A model combining pretreatment MRI radiomic features and tumor-infiltrating lymphocytes to predict response to neoadjuvant systemic therapy in triple-negative breast cancer

• Published in: European journal of radiology Vol. 149; p. 110220
• Main Authors: Jimenez, Jorge E., Abdelhafez, Abeer, Mittendorf, Elizabeth A., Elshafeey, Nabil, Yung, Joshua P., Litton, Jennifer K., Adrada, Beatriz E., Candelaria, Rosalind P., White, Jason, Thompson, Alastair M., Huo, Lei, Wei, Peng, Tripathy, Debu, Valero, Vicente, Yam, Clinton, Hazle, John D., Moulder, Stacy L., Yang, Wei T., Rauch, Gaiane M.
• Format: Journal Article
• Language: English
• Published: Ireland Elsevier B.V 01.04.2022
• Subjects: Breast Cancer; Breast MRI; Neoadjuvant systemic therapy; Radiomics; TIL; RF; TIL; Breast MRI; MRIRF; TNBC; Breast Cancer; Neoadjuvant systemic therapy; pCR; Radiomics
• ISSN: 0720-048X; 1872-7727; 1872-7727
• DOI: 10.1016/j.ejrad.2022.110220

•Pretreatment MRI radiomic features can predict treatment response in breast cancer.•Combined MRI radiomic and TIL model improves accuracy of response prediction.•Proposed “bio-radiomic” model could help to optimize management of breast cancer. 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. 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. 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). 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.