683948. DOI: 10.1159/000350774. View

West E, Mutasa S, Zhu Z, Ha R . Global Trend in Artificial Intelligence-Based Publications in Radiology From 2000 to 2018. AJR Am J Roentgenol. 2019; 213(6):1204-1206. DOI: 10.2214/AJR.19.21346. View

10.

Harrington L, diFlorio-Alexander R, Trinh K, MacKenzie T, Suriawinata A, Hassanpour S . Prediction of Atypical Ductal Hyperplasia Upgrades Through a Machine Learning Approach to Reduce Unnecessary Surgical Excisions. JCO Clin Cancer Inform. 2019; 2:1-11. PMC: 6874044. DOI: 10.1200/CCI.18.00083. View

11.

Deshaies I, Provencher L, Jacob S, Cote G, Robert J, Desbiens C . Factors associated with upgrading to malignancy at surgery of atypical ductal hyperplasia diagnosed on core biopsy. Breast. 2010; 20(1):50-5. DOI: 10.1016/j.breast.2010.06.004. View

12.

Bendifallah S, Defert S, Chabbert-Buffet N, Maurin N, Chopier J, Antoine M . Scoring to predict the possibility of upgrades to malignancy in atypical ductal hyperplasia diagnosed by an 11-gauge vacuum-assisted biopsy device: an external validation study. Eur J Cancer. 2011; 48(1):30-6. DOI: 10.1016/j.ejca.2011.08.011. View

13.

Ko E, Han W, Lee J, Cho J, Kim E, Jung S . Scoring system for predicting malignancy in patients diagnosed with atypical ductal hyperplasia at ultrasound-guided core needle biopsy. Breast Cancer Res Treat. 2007; 112(1):189-95. DOI: 10.1007/s10549-007-9824-0. View

14.

Racz J, Carter J, Degnim A . Lobular Neoplasia and Atypical Ductal Hyperplasia on Core Biopsy: Current Surgical Management Recommendations. Ann Surg Oncol. 2017; 24(10):2848-2854. DOI: 10.1245/s10434-017-5978-0. View

15.

Strigel R, Eby P, DeMartini W, Gutierrez R, Allison K, Peacock S . Frequency, upgrade rates, and characteristics of high-risk lesions initially identified with breast MRI. AJR Am J Roentgenol. 2010; 195(3):792-8. DOI: 10.2214/AJR.09.4081. View

16.

Liberman L, Holland A, Marjan D, Murray M, Bartella L, Morris E . Underestimation of atypical ductal hyperplasia at MRI-guided 9-gauge vacuum-assisted breast biopsy. AJR Am J Roentgenol. 2007; 188(3):684-90. DOI: 10.2214/AJR.06.0809. View

17.

Heller S, Elias K, Gupta A, Greenwood H, Mercado C, Moy L . Outcome of high-risk lesions at MRI-guided 9-gauge vacuum- assisted breast biopsy. AJR Am J Roentgenol. 2013; 202(1):237-45. DOI: 10.2214/AJR.13.10600. View

18.

Weinfurtner R, Patel B, Laronga C, Lee M, Falcon S, Mooney B . Magnetic resonance imaging-guided core needle breast biopsies resulting in high-risk histopathologic findings: upstage frequency and lesion characteristics. Clin Breast Cancer. 2015; 15(3):234-9. DOI: 10.1016/j.clbc.2014.12.005. View

19.

Mann R, Balleyguier C, Baltzer P, Bick U, Colin C, Cornford E . Breast MRI: EUSOBI recommendations for women's information. Eur Radiol. 2015; 25(12):3669-78. PMC: 4636525. DOI: 10.1007/s00330-015-3807-z. View

20.

Mann R, Kuhl C, Kinkel K, Boetes C . Breast MRI: guidelines from the European Society of Breast Imaging. Eur Radiol. 2008; 18(7):1307-18. PMC: 2441490. DOI: 10.1007/s00330-008-0863-7. View