skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: TU-D-207B-05: Intra-Tumor Partitioning and Texture Analysis of DCE-MRI Identifies Relevant Tumor Subregions to Predict Early Pathological Response of Breast Cancer to Neoadjuvant Chemotherapy

Abstract

Purpose: To predict early pathological response of breast cancer to neoadjuvant chemotherapy (NAC) based on quantitative, multi-region analysis of dynamic contrast enhancement magnetic resonance imaging (DCE-MRI). Methods: In this institution review board-approved study, 35 patients diagnosed with stage II/III breast cancer were retrospectively investigated using DCE-MR images acquired before and after the first cycle of NAC. First, principal component analysis (PCA) was used to reduce the dimensionality of the DCE-MRI data with a high-temporal resolution. We then partitioned the whole tumor into multiple subregions using k-means clustering based on the PCA-defined eigenmaps. Within each tumor subregion, we extracted four quantitative Haralick texture features based on the gray-level co-occurrence matrix (GLCM). The change in texture features in each tumor subregion between pre- and during-NAC was used to predict pathological complete response after NAC. Results: Three tumor subregions were identified through clustering, each with distinct enhancement characteristics. In univariate analysis, all imaging predictors except one extracted from the tumor subregion associated with fast wash-out were statistically significant (p< 0.05) after correcting for multiple testing, with area under the ROC curve or AUCs between 0.75 and 0.80. In multivariate analysis, the proposed imaging predictors achieved an AUC of 0.79 (p = 0.002) inmore » leave-one-out cross validation. This improved upon conventional imaging predictors such as tumor volume (AUC=0.53) and texture features based on whole-tumor analysis (AUC=0.65). Conclusion: The heterogeneity of the tumor subregion associated with fast wash-out on DCE-MRI predicted early pathological response to neoadjuvant chemotherapy in breast cancer.« less

Authors:
; ; ;  [1]
  1. Stanford University, Palo Alto, CA (United States)
Publication Date:
OSTI Identifier:
22653983
Resource Type:
Journal Article
Resource Relation:
Journal Name: Medical Physics; Journal Volume: 43; Journal Issue: 6; Other Information: (c) 2016 American Association of Physicists in Medicine; Country of input: International Atomic Energy Agency (IAEA)
Country of Publication:
United States
Language:
English
Subject:
60 APPLIED LIFE SCIENCES; 61 RADIATION PROTECTION AND DOSIMETRY; BIOMEDICAL RADIOGRAPHY; CHEMOTHERAPY; IMAGES; MAGNETIC RESONANCE; MAMMARY GLANDS; MULTIVARIATE ANALYSIS; NEOPLASMS; NMR IMAGING

Citation Formats

Wu, J, Gong, G, Cui, Y, and Li, R. TU-D-207B-05: Intra-Tumor Partitioning and Texture Analysis of DCE-MRI Identifies Relevant Tumor Subregions to Predict Early Pathological Response of Breast Cancer to Neoadjuvant Chemotherapy. United States: N. p., 2016. Web. doi:10.1118/1.4957513.
Wu, J, Gong, G, Cui, Y, & Li, R. TU-D-207B-05: Intra-Tumor Partitioning and Texture Analysis of DCE-MRI Identifies Relevant Tumor Subregions to Predict Early Pathological Response of Breast Cancer to Neoadjuvant Chemotherapy. United States. doi:10.1118/1.4957513.
Wu, J, Gong, G, Cui, Y, and Li, R. 2016. "TU-D-207B-05: Intra-Tumor Partitioning and Texture Analysis of DCE-MRI Identifies Relevant Tumor Subregions to Predict Early Pathological Response of Breast Cancer to Neoadjuvant Chemotherapy". United States. doi:10.1118/1.4957513.
@article{osti_22653983,
title = {TU-D-207B-05: Intra-Tumor Partitioning and Texture Analysis of DCE-MRI Identifies Relevant Tumor Subregions to Predict Early Pathological Response of Breast Cancer to Neoadjuvant Chemotherapy},
author = {Wu, J and Gong, G and Cui, Y and Li, R},
abstractNote = {Purpose: To predict early pathological response of breast cancer to neoadjuvant chemotherapy (NAC) based on quantitative, multi-region analysis of dynamic contrast enhancement magnetic resonance imaging (DCE-MRI). Methods: In this institution review board-approved study, 35 patients diagnosed with stage II/III breast cancer were retrospectively investigated using DCE-MR images acquired before and after the first cycle of NAC. First, principal component analysis (PCA) was used to reduce the dimensionality of the DCE-MRI data with a high-temporal resolution. We then partitioned the whole tumor into multiple subregions using k-means clustering based on the PCA-defined eigenmaps. Within each tumor subregion, we extracted four quantitative Haralick texture features based on the gray-level co-occurrence matrix (GLCM). The change in texture features in each tumor subregion between pre- and during-NAC was used to predict pathological complete response after NAC. Results: Three tumor subregions were identified through clustering, each with distinct enhancement characteristics. In univariate analysis, all imaging predictors except one extracted from the tumor subregion associated with fast wash-out were statistically significant (p< 0.05) after correcting for multiple testing, with area under the ROC curve or AUCs between 0.75 and 0.80. In multivariate analysis, the proposed imaging predictors achieved an AUC of 0.79 (p = 0.002) in leave-one-out cross validation. This improved upon conventional imaging predictors such as tumor volume (AUC=0.53) and texture features based on whole-tumor analysis (AUC=0.65). Conclusion: The heterogeneity of the tumor subregion associated with fast wash-out on DCE-MRI predicted early pathological response to neoadjuvant chemotherapy in breast cancer.},
doi = {10.1118/1.4957513},
journal = {Medical Physics},
number = 6,
volume = 43,
place = {United States},
year = 2016,
month = 6
}
  • Purpose: To develop an intra-tumor partitioning framework for identifying high-risk subregions from 18F-fluorodeoxyglucose positron emission tomography (FDG-PET) and CT imaging, and to test whether tumor burden associated with the high-risk subregions is prognostic of outcomes in lung cancer. Methods: In this institutional review board-approved retrospective study, we analyzed the pre-treatment FDG-PET and CT scans of 44 lung cancer patients treated with radiotherapy. A novel, intra-tumor partitioning method was developed based on a two-stage clustering process: first at patient-level, each tumor was over-segmented into many superpixels by k-means clustering of integrated PET and CT images; next, tumor subregions were identified bymore » merging previously defined superpixels via population-level hierarchical clustering. The volume associated with each of the subregions was evaluated using Kaplan-Meier analysis regarding its prognostic capability in predicting overall survival (OS) and out-of-field progression (OFP). Results: Three spatially distinct subregions were identified within each tumor, which were highly robust to uncertainty in PET/CT co-registration. Among these, the volume of the most metabolically active and metabolically heterogeneous solid component of the tumor was predictive of OS and OFP on the entire cohort, with a concordance index or CI = 0.66–0.67. When restricting the analysis to patients with stage III disease (n = 32), the same subregion achieved an even higher CI = 0.75 (HR = 3.93, logrank p = 0.002) for predicting OS, and a CI = 0.76 (HR = 4.84, logrank p = 0.002) for predicting OFP. In comparison, conventional imaging markers including tumor volume, SUVmax and MTV50 were not predictive of OS or OFP, with CI mostly below 0.60 (p < 0.001). Conclusion: We propose a robust intra-tumor partitioning method to identify clinically relevant, high-risk subregions in lung cancer. We envision that this approach will be applicable to identifying useful imaging biomarkers in many cancer types.« less
  • Purpose: To evaluate the effects of neoadjuvant intra-arterial chemotherapy (NAIC) for locally advanced uterine cervical cancer, and to analyze factors influencing the response to the chemotherapy. Methods: Thirty-four patients with invasive cervical cancer more than 4 cm in diameter were enrolled in this study. NAIC was performed using cisplatin-based regimens. The response was assessed by magnetic resonance imaging (MRI) and examination of surgical specimens. Pretreatment factors involved in the response to NAIC were evaluated and the relationship between the factors and the prognosis was assessed. Results:Clinical response was achieved in 28 (82%) patients. Thirty-one of 49 invasions in the parametrialmore » halves disappeared. Seventeen of 28 lymphnode swellings responded to NAIC. Six of the 14 stage III patients became operable. In the 19 surgical cases, pathologically complete responses were found in four. Twenty-eight of the 38 parametrial halves were free from cancer. No lymph node metastases were found in eight patients. Initial tumor volume was found to be an independent, significant determining factor of the response to NAIC. Patients with initial tumor volumes less than 80 cm{sup 3} had a significantly better estimated 5-year disease-free survival rate compared with those with larger tumors. Conclusion: NAIC for locally advanced cervical cancer is useful for preoperative tumor reduction.Tumor volume is a significant determining factor for the response to NAIC.« less
  • Purpose: To determine whether the exclusive use of radiotherapy (ERT) could be a treatment option after complete clinical response (cCR) to neoadjuvant chemotherapy (NCT) for early breast cancer (EBC). Methods and Materials: Between 1985 and 1999, 1,477 patients received NCT for EBC considered too large for primary conservative surgery. Of 165 patients with cCR, 65 patients were treated with breast surgery (with radiotherapy) and 100 patients were treated with ERT. Results: The two groups were comparable in terms of baseline characteristics, except for larger initial tumor sizes in the ERT group. There were no significant differences in overall, disease-free andmore » metastasis-free survival rates. Five-year and 10-year overall survival rates were 91% and 77% in the no-surgery group and 82% and 79% in the surgery group, respectively (p = 0.9). However, a nonsignificant trend toward higher locoregional recurrence rates (LRR) was observed in the no-surgery group (31% vs. 17% at 10 years; p = 0.06). In patients with complete responses on mammography and/or ultrasound, LRR were not significantly different (p = 0.45, 10-year LRR: 21% in surgery vs. 26% in ERT). No significant differences were observed in terms of the rate of cutaneous, cardiac, or pulmonary toxicities. Conclusions: Surgery is a key component of locoregional treatment for breast cancers that achieved cCR to NCT.« less
  • Purpose: The aim of this study was to investigate the role of postmastectomy radiation therapy in women with breast cancer who achieved a pathologic complete response (pCR) to neoadjuvant chemotherapy. Methods and Materials: We retrospectively identified 226 patients treated at our institution who achieved a pCR at surgery after receiving neoadjuvant chemotherapy. Of these, the 106 patients without inflammatory breast cancer who were treated with mastectomy were analyzed. The patients' clinical stages at diagnosis were I in 2%, II in 31%, IIIA in 30%, IIIB in 25%, and IIIC in 11% (American Joint Committee on Cancer 2003 system). Of themore » patients, 92% received anthracycline-based chemotherapy, and 38% also received a taxane. A total of 72 patients received postmastectomy radiation therapy, and 34 did not. The actuarial rates of local-regional recurrence (LRR) and survival of the two groups were compared using the log-rank test. Results: The median follow-up of surviving patients was 62 months. Use of radiation therapy did not affect the 10-year rates of LRR for patients with Stage I or II disease (the 10-year LRR rates were 0% for both groups). However, the 10-year LRR rate for patients with Stage III disease was significantly improved with radiation therapy (7.3% {+-} 3.5% with vs. 33.3% {+-} 15.7% without; p 0.040). Within this cohort, use of radiation therapy was also associated with improved disease-specific and overall survival. Conclusion: Postmastectomy radiation therapy provides a significant clinical benefit for breast cancer patients who present with clinical Stage III disease and achieve a pCR after neoadjuvant chemothearpy.« less
  • Purpose: Clinical and magnetic resonance imaging (MRI) characteristics at baseline and following chemoradiation therapy (CRT) most strongly associated with histopathologic response were investigated and survival outcomes evaluated in accordance with imaging and pathological response. Methods and Materials: Responders were defined as mrT3c/d-4 downstaged to ypT0-2 on pathology or low at risk mrT2 downstaged to ypT1 or T0. Multivariate logistic regression of baseline and posttreatment MRI: T, N, extramural venous invasion (EMVI), circumferential resection margin, craniocaudal length <5 cm, and MRI tumor height ≤5 cm were used to identify independent predictor(s) for response. An association between induction chemotherapy and EMVI statusmore » was analyzed. Survival outcomes for pathologic and MRI responders and nonresponders were analyzed. Results: Two hundred eighty-one patients were eligible; 114 (41%) patients were pathology responders. Baseline MRI negative EMVI (odds ratio 2.94, P=.007), tumor height ≤5 cm (OR 1.96, P=.02), and mrEMVI status change (positive to negative) following CRT (OR 3.09, P<.001) were the only predictors for response. There was a strong association detected between induction chemotherapy and ymrEMVI status change after CRT (OR 9.0, P<.003). ymrT0-2 gave a positive predictive value of 80% and OR of 9.1 for ypT0-2. ymrN stage accuracy of ypN stage was 75%. Three-year disease-free survival for pathology and MRI responders were similar at 80% and 79% and significantly better than poor responders. Conclusions: Tumor height and mrEMVI status are more important than baseline size and stage of the tumor as predictors of response to CRT. Both MRI- and pathologic-defined responders have significantly improved survival. “Good response” to CRT in locally advanced rectal cancer with ypT0-2 carries significantly better 3-year overall survival and disease-free survival. Use of induction chemotherapy for improving mrEMVI status and knowledge of MRI predictive factors could be taken into account in the pursuit of individualized neoadjuvant treatments for patients with rectal cancer.« less