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
. 2025 Feb 27;11(3):26.
doi: 10.3390/tomography11030026.

MRI-Based Model for Personalizing Neoadjuvant Treatment in Breast Cancer

Wen Li  1 , Natsuko Onishi  1 , Jessica E Gibbs  1 , Lisa J Wilmes  1 , Nu N Le  1 , Pouya Metanat  1 , Elissa R Price  1 , Bonnie N Joe  1 , John Kornak  2 , Christina Yau  3 , Denise M Wolf  4 , Mark Jesus M Magbanua  4 , Barbara LeStage  5 , Laura J van 't Veer  4 , Angela M DeMichele  6 , Laura J Esserman  3 , Nola M Hylton  1
Affiliations

MRI-Based Model for Personalizing Neoadjuvant Treatment in Breast Cancer

Wen Li et al. Tomography. .

Abstract

Background: Functional tumor volume (FTV), measured from dynamic contrast-enhanced MRI, is an imaging biomarker that can predict treatment response in breast cancer patients undergoing neoadjuvant chemotherapy (NAC). The FTV-based predictive model, combined with core biopsy, informed treatment decisions of recommending patients with excellent responses to proceed to surgery early in a large NAC clinical trial.

Methods: In this retrospective study, we constructed models using FTV measurements. We analyzed performance tradeoffs when a probability threshold was used to identify excellent responders through the prediction of pathology complete response (pCR). Individual models were developed within cohorts defined by the hormone receptor and human epidermal growth factor receptor 2 (HR/HER2) subtype.

Results: A total of 814 patients enrolled in the I-SPY 2 trial between 2010 and 2016 were included with a mean age of 49 years (range: 24 to 77). Among these patients, 289 (36%) achieved pCR. The area under the ROC curve (AUC) ranged from 0.68 to 0.74 for individual HR/HER2 subtypes. When probability thresholds were chosen based on minimum positive predictive value (PPV) levels of 50%, 70%, and 90%, the PPV-sensitivity tradeoff varied among subtypes. The highest sensitivities (100%, 87%, 45%) were found in the HR-/HER2+ sub-cohort for probability thresholds of 0, 0.62, and 0.72; followed by the triple-negative sub-cohort (98%, 52%, 4%) at thresholds of 0.13, 0.58, and 0.67; and HR+/HER2+ (78%, 16%, 8%) at thresholds of 0.34, 0.57, and 0.60. The lowest sensitivities (20%, 0%, 0%) occurred in the HR+/HER2- sub-cohort.

Conclusions: Predictive models developed using imaging biomarkers, alongside clinically validated probability thresholds, can be incorporated into decision-making for precision oncology.

Keywords: breast cancer; dynamic contrast-enhanced MRI; functional tumor volume; neoadjuvant chemotherapy; pathologic complete response; therapy decision.

PubMed Disclaimer

Conflict of interest statement

L.J.E. is on the Blue Cross Medical Advisory Panel, is an uncompensated board member of Quantum Leap Healthcare Collaborative, and is involved in an investigator-initiated trial for high-risk DCIS funded by Moderna for a phase 1 study of DCIS. C.Y. receives institutional research grants from NCI/NIH and salary support and travel reimbursement from Quantum Leap Healthcare Collaborative, has a US patent titled, “Breast cancer response prediction subtypes”, (No. 18/174,491), and received a University of California Inventor Share but declares no non-financial competing interests. L.J.v.’t.V. is a part-time employee of and has stock in Agendia NV and serves as an advisor and receives stock options from Exai, Inc., but declares no non-financial competing interests. A.M.D. receives institutional research funding from Novartis, Pfizer, Genentech, and Neogenomics, and serves as a Program Chair on the Scientific Advisory Committee of ASCO, but declares no non-financial competing interests. N.M.H. receives institutional research funding from NIH but declares no non-financial competing interests. All authors declare no conflicts of interest regarding this study.

Figures

Figure 1
Figure 1
Flowchart of data exclusion and inclusion. Patients with missing data and with poor quality MRIs were excluded from the analysis. HR: hormone receptor. HER2: human epidermal growth factor receptor 2. T0: pretreatment time point. T1: early treatment time point (approximately 3 weeks after the start of treatment. T2: inter-regimen (approximately 12 weeks after the start of treatment).
Figure 2
Figure 2
Plots of positive predictive value (PPV) and sensitivity versus predicted probability threshold. This plot was generated using the predictive model built in the full cohort and in hormone receptor (HR) and human epidermal growth factor receptor 2 (HER2) sub-cohorts: (a) Predicted probability was in the range of [0.00, 0.73], with corresponding ranges of [36%, 100%] and [100%, 2%] for PPV and sensitivity, respectively. (b) HR+/HER2−. The predicted probability was in the range of [0.00, 0.24], with corresponding ranges of [19%, 67%] and [100%, 3%] for PPV and sensitivity, respectively. (c) HR+/HER2+. The predicted probability was in the range of [0.03, 0.61], with corresponding ranges of [39%, 100%] and [100%, 2%] for PPV and sensitivity, respectively. (d) HR−/HER2+. The predicted probability was in the range of [0.03, 0.61], with corresponding ranges of [66%, 100%] and [100%, 11%] for PPV and sensitivity, respectively. (e) Triple negative. The predicted probability was in the range of [0.0002, 0.68], with corresponding ranges of [45%, 100%] and [100%, 1%] for PPV and sensitivity, respectively. In clinical application, a probability threshold was selected using a pre-specified PPV level, and the corresponding sensitivity can be used to evaluate the resulted PPV and sensitivity tradeoffs for the selected threshold.
Figure 3
Figure 3
An image example of HR+/HER2− breast cancer. Columns represent treatment time points: T0—pretreatment, T1—early treatment, T2—inter-regimen. Top row: maximum intensity projection (MIP) of subtraction between early enhancement (approximately 2 min and 30 s post-contrast injection) and pre-contrast. Bottom row: signal enhancement ratio (SER) map overlaying on an axial MR image. Functional tumor volume is calculated as the sum of voxels above preset percentage enhancement (PE) and SER thresholds of 70% and 0 within the rectangular bounding box (yellow box). The FTVs are 150 cc (cubic centimeter) at T0, 75 cc at T1, and 44 cc at T2.
Figure 4
Figure 4
An image example of the HR−/HER2+ breast cancer. Columns represent treatment time points: T0—pretreatment, T1—early treatment, T2—inter-regimen. Top row: maximum intensity projection (MIP) of subtraction between early enhancement (approximately 2 min and 30 s post-contrast injection) and pre-contrast. Bottom row: signal enhancement ratio (SER) map overlaying on an axial MR image. Functional tumor volume is calculated as the sum of voxels above preset percentage enhancement (PE) and SER thresholds of 70% and 0 within the rectangular bounding box (yellow box). The FTVs are 38 cc (cubic centimeter) at T0, 13 cc at T1, and 3 cc at T2.
See this image and copyright information in PMC

References

    1. Yee D., DeMichele A.M., Yau C., Isaacs C., Symmans W.F., Albain K.S., Chen Y.-Y., Krings G., Wei S., Harada S., et al. Association of Event-Free and Distant Recurrence-Free Survival with Individual-Level Pathologic Complete Response in Neoadjuvant Treatment of Stages 2 and 3 Breast Cancer: Three-Year Follow-up Analysis for the I-SPY2 Adaptively Randomized Clinical Trial. JAMA Oncol. 2020;6:1–9. doi: 10.1001/jamaoncol.2020.2535. - DOI - PMC - PubMed
    1. Spring L.M., Fell G., Arfe A., Sharma C., Greenup R., Reynolds K.L., Smith B.L., Alexander B., Moy B., Isakoff S.J., et al. Pathologic Complete Response after Neoadjuvant Chemotherapy and Impact on Breast Cancer Recurrence and Survival: A Comprehensive Meta-analysis. Clin. Cancer Res. 2020;26:2838–2848. doi: 10.1158/1078-0432.CCR-19-3492. - DOI - PMC - PubMed
    1. Marinovich M.L., Macaskill P., Irwig L., Sardanelli F., Mamounas E., von Minckwitz G., Guarneri V., Partridge S.C., Wright F.C., Choi J.H., et al. Agreement between MRI and pathologic breast tumor size after neoadjuvant chemotherapy, and comparison with alternative tests: Individual patient data meta-analysis. BMC Cancer. 2015;15:662. doi: 10.1186/s12885-015-1664-4. - DOI - PMC - PubMed
    1. Reig B., Lewin A.A., Du L., Heacock L., Toth H.K., Hetller S.L., Gao Y., Moy L. Breast MRI for Evaluation of Response to Neoadjuvant Therapy. RadioGraphics. 2021;41:665–679. doi: 10.1148/rg.2021200134. - DOI - PubMed
    1. Hylton N.M., Blume J.D., Bernreuter W.K., Pisano E.D., Rosen M.A., Morris E.A., Weatherall P.T., Lehman C.D., Newstead G.M., Polin S., et al. 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. doi: 10.1148/radiol.12110748. - DOI - PMC - PubMed

MeSH terms