Prediction Of Breast Cancer Response Research Articles

Transfer learning of pre-treatment quantitative ultrasound multi-parametric images for the prediction of breast cancer response to neoadjuvant chemotherapy

Locally advanced breast cancer (LABC) is a severe type of cancer with a poor prognosis, despite advancements in therapy. As the disease is often inoperable, current guidelines suggest upfront aggressive neoadjuvant chemotherapy (NAC). Complete pathological response to chemotherapy is linked to improved survival, but conventional clinical assessments like physical exams, mammography, and imaging are limited in detecting early response. Early detection of tissue response can improve complete pathological response and patient survival while reducing exposure to ineffective and potentially harmful treatments. A rapid, cost-effective modality without the need for exogenous contrast agents would be valuable for evaluating neoadjuvant therapy response. Conventional ultrasound provides information about tissue echogenicity, but image comparisons are difficult due to instrument-dependent settings and imaging parameters. Quantitative ultrasound (QUS) overcomes this by using normalized power spectra to calculate quantitative metrics. This study used a novel transfer learning-based approach to predict LABC response to neoadjuvant chemotherapy using QUS imaging at pre-treatment. Using data from 174 patients, QUS parametric images of breast tumors with margins were generated. The ground truth response to therapy for each patient was based on standard clinical and pathological criteria. The Residual Network (ResNet) deep learning architecture was used to extract features from the parametric QUS maps. This was followed by SelectKBest and Synthetic Minority Oversampling (SMOTE) techniques for feature selection and data balancing, respectively. The Support Vector Machine (SVM) algorithm was employed to classify patients into two distinct categories: nonresponders (NR) and responders (RR). Evaluation results on an unseen test set demonstrate that the transfer learning-based approach using spectral slope parametric maps had the best performance in the identification of nonresponders with precision, recall, F1-score, and balanced accuracy of 100, 71, 83, and 86%, respectively. The transfer learning-based approach has many advantages over conventional deep learning methods since it reduces the need for large image datasets for training and shortens the training time. The results of this study demonstrate the potential of transfer learning in predicting LABC response to neoadjuvant chemotherapy before the start of treatment using quantitative ultrasound imaging. Prediction of NAC response before treatment can aid clinicians in customizing ineffectual treatment regimens for individual patients.

A priori prediction of breast cancer response to neoadjuvant chemotherapy using quantitative ultrasound, texture derivative and molecular subtype

The purpose of this study was to investigate the performances of the tumor response prediction prior to neoadjuvant chemotherapy based on quantitative ultrasound, tumour core-margin, texture derivative analyses, and molecular parameters in a large cohort of patients (n = 208) with locally advanced and earlier-stage breast cancer and combined them to best determine tumour responses with machine learning approach. Two multi-features response prediction algorithms using a k-nearest neighbour and support vector machine were developed with leave-one-out and hold-out cross-validation methods to evaluate the performance of the response prediction models. In a leave-one-out approach, the quantitative ultrasound-texture analysis based model attained good classification performance with 80% of accuracy and AUC of 0.83. Including molecular subtype in the model improved the performance to 83% of accuracy and 0.87 of AUC. Due to limited number of samples in the training process, a model developed with a hold-out approach exhibited a slightly higher bias error in classification performance. The most relevant features selected in predicting the response groups are core-to-margin, texture-derivative, and molecular subtype. These results imply that that baseline tumour-margin, texture derivative analysis methods combined with molecular subtype can potentially be used for the prediction of ultimate treatment response in patients prior to neoadjuvant chemotherapy.

An approach to the prediction of breast cancer response to neoadjuvant chemotherapy based on tumor habitats in DCE-MRI images

An approach to the prediction of breast cancer response to neoadjuvant chemotherapy based on tumor habitats in DCE-MRI images

A hierarchical self-attention-guided deep learning framework to predict breast cancer response to chemotherapy using pre-treatment tumor biopsies.

Pathological complete response (pCR) to neoadjuvant chemotherapy (NAC) has demonstrated a strong correlation to improved survival in breast cancer (BC) patients. However, pCR rates to NAC are less than 30%, depending on the BC subtype. Early prediction of NAC response would facilitate therapeutic modifications for individual patients, potentially improving overall treatment outcomes and patient survival. This study, for the first time, proposes a hierarchical self-attention-guided deep learning framework to predict NAC response in breast cancer patients using digital histopathological images of pre-treatment biopsy specimens. Digitized hematoxylin and eosin-stained slides of BC core needle biopsies were obtained from 207 patients treated with NAC, followed by surgery. The response to NAC for each patient was determined using the standard clinical and pathological criteria after surgery. The digital pathology images were processed through the proposed hierarchical framework consisting of patch-level and tumor-level processing modules followed by a patient-level response prediction component. A combination of convolutional layers and transformer self-attention blocks were utilized in the patch-level processing architecture to generate optimized feature maps. The feature maps were analyzed through two vision transformer architectures adapted for the tumor-level processing and the patient-level response prediction components. The feature map sequences for these transformer architectures were defined based on the patch positions within the tumor beds and the bed positions within the biopsy slide, respectively. A five-fold cross-validation at the patient level was applied on the training set (144 patients with 9430 annotated tumor beds and 1,559,784 patches) to train the models and optimize the hyperparameters. An unseen independent test set (63 patients with 3574 annotated tumor beds and 173,637 patches) was used to evaluate the framework. The obtained results on the test set showed an AUC of 0.89 and an F1-score of 90% for predicting pCR to NAC a priori by the proposed hierarchical framework. Similar frameworks with the patch-level, patch-level + tumor-level, and patch-level + patient-level processing components resulted in AUCs of 0.79, 0.81, and 0.84 and F1-scores of 86%, 87%, and 89%, respectively. The results demonstrate a high potential of the proposed hierarchical deep-learning methodology for analyzing digital pathology images of pre-treatment tumor biopsies to predict the pathological response of breast cancer to NAC.

Precision Imaging: One Step Closer to Pretreatment Prediction of Breast Cancer Response to Neoadjuvant Systemic Therapy

Precision Imaging: One Step Closer to Pretreatment Prediction of Breast Cancer Response to Neoadjuvant Systemic Therapy

Changes in the tumor oxygenation but not in the tumor volume and tumor vascularization reflect early response of breast cancer to neoadjuvant chemotherapy

BackgroundBreast cancer neoadjuvant chemotherapy (NACT) allows for assessing tumor sensitivity to systemic treatment, planning adjuvant treatment and follow-up. However, a sufficiently large number of patients fail to achieve the desired level of pathological tumor response while optimal early response assessment methods have not been established now. In our study, we simultaneously assessed the early chemotherapy-induced changes in the tumor volume by ultrasound (US), the tumor oxygenation by diffuse optical spectroscopy imaging (DOSI), and the state of the tumor vascular bed by Doppler US to elaborate the predictive criteria of breast tumor response to treatment.MethodsA total of 133 patients with a confirmed diagnosis of invasive breast cancer stage II to III admitted to NACT following definitive breast surgery were enrolled, of those 103 were included in the final analysis. Tumor oxygenation by DOSI, tumor volume by US, and tumor vascularization by Doppler US were determined before the first and second cycle of NACT. After NACT completion, patients underwent surgery followed by pathological examination and assessment of the pathological tumor response. On the basis of these, data regression predictive models were created.ResultsWe observed changes in all three parameters 3 weeks after the start of the treatment. However, a high predictive potential for early assessment of tumor sensitivity to NACT demonstrated only the level of oxygenation, ΔStO2, (ρ = 0.802, p ≤ 0.01). The regression model predicts the tumor response with a high probability of a correct conclusion (89.3%). The “Tumor volume” model and the “Vascularization index” model did not accurately predict the absence of a pathological tumor response to treatment (60.9% and 58.7%, respectively), while predicting a positive response to treatment was relatively better (78.9% and 75.4%, respectively).ConclusionsDiffuse optical spectroscopy imaging appeared to be a robust tool for early predicting breast cancer response to chemotherapy. It may help identify patients who need additional molecular genetic study of the tumor in order to find the source of resistance to treatment, as well as to correct the treatment regimen.

Quantitative digital histopathology and machine learning to predict pathological complete response to chemotherapy in breast cancer patients using pre-treatment tumor biopsies

Complete pathological response (pCR) to neoadjuvant chemotherapy (NAC) is a prognostic factor for breast cancer (BC) patients and is correlated with improved survival. However, pCR rates are variable to standard NAC, depending on BC subtype. This study investigates quantitative digital histopathology coupled with machine learning (ML) to predict NAC response a priori. Clinicopathologic data and digitized slides of BC core needle biopsies were collected from 149 patients treated with NAC. The nuclei within the tumor regions were segmented on the histology images of biopsy samples using a weighted U-Net model. Five pathomic feature subsets were extracted from segmented digitized samples, including the morphological, intensity-based, texture, graph-based and wavelet features. Seven ML experiments were conducted with different feature sets to develop a prediction model of therapy response using a gradient boosting machine with decision trees. The models were trained and optimized using a five-fold cross validation on the training data and evaluated using an unseen independent test set. The prediction model developed with the best clinical features (tumor size, tumor grade, age, and ER, PR, HER2 status) demonstrated an area under the ROC curve (AUC) of 0.73. Various pathomic feature subsets resulted in models with AUCs in the range of 0.67 and 0.87, with the best results associated with the graph-based and wavelet features. The selected features among all subsets of the pathomic and clinicopathologic features included four wavelet and three graph-based features and no clinical features. The predictive model developed with these features outperformed the other models, with an AUC of 0.90, a sensitivity of 85% and a specificity of 82% on the independent test set. The results demonstrated the potential of quantitative digital histopathology features integrated with ML methods in predicting BC response to NAC. This study is a step forward towards precision oncology for BC patients to potentially guide future therapies.

Accuracy of ultrasound elastography for predicting breast cancer response to neoadjuvant chemotherapy: A systematic review and meta-analysis.

BACKGROUNDSeveral studies have reported the prognostic value of ultrasound elastography (UE) in patients receiving neoadjuvant chemotherapy (NACT) for breast cancer. However, the assessment of parameters differed between shear-wave elastography and strain elastography in terms of measured elasticity parameter and mode of imaging. It is important, therefore, to assess the accuracy of the two modes of elastography. AIMTo assess the accuracy of UE for predicting the pathologic complete response (pCR) in breast cancer patients following NACT.METHODSA comprehensive and systematic search was performed in the databases of MEDLINE, EMBASE, SCOPUS, PubMed Central, CINAHL, Web of Science and Cochrane library from inception until December 2020. Meta-analysis was performed using STATA software “Midas” package.RESULTSA total of 14 studies with 989 patients were included. The pooled sensitivities were 86% [95% confidence interval (CI): 76%-92%] for UE, 77% (95%CI: 68%-84%) for shear-wave elastography, and 92% (95%CI: 73%-98%) for strain-wave elastography. The pooled score specificities were 86% (95%CI: 80%-90%) for UE, 84% (95%CI: 72%-91%) for shear-wave elasticity, and 87% (95%CI: 81%-92%) for strain-wave elastography. A significant heterogeneity was found among studies based on the chi-square test results and an I2 statistic > 75%.CONCLUSIONStrain-wave type of UE can accurately predict the pCR following NACT amongst breast cancer patients. Studies exploring its accuracy in different ethnic populations are required to strengthen the evidence.

Abstract P3-02-04: Prediction of breast cancer response to neoadjuvant chemotherapy in different biological breast cancer subtypes using diffuse optical tomography

Abstract Background: Optical-based imaging modalities play an important role in assessing breast tissue composition by measuring optical property contrast from endogenous chromophores. The advantages of optical techniques are the use of non-ionizing radiation, ease of use, and relatively low cost. The primary objective of this study is to examine changes in optically derived parameters (i.e., deoxy-hemoglobin concentration, ctHHb) from different breast cancer subtypes under neoadjuvant chemotherapy (NAC), and correlate with tumor pathologic complete response (pCR). Methods: This retrospective study evaluated 89 tumors in total divided into three distinct subtypes: HR+/HER2- (n=34), HER2+ (n=27), and TNBC (n=28). All patients were imaged at baseline, before starting NAC (TP0), and two weeks after receiving one cycle of taxane-based chemotherapy (TP1). HER2+ breast cancer patients also received HER2-target therapy. pCR was defined as complete absence of invasive carcinoma in the breast and lymph node(s) (ypT0/is ypN0 Mx) at the time of surgery. Whole breast volume was imaged by a diffuse optical tomography breast imaging system (DOTBIS) using low-intensity near-infrared light. ctHHb tumor volume concentration was normalized by the non-affected health tissue ctHHb mean value (ctHHbN). For each molecular subgroup, we conducted an independent-samples t-test to determine if there was a difference in ctHHbN levels at TP1 compared to TP0 between patients with a pCR and non-pCR. Significance was assumed at a confidence interval of 95% (α = 0.05). Results: In total, 69 patients were imaged with DOTIBS at both time points, TP0 and TP1. HR+/HER2-, TNBC and HER2+ accounted for 32% (n=23), 37% (n=22) and 30% (n=22), respectively. The ratio between ctHHbN levels measured at TP1 and TP0 was statistically significantly lower in the pCR group than non-pCR for the HER2+ and HR+/HER2- molecular subgroups, Table 1. Conclusion: Aligned to the current practices in breast cancer management based on the characterization of breast cancer subtypes, our work evaluated changes in DOTBIS optically derived features and pCR status for different subtypes. We observed that ctHHbN levels change after two weeks of NAC and these changes are modifiable according to pCR status and are dependent on immunophenotype. Table 1.Ratio between ctHHbN levels measured at TP1 and TP0 between pCR and non-pCR according to different molecular subtypes.Molecular SubtypepCR (mean ± SD )non-pCR (mean ± SD )p-valueHR+/HER2- (n=23)0.77 ± 0.22 (n=6)1.14 ± 0.24 (n=17).01HER2+ (n=24)0.74 ± 0.30 (n=15)1.54 ± 0.98 (n=9).04TNBC (n=22)0.96 ± 0.38 (n=4)1.29 ± 0.37 (n=18).18Bold values indicate statistical significance at p<.05 level. Citation Format: Mirella L Altoe, Kevin M Kalinsky, Hua Guo, Hanina Hibshoosh, Mariella Tejada, Katherine D Crew, Melissa K Accordino, Meghna S Trivedi, Alessandro Marone, Hyun K Kim, Andreas H Hielscher, Dawn L Hershman. Prediction of breast cancer response to neoadjuvant chemotherapy in different biological breast cancer subtypes using diffuse optical tomography [abstract]. In: Proceedings of the 2021 San Antonio Breast Cancer Symposium; 2021 Dec 7-10; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2022;82(4 Suppl):Abstract nr P3-02-04.

Deep learning of quantitative ultrasound multi-parametric images at pre-treatment to predict breast cancer response to chemotherapy

In this study, a novel deep learning-based methodology was investigated to predict breast cancer response to neo-adjuvant chemotherapy (NAC) using the quantitative ultrasound (QUS) multi-parametric imaging at pre-treatment. QUS multi-parametric images of breast tumors were generated using the data acquired from 181 patients diagnosed with locally advanced breast cancer and planned for NAC followed by surgery. The ground truth response to NAC was identified for each patient after the surgery using the standard clinical and pathological criteria. Two deep convolutional neural network (DCNN) architectures including the residual network and residual attention network (RAN) were explored for extracting optimal feature maps from the parametric images, with a fully connected network for response prediction. In different experiments, the features maps were derived from the tumor core only, as well as the core and its margin. Evaluation results on an independent test set demonstrate that the developed model with the RAN architecture to extract feature maps from the expanded parametric images of the tumor core and margin had the best performance in response prediction with an accuracy of 88% and an area under the receiver operating characteristic curve of 0.86. Ten-year survival analyses indicate statistically significant differences between the survival of the responders and non-responders identified based on the model prediction at pre-treatment and the standard criteria at post-treatment. The results of this study demonstrate the promising capability of DCNNs with attention mechanisms in predicting breast cancer response to NAC prior to the start of treatment using QUS multi-parametric images.

Predicting breast cancer response to neoadjuvant chemotherapy using ensemble deep transfer learning based on CT images.

To develop an ensemble a deep transfer learning model of CT images for predicting pathologic complete response (pCR) in breast cancer patients undergoing neoadjuvant chemotherapy (NAC). The data were obtained from the public dataset 'QIN-Breast' from The Cancer Imaging Archive (TCIA). CT images were gathered before and after the first cycle of NAC. CT images of 121 breast cancer patients were used to train and test the model. Among these patients, 58 achieved a pCR and 63 showed a non-pCR based pathology examination of surgical results after NAC. The dataset was split into training and testing subsets with a ratio of 7:3. In addition, the number of training samples in the dataset was increased from 656 to 1,968 by performing an image augmentation method. Two deep transfer learning models namely, DenseNet201 and ResNet152V2, and the ensemble model with a concatenation of two models, were trained and tested using CT images. The ensemble model obtained the highest accuracy of 100% on the testing dataset. Furthermore, we received the best performance of 100% in recall, precision and f1-score value for the ensemble model. This supports the fact that the ensemble model results in better-generalized model and leads to efficient framework. Although a 0.004 and 0.003 difference were seen between the AUC of two base models (DenseNet201 and ResNet152V2) and the proposed ensemble, this increase in the model quality is critical in medical research. T-SNE revealed that in the proposed ensemble, no points were clustered into the wrong class. These results expose the strong performance of the proposed ensemble. The study concluded that the ensemble model can increase the ability to predict breast cancer response to first-cycle NAC than two DenseNet201 and ResNet152V2 models.

Characterizing intra-tumor regions on quantitative ultrasound parametric images to predict breast cancer response to chemotherapy at pre-treatment

The efficacy of quantitative ultrasound (QUS) multi-parametric imaging in conjunction with unsupervised classification algorithms was investigated for the first time in characterizing intra-tumor regions to predict breast tumor response to chemotherapy before the start of treatment. QUS multi-parametric images of breast tumors were generated using the ultrasound radiofrequency data acquired from 181 patients diagnosed with locally advanced breast cancer and planned for neo-adjuvant chemotherapy followed by surgery. A hidden Markov random field (HMRF) expectation maximization (EM) algorithm was applied to identify distinct intra-tumor regions on QUS multi-parametric images. Several features were extracted from the segmented intra-tumor regions and tumor margin on different parametric images. A multi-step feature selection procedure was applied to construct a QUS biomarker consisting of four features for response prediction. Evaluation results on an independent test set indicated that the developed biomarker coupled with a decision tree model with adaptive boosting (AdaBoost) as the classifier could predict the treatment response of patient at pre-treatment with an accuracy of 85.4% and an area under the receiver operating characteristic (ROC) curve (AUC) of 0.89. In comparison, the biomarkers consisted of the features derived from the entire tumor core (without consideration of the intra-tumor regions), and the entire tumor core and the tumor margin could predict the treatment response of patients with an accuracy of 74.5% and 76.4%, and an AUC of 0.79 and 0.76, respectively. Standard clinical features could predict the therapy response with an accuracy of 69.1% and an AUC of 0.6. Long-term survival analyses indicated that the patients predicted by the developed model as responders had a significantly better survival compared to the non-responders. Similar findings were observed for the two response cohorts identified at post-treatment based on standard clinical and pathological criteria. The results obtained in this study demonstrated the potential of QUS multi-parametric imaging integrated with unsupervised learning methods in identifying distinct intra-tumor regions in breast cancer to characterize its responsiveness to chemotherapy prior to the start of treatment.

Prediction of chemotherapy response in breast cancer patients at pre-treatment using second derivative texture of CT images and machine learning

Although neoadjuvant chemotherapy (NAC) is a crucial component of treatment for locally advanced breast cancer (LABC), only about 70% of patients respond to it. Effective adjustment of NAC for individual patients can significantly improve survival rates of those resistant to standard regimens. Thus, the early prediction of NAC outcome is of great importance in facilitating a personalized paradigm for breast cancer therapeutics. In this study, quantitative computed tomography (qCT) parametric imaging in conjunction with machine learning techniques were investigated to predict LABC tumor response to NAC. Textural and second derivative textural (SDT) features of CT images of 72 patients diagnosed with LABC were analysed before the initiation of NAC to quantify intra-tumor heterogeneity. These quantitative features were processed through a correlation-based feature reduction followed by a sequential feature selection with a bootstrap 0.632+ area under the receiver operating characteristic (ROC) curve (AUC0.632+) criterion. The best feature subset consisted of a combination of one textural and three SDT features. Using these features, an AdaBoost decision tree could predict the patient response with a cross-validated AUC0.632+ accuracy, sensitivity and specificity of 0.88, 85%, 88% and 75%, respectively. This study demonstrates, for the first time, that a combination of textural and SDT features of CT images can be used to predict breast cancer response NAC prior to the start of treatment which can potentially facilitate early therapy adjustments.

Early Assessment Window for Predicting Breast Cancer Neoadjuvant Therapy using Biomarkers, Ultrasound, and Diffuse Optical Tomography.

The purpose of the study was to assess the utility of tumor biomarkers, ultrasound (US) and US-guided diffuse optical tomography (DOT) in early prediction of breast cancer responseto neoadjuvant therapy (NAT). This prospective HIPAA compliant study was approved by the institutional review board. Forty one patients were imaged with US and US-guided DOT prior to NAT, at completion of the first three treatment cycles, and prior to definitive surgery from February 2017 to January 2020. Miller-Payne grading was used to assess pathologic response. Receiver operating characteristic curves (ROCs) were derived from logistic regression using independent variables, including: tumor biomarkers, US maximum diameter, percentage reduction of the diameter (%US), pretreatment maximum total hemoglobin concentration (HbT) and percentage reduction in HbT (%HbT) at different treatment time points. Resulting ROCs were compared using area under the curve (AUC). Statistical significance was tested using two-sided two-sample student t-test with P < 0.05 considered statistically significant. Logistic regression was used for ROC analysis. Thirty-eight patients (mean age = 47, range 24-71years) successfully completed the study, including 15 HER2 + of which 11 were ER + ; 12 ER + or PR + /HER2-, and 11 triple negative. The combination of HER2 and ER biomarkers, %HbT at the end of cycle 1 (EOC1) and %US (EOC1) provided the best early prediction, AUC = 0.941 (95% CI 0.869-1.0). Similarly an AUC of 0.910 (95% CI 0.810-1.0) with %US (EOC1) and %HbT (EOC1) can be achieved independent of HER2 and ER status. The most accurate prediction, AUC = 0.974 (95% CI 0.933-1.0), was achieved with %US at EOC1 and %HbT (EOC3) independent of biomarker status. The combined use of tumor HER2 and ER status, US, and US-guided DOT may provide accurate prediction of NAT response as early as the completion of the first treatment cycle. NCT02891681. https://clinicaltrials.gov/ct2/show/NCT02891681 , Registration time: September 7, 2016.

Abstract PS13-18: Predicting breast cancer response to neoadjuvant therapies using a mathematical model individualized with patient-specific magnetic resonance imaging data: Preliminary Results

Abstract Background: This study evaluates the ability to predict the response of locally advanced breast cancers to neoadjuvant therapy (NAT) using patient-specific magnetic resonance imaging (MRI) data and a biophysical mathematical model. The 3D mathematical model consists of three parts: tumor cell proliferation, tumor spread (diffusion), and treatment. In particular, the tumor cells proliferate according to logistic growth, and the diffusion term is coupled to the mechanical properties of the surrounding fibroglandular and adipose tissues to inform individual tumor growth patterns (specific to each patient’s anatomy). The model’s treatment term accounts for tumor cell reduction according to approximate local drug delivery for each patient. Methods: Patients (N = 21) with intermediate to high grade invasive breast cancers with varying receptor status, who were eligible for NAT as a component of their clinical care, were recruited. Each patient was treated with standard-of-care consisting of one or two NAT regimens in sequence followed by surgical resection of any residual tumor. MRI data are acquired at four time points: 1) prior to initiation of NAT, 2) after 1 cycle of NAT, 3) after 2-4 cycles of NAT, and 4) 1 cycle after scan 3. The MRI data is processed and evaluated using our semi-automated pipeline. Specifically, diffusion-weighted MRI data is utilized to characterize the cellularity throughout the tumor tissue, and dynamic contrast-enhanced (DCE-) MRI data is used to segment the breast tissue and analyze the local drug delivery using pharmacokinetic analysis and population-derived plasma curves of drug concentrations. The model’s predictive ability is assessed using three different strategies. First, the model is calibrated using each patient’s first two scans to enable predictions of the total tumor cellularity, volume, and longest axis that are directly compared to the values measured from their third scan. Second, the model’s predictions for tumor response are compared to the corresponding response evaluation criteria in solid tumors (RECIST) results. Third, the model is re-calibrated using scans 3 and 4 and simulated to the time of surgery to compare the model’s predictions to each patient’s response status determined by surgical pathology. Results: Calibrating the model with MRI data for one cycle of therapy yields predictions strongly correlated with tumor response measured from each patient’s third scan, concordance correlation coefficients of 0.91, 0.90, and 0.86 for total cellularity, volume, and longest axis, respectively (p &amp;lt; 0.01, N = 18). The model’s predictions are significantly (p &amp;lt; 0.01) correlated with tumor response as designated by RECIST for the cohort. Specifically, the model predicts greater percent reduction in the longest axis for the RECIST designated responder group (i.e., complete response and partial response) compared to non-responders. At the time of surgery, the model predicts changes in total tumor cellularity from baseline that are significantly (p &amp;lt; 0.01) correlated with pathological response status—an area under the receiver operator characteristic curve of 0.92 and a sensitivity and specificity of 1.0 and 0.74, respectively. Discussion: These preliminary results suggest that this clinical-mathematical approach can be predictive of tumor response very early in the course of NAT on a patient-specific basis. Moreover, the study was performed in the community-care setting across a heterogenous group of patients, indicating the approach may be practical for wide-spread application. NCI U01 CA174706, NCI U01 CA154602, CPRIT RR160005, ACS-RSG-18-006-01-CCE, R01CA240589, NCI-U24CA226110, CPRIT RR160093 Citation Format: Angela M Jarrett, David A. Hormuth, II, Anum K Syed, Chengyue Wu, John Virostko, Anna G Sorace, Julie C DiCarlo, Jeanne Kowalski, Debra Patt, Boone Goodgame, Sarah Avery, Thomas E Yankeelov. Predicting breast cancer response to neoadjuvant therapies using a mathematical model individualized with patient-specific magnetic resonance imaging data: Preliminary Results [abstract]. In: Proceedings of the 2020 San Antonio Breast Cancer Virtual Symposium; 2020 Dec 8-11; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2021;81(4 Suppl):Abstract nr PS13-18.

Predicting breast cancer response to neoadjuvant treatment using multi-feature MRI: results from the I-SPY 2 TRIAL

Dynamic contrast-enhanced (DCE) MRI provides both morphological and functional information regarding breast tumor response to neoadjuvant chemotherapy (NAC). The purpose of this retrospective study is to test if prediction models combining multiple MRI features outperform models with single features. Four features were quantitatively calculated in each MRI exam: functional tumor volume, longest diameter, sphericity, and contralateral background parenchymal enhancement. Logistic regression analysis was used to study the relationship between MRI variables and pathologic complete response (pCR). Predictive performance was estimated using the area under the receiver operating characteristic curve (AUC). The full cohort was stratified by hormone receptor (HR) and human epidermal growth factor receptor 2 (HER2) status (positive or negative). A total of 384 patients (median age: 49 y/o) were included. Results showed analysis with combined features achieved higher AUCs than analysis with any feature alone. AUCs estimated for the combined versus highest AUCs among single features were 0.81 (95% confidence interval [CI]: 0.76, 0.86) versus 0.79 (95% CI: 0.73, 0.85) in the full cohort, 0.83 (95% CI: 0.77, 0.92) versus 0.73 (95% CI: 0.61, 0.84) in HR-positive/HER2-negative, 0.88 (95% CI: 0.79, 0.97) versus 0.78 (95% CI: 0.63, 0.89) in HR-positive/HER2-positive, 0.83 (95% CI not available) versus 0.75 (95% CI: 0.46, 0.81) in HR-negative/HER2-positive, and 0.82 (95% CI: 0.74, 0.91) versus 0.75 (95% CI: 0.64, 0.83) in triple negatives. Multi-feature MRI analysis improved pCR prediction over analysis of any individual feature that we examined. Additionally, the improvements in prediction were more notable when analysis was conducted according to cancer subtype.

Predicting breast cancer response to neoadjuvant chemotherapy based on tumor vascular features in needle biopsies.

In clinical breast cancer intervention, selection of the optimal treatment protocol based on predictive biomarkers remains an elusive goal. Here, we present a modeling tool to predict the likelihood of breast cancer response to neoadjuvant chemotherapy using patient specific tumor vasculature biomarkers. A semi-automated analysis was implemented and performed on 3990 histological images from 48 patients, with 10-208 images analyzed for each patient. We applied a histology-based model to resected primary breast cancer tumors (n = 30), and then evaluated a cohort of patients (n = 18) undergoing neoadjuvant chemotherapy, collecting pre- and post-treatment pathology specimens and MRI data. We found that core biopsy samples can be used with acceptable accuracy (r = 0.76) to determine histological parameters representative of the whole tissue region. Analysis of model histology parameters obtained from tumor vasculature measurements, specifically diffusion distance divided by radius of drug source (L/rb) and blood volume fraction (BVF), provides a statistically significant separation of patients obtaining a pathologic complete response (pCR) from those that do not (Student's t-test; P < 0.05). With this model, it is feasible to evaluate primary breast tumor vasculature biomarkers in a patient specific manner, thereby allowing a precision approach to breast cancer treatment.

Early Prediction of Breast Cancer Therapy Response using Multiresolution Fractal Analysis of DCE-MRI Parametric Maps.

We aimed to determine whether multiresolution fractal analysis of voxel-based dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) parametric maps can provide early prediction of breast cancer response to neoadjuvant chemotherapy (NACT). In total, 55 patients underwent 4 DCE-MRI examinations before, during, and after NACT. The shutter-speed model was used to analyze the DCE-MRI data and generate parametric maps within the tumor region of interest. The proposed multiresolution fractal method and the more conventional methods of single-resolution fractal, gray-level co-occurrence matrix, and run-length matrix were used to extract features from the parametric maps. Only the data obtained before and after the first NACT cycle were used to evaluate early prediction of response. With a training (N = 40) and testing (N = 15) data set, support vector machine was used to assess the predictive abilities of the features in classification of pathologic complete response versus non-pathologic complete response. Generally the multiresolution fractal features from individual maps and the concatenated features from all parametric maps showed better predictive performances than conventional features, with receiver operating curve area under the curve (AUC) values of 0.91 (all parameters) and 0.80 (Ktrans), in the training and testing sets, respectively. The differences in AUC were statistically significant (P < .05) for several parametric maps. Thus, multiresolution analysis that decomposes the texture at various spatial-frequency scales may more accurately capture changes in tumor vascular heterogeneity as measured by DCE-MRI, and therefore provide better early prediction of NACT response.

HLA-DR in Cytotoxic T Lymphocytes Predicts Breast Cancer Patients' Response to Neoadjuvant Chemotherapy.

Prediction of breast cancer response to Neoadjuvant Chemotherapy (NACT) is an urgent need to promptly direct non-responder patients to alternative therapies. Infiltrating T lymphocytes, namely cytotoxic T lymphocytes (CTLs) have been appointed as predictors of response. However, cancer cells have the ability to dampen CTLs' activity and thus, the prognostic value of the CTLs, per se, is debatable. Here, we disclose that more than the occurrence of CTLs, it is their activation state, revealed by HLA-DR expression, that can accurately predict response to NACT. Flow cytometry analysis of breast cancer biopsies showed that the frequency of CTLs and other lymphocytes were similar regardless disease stage and between NACT responders and non-responders. However, only breast cancer patients without axillary lymph node metastasis and NACT responders have HLA-DRhi CTLs. Interestingly, HLA-DR levels in tumor CTLs is correlated with HLA-DR levels in systemic CTLs. These HLA-DR+ CTLs produce IFN-γ and Granzyme B, enlightening their effector and probable anti-tumor activity profile. Moreover, the level of HLA-DR in CTLs is negatively correlated with the level of HLA-DR in T regulatory lymphocytes and with immunosuppressive and pro-tumor molecules in the tumor microenvironment. Hence, HLA-DR levels in CTLs is a highly sensitive and specific potential predictive factor of NACT-response, which can be assessed in blood to guide therapeutic decisions.

Abstract 1610: Expression of genes of the uPA system from LCM-procured breast carcinoma cells and their relationships with clinical outcomes

Abstract Introduction: The urokinase plasminogen activator (uPA), its receptor uPAR and serine protease inhibitors PAI-1 or PAI-2 play a key role in tissue membrane remodeling and invasion of basement membranes by induction of a fibrinolytic pathway. Earlier studies reported that uPA and PAI-1 protein levels assist in prediction of breast cancer response to chemotherapy. Our goal is to develop molecular signatures of candidate genes and identify novel relationships with these four protein biomarkers that demonstrate clinical utility for assessment of breast carcinoma outcomes. Methods: The retrospective study used de-identified tissue biopsies from primary breast cancers on which biomarker and clinical outcomes were stored in an IRB-approved Database. ELISA analyses of uPA, uPAR and PAI-1 performed using IMUBIND kits (American Diagnostica Inc.) used cutoff values previously reported. Estrogen (ER) and progestin receptor (PR) assays were performed either by EIA (Abbott Labs) or by radioligand binding (NEN/DuPont). Relative expression levels of 22,000 genes were determined by microarray using RNA extracted and amplified from Laser-Capture Microdissection (LCM) procured breast carcinoma cells. Univariable and multivariable Cox regression analyses, Kaplan-Meier plots, Violin and scatter grams were performed by R Studio version 3.4.1. External validation of gene subsets derived were performed with SurvExpress. Results: uPA and PAI-1 protein content of a carcinoma were predictive of overall survival (OS). Examination of biomarker gene expression by Violin plots revealed that either ER- or PR- breast cancers expressed elevated levels of UPA, UPAR and PAI2 compared to that of ER+ or PR+ carcinoma cells. Scatter grams suggested an inverse relationship between ER/PR protein levels and expression of UPA, UPAR and PAI2. Univariable Cox regression analyses indicated that PAI2 expression was associated with progression-free survival (PFS) and OS while UPA and PAI1 expression was only associated with OS with a p value &amp;lt; 0.3 (selected as the discovery limit). When carcinomas were sorted by biomarker levels, qPCR expression of RERG and NQO-1 were elevated in uPA- lesions while CD34 and EDG-1 were elevated in uPAR- cancers. However, ERBB4 expression was elevated in PAI-1+ carcinomas. Multivariate Cox regression, performed with backward conditional selection using microarray data with ER or PR status revealed clinically relevant genes for PFS and OS. SurvExpress, an online tool, validated gene subsets externally. Conclusions: Use of LCM-procured breast carcinoma cells in a nondestructive manner uncovered relationships between gene expression and either uPA, uPAR, PAI-1 or PAI-2 protein content of a lesion to reveal candidates for predicting clinical outcomes. Certain of these gene subsets appear related to patient prognosis when considered with ER/PR status of the carcinomas. Citation Format: Seth B. Sereff, Michael W. Daniels, James L. Wittliff. Expression of genes of the uPA system from LCM-procured breast carcinoma cells and their relationships with clinical outcomes [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2018; 2018 Apr 14-18; Chicago, IL. Philadelphia (PA): AACR; Cancer Res 2018;78(13 Suppl):Abstract nr 1610.