Early prediction of neoadjuvant treatment outcome in locally advanced breast cancer using parametric response mapping and radial heterogeneity from breast MRI

Abstract

Background: Early prediction of nonresponse is essential in order to avoid inefficient treatments. Purpose: To evaluate if parametrical response mapping (PRM)-derived biomarkers could predict early morphological response (EMR) and pathological complete response (pCR) 24-72 hours after initiation of chemotherapy treatment and whether concentric analysis of nonresponding PRM regions could better predict response. Study Type: This was a retrospective analysis of prospectively acquired cohort, nonrandomized, monocentric, diagnostic study. Population: Sixty patients were initially recruited, with 39 women participating in the final cohort. Field Strength/Sequence: A 1.5T scanner was used for MRI examinations. Assessment: Dynamic contrast-enhanced (DCE)-MR images were acquired at baseline (timepoint 1, TP1), 24-72 hours after the first chemotherapy (TP2), and after the end of anthracycline treatment (TP3). PRM was performed after fusion of T 1 subtraction images from TP1 and TP2 using an affine registration algorithm. Pixels with an increase of more than 10% of their value (PRMdce +) were corresponding nonresponding regions of the tumor. Patients with a decrease of maximum diameter (%dDmax) between TP1 and TP3 of more than 30% were defined as EMR responders. pCR patients achieved a residual cancer burden score of 0. Statistical Tests: T-test, receiver operating characteristic (ROC) curves, and logistic regression were used for the analysis. Results: PRM showed a statistical difference between pCR response groups (P < 0.01) and AUC of 0.88 for the prediction of non-pCR. Logistic regression analysis demonstrated that PRMdce+ and Grade II were significant (P < 0.01) for non-pCR prediction (AUC = 0.94). Peripheral tumor region demonstrated higher performance for the prediction of non-pCR (AUC = 0.85) than intermediate and central zones; however, statistical comparison showed no significant difference. Data Conclusion: PRM could be predictive of non-pCR 24-72 hours after initiation of chemotherapy treatment. Moreover, the peripheral region showed increased AUC for non-pCR prediction and increased signal intensity during treatment for non-pCR tumors, information that could be used for optimal tissue sampling. Level of Evidence: 1 Technical Efficacy Stage: 4

Four‐Dimensional Machine Learning Radiomics for the Pretreatment Assessment of Breast Cancer Pathologic Complete Response to Neoadjuvant Chemotherapy in Dynamic Contrast‐Enhanced MRI

“…spatial enhancement) or kinetics (i.e. temporal enhancement) from DCE‐MRI images 17–28 . This information was then used to develop machine learning (ML) models for NAC response prediction.…”

“…[17][18][19][20][21][22][23][24] To better account for tumor heterogeneity, a recognized challenge that may hinder treatment effectiveness, 9 a few investigators localized the extraction of kinetic features in different tumor subregions, to quantify differences in enhancement dynamics throughout the tumor environment. [25][26][27][28] Several authors performed classification experiments by stratifying per breast cancer molecular subtype. [17][18][19][20][21] Those studies thus uniformly show that both texture and dynamic features could be useful for NAC response prediction.…”

“…temporal enhancement) from DCE‐MRI images. 17 , 18 , 19 , 20 , 21 , 22 , 23 , 24 , 25 , 26 , 27 , 28 This information was then used to develop machine learning (ML) models for NAC response prediction. Most often, tumor (and, sometimes, peritumoral) texture are quantified from the first postcontrast image, or, in a few cases, independently for different temporal phases.…”

Quantitative Comparison of Prone and Supine PERCIST Measurements in Breast Cancer

“…Breast MRI is recommended for evaluation of disease extent in patients with biopsy-proven breast cancer just before surgery, and the utility of this modality to predict response to NAT is an active area of investigation (21)(22)(23)(24)(25)(26). By combining the molecular information of PET with the morphological and functional information provided by MRI, it is possible to provide a more comprehensive biological assessment of a lesion.…”

Mammographic and Ultrasonographic Imaging Analysis for Neoadjuvant Chemotherapy Evaluation: Volume Reduction Indexes That Correlate With Pathological Complete Response

“…Moreover, there is no standard method to monitor NAC response through imaging, especially using morphological analysis [ 17 ]. Even though, there are many advanced imaging parameters being tested especially with MRI [ 18 ], even if this is not a largely available imaging method in poorer populations, who have higher odds of mortality due to breast cancer [ 15 ].…”