TY - JOUR
T1 - A model combining pretreatment MRI radiomic features and tumor-infiltrating lymphocytes to predict response to neoadjuvant systemic therapy in triple-negative breast cancer
AU - Jimenez, Jorge E.
AU - Abdelhafez, Abeer
AU - Mittendorf, Elizabeth A.
AU - Elshafeey, Nabil
AU - Yung, Joshua P.
AU - Litton, Jennifer K.
AU - Adrada, Beatriz E.
AU - Candelaria, Rosalind P.
AU - White, Jason
AU - Thompson, Alastair M.
AU - Huo, Lei
AU - Wei, Peng
AU - Tripathy, Debu
AU - Valero, Vicente
AU - Yam, Clinton
AU - Hazle, John D.
AU - Moulder, Stacy L.
AU - Yang, Wei T.
AU - Rauch, Gaiane M.
N1 - Publisher Copyright:
© 2022 Elsevier B.V.
PY - 2022/4
Y1 - 2022/4
N2 - Purpose: We aimed to develop a predictive model based on pretreatment MRI radiomic features (MRIRF) and tumor-infiltrating lymphocyte (TIL) levels, an established prognostic marker, to improve the accuracy of predicting pathologic complete response (pCR) to neoadjuvant systemic therapy (NAST) in triple-negative breast cancer (TNBC) patients. Methods: This Institutional Review Board (IRB) approved retrospective study included a preliminary set of 80 women with biopsy-proven TNBC who underwent NAST, pretreatment dynamic contrast enhanced MRI, and biopsy-based pathologic assessment of TIL. A threshold of ≥ 20% was used to define high TIL. Patients were classified into pCR and non-pCR based on pathologic evaluation of post-NAST surgical specimens. pCR was defined as the absence of invasive carcinoma in the surgical specimen. Segmentation and MRIRF extraction were done using a Food and Drug Administration (FDA) approved software QuantX. The top five features were combined into a single MRIRF signature value. Results: Of 145 extracted MRIRF, 38 were significantly correlated with pCR. Five nonredundant imaging features were identified: volume, uniformity, peak timepoint variance, homogeneity, and variance. The accuracy of the MRIRF model, P = .001, 72.7% positive predictive value (PPV), 72.0% negative predictive value (NPV), was similar to the TIL model (P = .038, 65.5% PPV, 72.6% NPV). When MRIRF and TIL models were combined, we observed improved prognostic accuracy (P < .001, 90.9% PPV, 81.4% NPV). The models area under the receiver operating characteristic curve (AUC) was 0.632 (TIL), 0.712 (MRIRF) and 0.752 (TIL + MRIRF). Conclusion: A predictive model combining pretreatment MRI radiomic features with TIL level on pretreatment core biopsy improved accuracy in predicting pCR to NAST in TNBC patients.
AB - Purpose: We aimed to develop a predictive model based on pretreatment MRI radiomic features (MRIRF) and tumor-infiltrating lymphocyte (TIL) levels, an established prognostic marker, to improve the accuracy of predicting pathologic complete response (pCR) to neoadjuvant systemic therapy (NAST) in triple-negative breast cancer (TNBC) patients. Methods: This Institutional Review Board (IRB) approved retrospective study included a preliminary set of 80 women with biopsy-proven TNBC who underwent NAST, pretreatment dynamic contrast enhanced MRI, and biopsy-based pathologic assessment of TIL. A threshold of ≥ 20% was used to define high TIL. Patients were classified into pCR and non-pCR based on pathologic evaluation of post-NAST surgical specimens. pCR was defined as the absence of invasive carcinoma in the surgical specimen. Segmentation and MRIRF extraction were done using a Food and Drug Administration (FDA) approved software QuantX. The top five features were combined into a single MRIRF signature value. Results: Of 145 extracted MRIRF, 38 were significantly correlated with pCR. Five nonredundant imaging features were identified: volume, uniformity, peak timepoint variance, homogeneity, and variance. The accuracy of the MRIRF model, P = .001, 72.7% positive predictive value (PPV), 72.0% negative predictive value (NPV), was similar to the TIL model (P = .038, 65.5% PPV, 72.6% NPV). When MRIRF and TIL models were combined, we observed improved prognostic accuracy (P < .001, 90.9% PPV, 81.4% NPV). The models area under the receiver operating characteristic curve (AUC) was 0.632 (TIL), 0.712 (MRIRF) and 0.752 (TIL + MRIRF). Conclusion: A predictive model combining pretreatment MRI radiomic features with TIL level on pretreatment core biopsy improved accuracy in predicting pCR to NAST in TNBC patients.
KW - Breast Cancer
KW - Breast MRI
KW - Neoadjuvant systemic therapy
KW - Radiomics
KW - TIL
UR - http://www.scopus.com/inward/record.url?scp=85124879127&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85124879127&partnerID=8YFLogxK
U2 - 10.1016/j.ejrad.2022.110220
DO - 10.1016/j.ejrad.2022.110220
M3 - Article
C2 - 35193025
AN - SCOPUS:85124879127
SN - 0720-048X
VL - 149
JO - European Journal of Radiology
JF - European Journal of Radiology
M1 - 110220
ER -