Dataset Information

Quantitative ultrasound radiomics using texture derivatives in prediction of treatment response to neo-adjuvant chemotherapy for locally advanced breast cancer.

ABSTRACT:

Background

To investigate quantitative ultrasound (QUS) based higher-order texture derivatives in predicting the response to neoadjuvant chemotherapy (NAC) in patients with locally advanced breast cancer (LABC).

Materials and methods

100 Patients with LABC were scanned before starting NAC. Five QUS parametric image-types were generated from radio-frequency data over the tumor volume. From each QUS parametric-image, 4 grey level co-occurrence matrix-based texture images were derived (20 QUS-Tex¹), which were further processed to create texture derivatives (80 QUS-Tex¹-Tex²). Patients were classified into responders and non-responders based on clinical/pathological responses to treatment. Three machine learning algorithms based on linear discriminant (FLD), k-nearest-neighbors (KNN), and support vector machine (SVM) were used for developing radiomic models of response prediction.

Results

A KNN-model provided the best results with sensitivity, specificity, accuracy, and area under curve (AUC) of 87%, 81%, 82%, and 0.86, respectively. The most helpful features in separating the two response groups were QUS-Tex¹-Tex² features. The 5-year recurrence-free survival (RFS) calculated for KNN predicted responders and non-responders using QUS-Tex¹-Tex² model were comparable to RFS for the actual response groups.

Conclusions

We report the first study demonstrating QUS texture-derivative methods in predicting NAC responses in LABC, which leads to better results compared to using texture features alone.

SUBMITTER: Dasgupta A

PROVIDER: S-EPMC7584238 | biostudies-literature | 2020 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Quantitative ultrasound radiomics using texture derivatives in prediction of treatment response to neo-adjuvant chemotherapy for locally advanced breast cancer.

Dasgupta Archya A Brade Stephen S Sannachi Lakshmanan L Quiaoit Karina K Fatima Kashuf K DiCenzo Daniel D Osapoetra Laurentius O LO Saifuddin Murtuza M Trudeau Maureen M Gandhi Sonal S Eisen Andrea A Wright Frances F Look-Hong Nicole N Sadeghi-Naini Ali A Tran William T WT Curpen Belinda B Czarnota Gregory J GJ

Oncotarget 20201020 42

<h4>Background</h4>To investigate quantitative ultrasound (QUS) based higher-order texture derivatives in predicting the response to neoadjuvant chemotherapy (NAC) in patients with locally advanced breast cancer (LABC).<h4>Materials and methods</h4>100 Patients with LABC were scanned before starting NAC. Five QUS parametric image-types were generated from radio-frequency data over the tumor volume. From each QUS parametric-image, 4 grey level co-occurrence matrix-based texture images were derive ...[more]

PMID: 33144919

Similar Datasets

Project description:Current standard for most of the locally advanced rectal cancers is preoperative chemoradiotherapy, and, variably per institution, postoperative adjuvant chemotherapy. Short-course preoperative radiation with delayed surgery has been shown to induce tumour down-staging in both randomized and observational studies. The concept of neo-adjuvant chemotherapy has been proven successful in gastric cancer, hepatic metastases from colorectal cancer and is currently tested in primary colon cancer.Patients with rectal cancer with high risk features for local or systemic failure on magnetic resonance imaging are randomized to either a standard arm or an experimental arm. The standard arm consists of chemoradiation (1.8 Gy x 25 or 2 Gy x 25 with capecitabine) preoperatively, followed by selective postoperative adjuvant chemotherapy. Postoperative chemotherapy is optional and may be omitted by participating institutions. The experimental arm includes short-course radiotherapy (5 Gy x 5) followed by full-dose chemotherapy (capecitabine and oxaliplatin) in 6 cycles before surgery. In the experimental arm, no postoperative chemotherapy is prescribed. Surgery is performed according to TME principles in both study arms. The hypothesis is that short-course radiotherapy with neo-adjuvant chemotherapy increases disease-free and overall survival without compromising local control. Primary end-point is disease-free survival at 3 years. Secondary endpoints include overall survival, local control, toxicity profile, and treatment completion rate, rate of pathological complete response and microscopically radical resection, and quality of life.Following the advances in rectal cancer management, increased focus on survival rather than only on local control is now justified. In an experimental arm, short-course radiotherapy is combined with full-dose chemotherapy preoperatively, an alternative that offers advantages compared to concomitant chemoradiotherapy with or without postoperative chemotherapy. In a multi-centre setting this regimen is compared to current standard with the aim of improving survival for patients with locally advanced rectal cancer.ClinicalTrials.gov NCT01558921.

Project description:Introduction: MicroRNAs (miRNAs) are small non-coding RNA that play 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. Methods: Tissue 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, Spearman, Wilcoxon signed-ranks tests. Pâ¤0.05 was considered statistically significant. Results: We analyzed 32 tissue samples and 108 serum samples from 8 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. The serum levels of miR-3200 declined during NAC, and higher serum levels were associated with lower residual breast cancer burden and relapse rates. Conclusion: Variations in serum miRNA levels during NAC treatment may be therapeutically significant for predicting response and survival outcomes. Serum and tissue from a total of 27 consecutive patients diagnosed with locally advanced breast cancer undergoing NAC treatment were collected however microarray data were generated from tissue biopsy of 5 patients at four timepoints for both Normal and tumor. Additionally 3 tissue from only tumor at four timepoints and 6 patients at two timepoint T1 and T4

Project description:Introduction: MicroRNAs (miRNAs) are small non-coding RNA that play 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. Methods: Tissue 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, Spearman, Wilcoxon signed-ranks tests. P≤0.05 was considered statistically significant. Results: We analyzed 32 tissue samples and 108 serum samples from 8 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. The serum levels of miR-3200 declined during NAC, and higher serum levels were associated with lower residual breast cancer burden and relapse rates. Conclusion: Variations in serum miRNA levels during NAC treatment may be therapeutically significant for predicting response and survival outcomes.

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.

Dataset Information

Quantitative ultrasound radiomics using texture derivatives in prediction of treatment response to neo-adjuvant chemotherapy for locally advanced breast cancer.

Background

Materials and methods

Results

Conclusions

Publications

Quantitative ultrasound radiomics using texture derivatives in prediction of treatment response to neo-adjuvant chemotherapy for locally advanced breast cancer.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets