Dataset Information

MRI Radiomics for Prediction of Tumor Response and Downstaging in Rectal Cancer Patients after Preoperative Chemoradiation.

ABSTRACT: Purpose: This study aimed to investigate radiomic features extracted from magnetic resonance imaging (MRI) scans performed before and after neoadjuvant chemoradiotherapy (nCRT) in predicting response of locally advanced rectal cancer (LARC).

Methods and materials: Thirty-nine patients who underwent nCRT for LARC were included, with 294 radiomic features extracted from MRI that was performed before (pre-CRT) and 6 to 8 weeks after completing nCRT (post-CRT). Based on tumor regression grade (TRG), 26 patients were classified as having a histopathologic good response (GR; TRG 0-1) and 13 as non-GR (TRG 2-3). Tumor downstaging (T-downstaging) occurred in 25 patients. Univariate analyses were performed to assess potential radiomic and delta-radiomic predictors for TRG in pathologic complete response (pCR) versus non-pCR, GR versus non-GR, and T-downstaging. The support vector machine-based multivariate model was used to select the best predictors for TRG and T-downstaging.

Results: We identified 13 predictive features for pCR versus non-pCR, 14 for GR versus non-GR, and 16 for T-downstaging. Pre-CRT gray-level run length matrix nonuniformity, pre-CRT neighborhood intensity difference matrix (NIDM) texture strength, and post-CRT NIDM busyness predicted all 3 treatment responses. The best predictor for GR versus non-GR was pre-CRT global minimum combined with clinical N stage in the multivariate analysis. The best predictor for T-downstaging was the combination of pre-CRT gray-level co-occurrence matrix correlation, NIDM-texture strength, and gray-level co-occurrence matrix variance. The pre-CRT, post-CRT, and delta radiomic-based models had no significant difference in predicting all 3 responses.

Conclusions: Pre-CRT MRI, post-CRT MRI, and delta radiomic-based models have the potential to predict tumor response after nCRT in LARC. These data, if validated in larger cohorts, can provide important predictive information to aid in clinical decision making.

SUBMITTER: Chen H

PROVIDER: S-EPMC7718560 | biostudies-literature | 2020 Nov-Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

MRI Radiomics for Prediction of Tumor Response and Downstaging in Rectal Cancer Patients after Preoperative Chemoradiation.

Chen Haihui H Shi Liting L Nguyen Ky Nam Bao KNB Monjazeb Arta M AM Matsukuma Karen E KE Loehfelm Thomas W TW Huang Haixin H Qiu Jianfeng J Rong Yi Y

Advances in radiation oncology 20200511 6

<h4>Purpose</h4>This study aimed to investigate radiomic features extracted from magnetic resonance imaging (MRI) scans performed before and after neoadjuvant chemoradiotherapy (nCRT) in predicting response of locally advanced rectal cancer (LARC).<h4>Methods and materials</h4>Thirty-nine patients who underwent nCRT for LARC were included, with 294 radiomic features extracted from MRI that was performed before (pre-CRT) and 6 to 8 weeks after completing nCRT (post-CRT). Based on tumor regression ...[more]

PMID: 33305090

Similar Datasets

Project description:BackgroundTumor response to neoadjuvant therapy is heterogenous and prognostically important for locally advanced rectal adenocarcinoma (LARC) patients. Commonly applied response classification approaches including tumor regression grading (TRG) and TN downstaging can be discordant. The aim of this study is to compare the prognostic value of discordant tumor response measurement categorized according to the AJCC/CAP TRG schema and ypTN stage.MethodsThis is a single-center retrospective review of 90 consecutive patients with stage II-III rectal cancer receiving neoadjuvant chemoradiation (nCRT), total mesorectal excision (TME) and adjuvant chemotherapy (ACT) between 2007 and 2018. Two pathologists re-examined each case to assign a consensus AJCC TRG. A Cox proportional hazards ratio model assessed the effect of patient, tumor, and treatment factors on disease-free survival (DFS).ResultsMedian follow-up after surgery was 46 months (95% CI: 41-50 months). Median age at diagnosis was 55 years (range: 27-80). Most patients were male (58%) and Caucasian (92%) with clinical stage III disease (68%). Seventy-three patients (81%) underwent low anterior resection (LAR), 17 (19%) underwent abdominoperineal resection (APR). The median interval from completion of nCRT to surgery was 62 days (IQR: 56-70 days). The 4-year OS, DFS, and LC was 92.4%, 74.4%, and 90.2%, respectively. In the multivariate analysis, ypTN downstaging was not prognostically significant; however, AJCC TRG score 3 (minimal tumor response to treatment) was strongly predictive for inferior DFS (3-year DFS 79% vs. 25%, P<0.001). Patients with TRG 3 had a significantly higher risk of both local (75% vs. 5%) and distant failure (75% vs. 19%).ConclusionsMinimal tumor response to neoadjuvant therapy, AJCC TRG 3, irrespective of ypTN downstaging, is a pattern of residual disease that is at highest risk for recurrence. Response categorization discrepancies may be partly explained by alternative patterns of residual disease, including tumor fragmentation, and may be best reflected by TRG. The optimal tumor response categorization method requires further study to best stratify patient risk and management.

Dataset Information

MRI Radiomics for Prediction of Tumor Response and Downstaging in Rectal Cancer Patients after Preoperative Chemoradiation.

Publications

MRI Radiomics for Prediction of Tumor Response and Downstaging in Rectal Cancer Patients after Preoperative Chemoradiation.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets