Dataset Information

A priori prediction of response in multicentre locally advanced breast cancer (LABC) patients using quantitative ultrasound and derivative texture methods.

ABSTRACT:

Purpose

We develop a multi-centric response predictive model using QUS spectral parametric imaging and novel texture-derivate methods for determining tumour responses to neoadjuvant chemotherapy (NAC) prior to therapy initiation.

Materials and methods

QUS Spectroscopy provided parametric images of mid-band-fit (MBF), spectral-slope (SS), spectral-intercept (SI), average-scatterer-diameter (ASD), and average-acoustic-concentration (AAC) in 78 patients with locally advanced breast cancer (LABC) undergoing NAC. Ultrasound radiofrequency data were collected from Sunnybrook Health Sciences Center (SHSC), University of Texas MD Anderson Cancer Center (MD-ACC), and St. Michaels Hospital (SMH) using two different systems. Texture analysis was used to quantify heterogeneities of QUS parametric images. Further, a second-pass texture analysis was applied to obtain texture-derivate features. QUS, texture- and texture-derivate parameters were determined from both tumour core and a 5-mm tumour margin and were used in comparison to histopathological analysis for developing a response predictive model to classify responders versus non-responders. Model performance was assessed using leave-one-out cross-validation. Three standard classification algorithms including a linear discriminant analysis (LDA), k-nearest-neighbors (KNN), and support vector machines-radial basis function (SVM-RBF) were evaluated.

Results

A combination of tumour core and margin classification resulted in a peak response prediction performance of 88% sensitivity, 78% specificity, 84% accuracy, 0.86 AUC, 84% PPV, and 83% NPV, achieved using the SVM-RBF classification algorithm. Other parameters and classifiers performed less well running from 66% to 80% accuracy.

Conclusions

A QUS-based framework and novel texture-derivative method enabled accurate prediction of responses to NAC. Multi-centric response predictive model provides indications of the robustness of the approach to variations due to different ultrasound systems and acquisition parameters.

SUBMITTER: Osapoetra LO

PROVIDER: S-EPMC7825636 | biostudies-literature | 2021 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

<i>A priori</i> prediction of response in multicentre locally advanced breast cancer (LABC) patients using quantitative ultrasound and derivative texture methods.

Osapoetra Laurentius O LO Sannachi Lakshmanan L Quiaoit Karina K Dasgupta Archya A DiCenzo Daniel D Fatima Kashuf K Wright Frances F Dinniwell Robert R Trudeau Maureen M Gandhi Sonal S Tran William W Kolios Michael C MC Yang Wei W Czarnota Gregory J GJ

Oncotarget 20210119 2

<h4>Purpose</h4>We develop a multi-centric response predictive model using QUS spectral parametric imaging and novel texture-derivate methods for determining tumour responses to neoadjuvant chemotherapy (NAC) prior to therapy initiation.<h4>Materials and methods</h4>QUS Spectroscopy provided parametric images of mid-band-fit (MBF), spectral-slope (SS), spectral-intercept (SI), average-scatterer-diameter (ASD), and average-acoustic-concentration (AAC) in 78 patients with locally advanced breast c ...[more]

PMID: 33520113

Similar Datasets

Project description:IntroductionMicroRNAs (miRNAs) are small non-coding RNA that plays a vital role in cancer progression. Neo-adjuvant chemotherapy (NAC) has become the standard of care for locally advanced breast cancer. The aim of this study was to evaluate miRNA alterations during NAC using multiple samples of tissue and serum to correlate miRNA expression with clinico-pathological features and patient outcomes.MethodsTissue and serum samples were collected from patients with locally advanced breast cancer undergoing NAC at four time points: time of diagnosis, after the first and fourth cycle of doxorubicin/cyclophosphamide treatment, and after the fourth cycle of docetaxel administration. First, we evaluated the miRNA expression profiles in tissue and correlated expression with clinico-pathological features. Then, a panel of four miRNAs (miR-451, miR-3200, miR-21, and miR-205) in serum samples was further validated using quantitative reverse-transcription polymerase chain reaction (RT-qPCR). The alterations in serum levels of miRNA, associations with clinical and pathological responses, correlation with clinico-pathological features, and survival outcomes were studied using Friedman, Mann-Whitney U, and Spearman, Wilcoxon signed-ranks tests. P≤0.05 was considered statistically significant.ResultsWe analyzed 72 tissue samples and 108 serum samples from 9 patients and 27 patients, respectively. MicroRNA expression profiling of tumor versus normal tissue revealed more than 100 differentially expressed miRNAs. Serum miR-451 levels were significantly decreased during treatment, and higher serum levels were associated with improved clinical and pathological responses and disease-free survival. This is one of the early reports on miR-3200 in response to treatment in breast cancer, as serum levels of miR-3200 found to decline during NAC, and higher serum levels were associated with lower residual breast cancer burden and relapse rates at time of diagnosis.ConclusionVariations in serum miRNA levels during NAC treatment may be therapeutically significant for predicting response and survival outcomes.