Kenneth G. A. Gilhuijs

Objectives: This study aimed to evaluate the potential additional value of deep radiomics for assessing residual cancer burden (RCB) in locally advanced breast cancer, after neoadjuvant chemotherapy (NAC) but before surgery, compared to standard predictors: tumor volume and subtype. Materials and methods: This retrospective study used a 105-patient single-institution training set and a 41-patient external test set from three institutions in the LIMA trial. DCE-MRI was performed before and after NAC, and RCB was determined post-surgery. Three networks (nnU-Net, Attention U-net and vector-quantized encoder-decoder) were trained for tumor segmentation. For each network, deep features were extracted from the bottleneck layer and used to train random forest regression models to predict RCB score. Models were compared to (1) a model trained on tumor volume and (2) a model combining tumor volume and subtype. The potential complementary performance of combining deep radiomics with a clinical-radiological model was assessed. From the predicted RCB score, three metrics were calculated: area under the curve (AUC) for categories RCB-0/RCB-I versus RCB-II/III, pathological complete response (pCR) versus non-pCR, and Spearman’s correlation. Results: Deep radiomics models had an AUC between 0.68–0.74 for pCR and 0.68–0.79 for RCB, while the volume-only model had an AUC of 0.74 and 0.70 for pCR and RCB, respectively. Spearman’s correlation varied from 0.45–0.51 (deep radiomics) to 0.53 (combined model). No statistical difference between models was observed. Conclusions: Segmentation network-derived deep radiomics contain similar information to tumor volume and subtype for inferring pCR and RCB after NAC, but do not complement standard clinical predictors in the LIMA trial. Key Points: Question It is unknown if and which deep radiomics approach is most suitable to extract relevant features to assess neoadjuvant chemotherapy response on breast MRI . Findings Radiomic features extracted from deep-learning networks yield similar results in predicting neoadjuvant chemotherapy response as tumor volume and subtype in the LIMA study. However, they do not provide complementary information . Clinical relevance For predicting response to neoadjuvant chemotherapy in breast cancer patients, tumor volume on MRI and subtype remain important predictors of treatment outcome; deep radiomics might be an alternative when determining tumor volume and/or subtype is not feasible . Graphical

Purpose: In this study, we aimed to explore if the combination of tumor infiltrating lymphocytes (TILs) and change in tumor load on dynamic contrast-enhanced magnetic resonance imaging leads to better assessment of response to neoadjuvant chemotherapy (NAC) in patients with breast cancer, compared to either alone. Methods: In 190 NAC treated patients, MRI scans were performed before and at the end of treatment. The percentage of stromal TILs (%TILs) was assessed in pre-NAC biopsies according to established criteria. Prediction models were developed with linear regression by least absolute shrinkage and selection operator and cross validation (CV), with residual cancer burden as the dependent variable. Discrimination for pathological complete response (pCR) was evaluated using area under the receiver operating characteristic curves (AUC). We used Cox regression analysis for exploring the association between %TILs and recurrence-free survival (RFS). Results: Fifty-one patients reached pCR. In all patients, the %TILs model and change in MRI tumor load model had an estimated CV AUC of 0.69 (95% confidence interval (CI) 0.53–0.78) and 0.69 (95% CI 0.61–0.79), respectively, whereas a model combining the variables resulted in an estimated CV AUC of 0.75 (95% CI 0.66–0.83). In the group with tumors that were ER positive and HER2 negative (ER+/HER2−) and in the group with tumors that were either triple negative or HER2 positive (TN&HER2+) separately, the combined model reached an estimated CV AUC of 0.72 (95% CI 0.60–0.88) and 0.70(95% CI 0.59–0.82), respectively. A significant association was observed between pre-treatment %TILS and RFS (hazard ratio (HR) 0.72 (95% CI 0.53–0.98), for every standard deviation increase in %TILS, p = 0.038). Conclusion: The combination of TILs and MRI is informative of response to NAC in patients with both ER+/HER2− and TN&HER2+ tumors.

Accurate prediction of response to neoadjuvant chemotherapy (NAC) can help tailor treatment to individual patients’ needs. Little is known about the combination of liquid biopsies and computer extracted features from multiparametric magnetic resonance imaging (MRI) for the prediction of NAC response in breast cancer. Here, we report on a prospective study with the aim to explore the predictive potential of this combination in adjunct to standard clinical and pathological information before, during and after NAC. The study was performed in four Dutch hospitals. Patients without metastases treated with NAC underwent 3 T multiparametric MRI scans before, during and after NAC. Liquid biopsies were obtained before every chemotherapy cycle and before surgery. Prediction models were developed using penalized linear regression to forecast residual cancer burden after NAC and evaluated for pathologic complete response (pCR) using leave-one-out-cross-validation (LOOCV). Sixty-one patients were included. Twenty-three patients (38%) achieved pCR. Most prediction models yielded the highest estimated LOOCV area under the curve (AUC) at the post-treatment timepoint. A clinical-only model including tumor grade, nodal status and receptor subtype yielded an estimated LOOCV AUC for pCR of 0.76, which increased to 0.82 by incorporating post-treatment radiological MRI assessment (i.e., the “clinical-radiological” model). The estimated LOOCV AUC was 0.84 after incorporation of computer-extracted MRI features, and 0.85 when liquid biopsy information was added instead of the radiological MRI assessment. Adding liquid biopsy information to the clinical-radiological resulted in an estimated LOOCV AUC of 0.86. In conclusion, inclusion of liquid biopsy-derived markers in clinical-radiological prediction models may have potential to improve prediction of pCR after NAC in breast cancer.

Background Automated identification of quantitative breast parenchymal enhancement features on dynamic contrast-enhanced (DCE) MRI scans could provide added value in assessment of breast cancer risk in women with extremely dense breasts. Purpose To automatically identify quantitative properties of the breast parenchyma on baseline DCE MRI scans and assess their association with breast cancer occurrence in women with extremely dense breasts. Materials and Methods This study represents a secondary analysis of the Dense Tissue and Early Breast Neoplasm Screening trial. MRI was performed in eight hospitals between December 2011 and January 2016. After segmentation of fibroglandular tissue, quantitative features (including volumetric density, volumetric morphology, and enhancement characteristics) of the parenchyma were extracted from baseline MRI scans. Principal component analysis was used to identify parenchymal measures with the greatest variance. Multivariable Cox proportional hazards regression was applied to assess the association between breast cancer occurrence and quantitative parenchymal features, followed by stratification of significant features into tertiles. Results A total of 4553 women (mean age, 55.7 years ± 6 [SD]) with extremely dense breasts were included; of these women, 122 (3%) were diagnosed with breast cancer. Five principal components representing 96% of the variance were identified, and the component explaining the greatest independent variance (42%) consisted of MRI features relating to volume of enhancing parenchyma. Multivariable analysis showed that volume of enhancing parenchyma was associated with breast cancer occurrence (hazard ratio [HR], 1.09; 95% CI: 1.01, 1.18; P = .02). Additionally, women in the high tertile of volume of enhancing parenchyma showed a breast cancer occurrence twice that of women in the low tertile (HR, 2.09; 95% CI: 1.25, 3.61; P = .005). Conclusion In women with extremely dense breasts, a high volume of enhancing parenchyma on baseline DCE MRI scans was associated with increased occurrence of breast cancer as compared with a low volume of enhancing parenchyma. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Grimm in this issue.

Background: While several methods have been proposed for automated assessment of breast‐cancer response to neoadjuvant chemotherapy on breast MRI, limited information is available about their performance across multiple institutions.Purpose: To assess the value and robustness of deep learning‐derived volumes of locally advanced breast cancer (LABC) on MRI to infer the presence of residual disease after neoadjuvant chemotherapy.Study Type: Retrospective.Subjects: Training cohort: 102 consecutive female patients with LABC scheduled for neoadjuvant chemotherapy (NAC) from a single institution (age: 25–73 years). Independent testing cohort: 55 consecutive female patients with LABC from four institutions (age: 25–72 years).Field Strength/Sequence: Training cohort: single vendor 1.5 T or 3.0 T. Testing cohort: multivendor 3.0 T. Gradient echo dynamic contrast‐enhanced sequences.Assessment: A convolutional neural network (nnU‐Net) was trained to segment LABC. Based on resulting tumor volumes, an extremely randomized tree model was trained to assess residual cancer burden (RCB)‐0/I vs. RCB‐II/III. An independent model was developed using functional tumor volume (FTV). Models were tested on an independent testing cohort and response assessment performance and robustness across multiple institutions were assessed.Statistical Tests: The receiver operating characteristic (ROC) was used to calculate the area under the ROC curve (AUC). DeLong's method was used to compare AUCs. Correlations were calculated using Pearson's method. P values R = 0.95, P < 0.05). Automated volumetric measurements were significantly correlated with FTV (R = 0.80). Tumor volume‐derived from deep learning of DCE‐MRI was associated with RCB, yielding an AUC of 0.76 to discriminate between RCB‐0/I and RCB‐II/III, performing similar to the FTV‐based model (AUC = 0.77, P = 0.66). Performance was comparable across institutions (IQR AUC: 0.71–0.84).Data Conclusion: Deep learning‐based segmentation estimates changes in tumor load on DCE‐MRI that are associated with RCB after NAC and is robust against variations between institutions.Evidence Level: 2.Technical Efficacy: Stage 4.

Objectives: Computer-aided triaging (CAT) and computer-aided diagnosis (CAD) of screening breast magnetic resonance imaging have shown potential to reduce the workload of radiologists in the context of dismissing normal breast scans and dismissing benign disease in women with extremely dense breasts. The aim of this study was to validate the potential of integrating CAT and CAD to reduce workload and workup on benign lesions in the second screening round of the DENSE trial, without missing cancer. Methods: We included 2901 breast magnetic resonance imaging scans, obtained from 8 hospitals in the Netherlands. Computer-aided triaging and CAD were previously developed on data from the first screening round. Computer-aided triaging dismissed examinations without lesions. Magnetic resonance imaging examinations triaged to radiological reading were counted and subsequently processed by CAD. The number of benign lesions correctly classified by CAD was recorded. The false-positive fraction of the CAD was compared with that of unassisted radiological reading in the second screening round. Receiver operating characteristics (ROC) analysis was performed and the generalizability of CAT and CAD was assessed by comparing results from first and second screening rounds. Results: Computer-aided triaging dismissed 950 of 2901 (32.7%) examinations with 49 lesions in total; none were malignant. Subsequent CAD classified 132 of 285 (46.3%) lesions as benign without misclassifying any malignant lesion. Together, CAT and CAD yielded significantly fewer false-positive lesions, 53 of 109 (48.6%) and 89 of 109 (78.9%), respectively (P = 0.001), than radiological reading alone. Computer-aided triaging had a smaller area under the ROC curve in the second screening round compared with the first, 0.83 versus 0.76 (P = 0.001), but this did not affect the negative predictive value at the 100% sensitivity operating threshold. Computer-aided diagnosis was not associated with significant differences in area under the ROC curve (0.857 vs 0.753, P = 0.08). At the operating thresholds, the specificities of CAT (39.7% vs 41.0%, P = 0.70) and CAD (41.0% vs 38.2%, P = 0.62) were successfully reproduced in the second round. Conclusion: The combined application of CAT and CAD showed potential to reduce workload of radiologists and to reduce number of biopsies on benign lesions. Computer-aided triaging (CAT) correctly dismissed 950 of 2901 (32.7%) examinations with 49 lesions in total; none were malignant. Subsequent computer-aided diagnosis (CAD) classified 132 of 285 (46.3%) lesions as benign without misclassifying any malignant lesion. Together, CAT and CAD yielded significantly fewer false-positive lesions, 53 of 109 (48.6%) and 89 of 109 (78.9%), respectively (P = 0.001), than radiological reading alone.

Introduction The response to neoadjuvant chemotherapy (NAC) in breast cancer has important prognostic implications. Dynamic prediction of tumour regression by NAC may allow for adaption of the treatment plan before completion, or even before the start of treatment. Such predictions may help prevent overtreatment and related toxicity and correct for undertreatment with ineffective regimens. Current imaging methods are not able to fully predict the efficacy of NAC. To successfully improve response prediction, tumour biology and heterogeneity as well as treatment-induced changes have to be considered. In the LIMA study, multiparametric MRI will be combined with liquid biopsies. In addition to conventional clinical and pathological information, these methods may give complementary information at multiple time points during treatment. Aim To combine multiparametric MRI and liquid biopsies in patients with breast cancer to predict residual cancer burden (RCB) after NAC, in adjunct to standard clinico-pathological information. Predictions will be made before the start of NAC, approximately halfway during treatment and after completion of NAC. Methods In this multicentre prospective observational study we aim to enrol 100 patients. Multiparametric MRI will be performed prior to NAC, approximately halfway and after completion of NAC. Liquid biopsies will be obtained immediately prior to every cycle of chemotherapy and after completion of NAC. The primary endpoint is RCB in the surgical resection specimen following NAC. Collected data will primarily be analysed using multivariable techniques such as penalised regression techniques. Ethics and dissemination Medical Research Ethics Committee Utrecht has approved this study (NL67308.041.19). Informed consent will be obtained from each participant. All data are anonymised before publication. The findings of this study will be submitted to international peer-reviewed journals. Trial registration number NCT04223492.