Dataset Information

Delta-radiomics signature predicts treatment outcomes after preoperative chemoradiotherapy and surgery in rectal cancer.

ABSTRACT:

Background

To develop and compare delta-radiomics signatures from 2- (2D) and 3-dimensional (3D) features that predict treatment outcomes following preoperative chemoradiotherapy (CCRT) and surgery for locally advanced rectal cancer.

Methods

In total, 101 patients (training cohort, n?=?67; validation cohort, n?=?34) with locally advanced rectal adenocarcinoma between 2008 and 2015 were included. We extracted 55 features from T2-weighted magnetic resonance imaging (MRI) scans. Delta-radiomics feature was defined as the difference in radiomics feature before and after CCRT. Signatures were developed to predict local recurrence (LR), distant metastasis (DM), and disease-free survival (DFS) from 2D and 3D features. The least absolute shrinkage and selection operator regression was used to select features and build signatures. The delta-radiomics signatures and clinical factors were integrated into Cox regression analysis to determine if the signatures were independent prognostic factors.

Results

The radiomics signatures for LR, DM, and DFS were developed and validated using both 2D and 3D features. Outcomes were significantly different in the low- and high-risk patients dichotomized by optimal cutoff in both the training and validation cohorts. In multivariate analysis, the signatures were independent prognostic factors even when considering the clinical parameters. There were no significant differences in C-index from 2D vs. 3D signatures.

Conclusions

This is the first study to develop delta-radiomics signatures for rectal cancer. The signatures successfully predicted the outcomes and were independent prognostic factors. External validation is warranted to ensure their performance.

SUBMITTER: Jeon SH

PROVIDER: S-EPMC6417065 | biostudies-literature | 2019 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Delta-radiomics signature predicts treatment outcomes after preoperative chemoradiotherapy and surgery in rectal cancer.

Jeon Seung Hyuck SH Song Changhoon C Chie Eui Kyu EK Kim Bohyoung B Kim Young Hoon YH Chang Won W Lee Yoon Jin YJ Chung Joo-Hyun JH Chung Jin Beom JB Lee Keun-Wook KW Kang Sung-Bum SB Kim Jae-Sung JS

Radiation oncology (London, England) 20190312 1

<h4>Background</h4>To develop and compare delta-radiomics signatures from 2- (2D) and 3-dimensional (3D) features that predict treatment outcomes following preoperative chemoradiotherapy (CCRT) and surgery for locally advanced rectal cancer.<h4>Methods</h4>In total, 101 patients (training cohort, n = 67; validation cohort, n = 34) with locally advanced rectal adenocarcinoma between 2008 and 2015 were included. We extracted 55 features from T2-weighted magnetic resonance imaging (MRI) scans. Delt ...[more]

PMID: 30866965

Similar Datasets

Project description:The incorporation of chemoradiation prior to resection of the tumour has revolutionized the management of locally advanced rectal cancer. However, a large proportion of these patients are resistant to preoperative treatment schedule. We recently reported that c-Myc gene expression correlates negatively with this resistance in patients with rectal cancer. In this study, we carried out integrated analysis of miRNA and mRNA expression profiling in 45 pre-treatment rectal tumour. Further, expression of miRNAs and c-Myc, and their relationship with clinicopathological factors and patient survival was analysed. As a result, we found that 12 miRNAs were differentially expressed between responder and non-responder rectal cancer patients. Functional classification revealed an association between differentially expressed miRNAs and c-Myc. Subsequent quantitative real-time PCR results showed that both, miRNA-148 and miRNA-375 levels were significantly lower in responder compared to non-responder patients. Notably, the higher level of miRNA-375 was significantly negatively correlated with c-Myc. These results suggest that miRNA-375 and its targeted c-Myc play an important role as predictive biomarker of response to neoadjuvant treatment in patients with locally advanced rectal cancer, but still not suitable for prognosis. Pre-treatment biopsies of 22 patients with LARC were prospectively collected and freshly frozen according to an institutional board-approved protocol. Tumour response was assessed in surgical specimens by pathological examination based on the semi-quantitative tumour regression grading (TRG) system described by Mandard in 1994[36]: TRG1 and TRG2 scores were considered responders, whereas TRG3, TRG4, and TRG5 were classified as non-responders. The inclusion criteria were: histologically proven rectal tumour at a clinical stage UICC II-III (cT3-4/and or N positive), following endorectal ultrasound and/or MRI scan. Patients were excluded if they had the tumour located above 13 cm from the anal verge by rigid rectoscopy, synchronic colonic cancer assessed by colonoscopy, distant metastases by 18FDG PET-CT scan, and suspicion of hereditary colorectal cancer. All patients subsequently received a total dose of 50.4Gy of radiation (28 fractions of 1.8Gy) associated with capecitabine (oral form of 5-FU) with or without oxaliplatine, according to our Hospital Clinical Practice Guidelines. Standardized Surgery was performed, including total mesorectal excision, following an interval of 8-10 weeks after completion of CT/RT.

Dataset Information

Delta-radiomics signature predicts treatment outcomes after preoperative chemoradiotherapy and surgery in rectal cancer.

Background

Methods

Results

Conclusions

Publications

Delta-radiomics signature predicts treatment outcomes after preoperative chemoradiotherapy and surgery in rectal cancer.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets