Multi-parametric magnetic resonance imaging assessment of whole tumour heterogeneity for chemoradiotherapy response prediction in rectal cancer

Abstract

Background and purpose: Prediction of chemoradiotherapy response (CRT) in locally advanced rectal cancer would enable stratification of management. The purpose was to prospectively evaluate multi-parametric magnetic resonance imaging (MRI) assessment of tumour heterogeneity combining diffusion weighted imaging (DWI) and dynamic contrast enhanced (DCE) MRI for the prediction of CRT response in locally advanced rectal cancer. Materials and methods: Patients with Stage II or III rectal adenocarcinoma undergoing neoadjuvant CRT and surgery underwent MRI (DWI and DCE) before, during (week 3), and after CRT (1 week before surgery). Patients with histopathology tumour regression grade (TRG) 0-1 were classified as responders, and TRG 2-3 were classified as non-responders. A whole tumour voxel-wise technique was used to produce apparent diffusion coefficient (ADC) and K trans (Tofts model) histograms derived from DWI and DCE-MRI, respectively. Logistic regression was used to predict response status for ADC and K trans quantiles. Results: Thirty-three patients were included in this analysis; 16 responders, and 17 non-responders. On heterogeneity analysis, odds of being a responder were significantly higher after CRT (before surgery) for higher ADC 75th (p = 0.049) and ADC 90th (p = 0.034) percentile values. The K trans quantiles were lower in nonresponders than responders before and during CRT, and higher after CRT although no significant association with response status was observed (p ≥ 0.10). Conclusions: DWI-MRI after CRT (before surgery) incorporating a histogram analysis of whole tumour heterogeneity was predictive of CRT response in patients with locally advanced rectal cancer. DCE-MRI did not add value in response prediction. Clinical trial registration: Australian New Zealand Clinical Trials Registry (ANZCTR) number ACTRN12616001690448.

Dynamic Contrast-enhanced Magnetic Resonance Imaging Evaluation of Whole Tumour Perfusion Heterogeneity Predicts Distant Disease-free Survival in Locally Advanced Rectal Cancer

“…Although ADC after CRT in this study was found to be useful in predicting pathological response to CRT [21], ADC was not useful for predicting DFS. A study by Bakke et al [17] of 27 patients also found that ADC before CRT was not able to predict DFS.…”

“…The primary objective in this study, the correlation of MRI with CRT histopathological treatment response status, has been reported [20,21]. Our group found that ADC 75th and 90th quantile values after CRT were predictive of histopathological response status, with higher values predictive of response.…”

Artificial intelligence in multiparametric magnetic resonance imaging: A review

“…305,306,309 To better predict the disease progression, machine learning algorithms have been designed and applied to assist clinicians in analyzing patient information (some recent published papers are listed in Table 3). 190,193,230,[310][311][312][313][314][315][316][317][318][319][320][321] Recent disease risk prediction methods have mostly focused on head-and-neck cancer, 311,316 breast cancer, 190,193 rectal cancer, 312,313,315,319,321 brain cancer, 314,320 and liver disease, 317 For example, after stratifying glioblastoma patients were treated with chemoradiation therapy, 306 machine learning models were applied to patient OS time prediction. 305,306,309 Besides using mpMRI images, clinical profiles such as patient personal information, treatment factors, and genotypic-related features were combined for model training to improve the prediction accuracy.…”

Correlations of tumour permeability parameters with apparent diffusion coefficient in nasopharyngeal carcinoma

“…These permeability characteristics can be differentially visualised in parametric maps. As concurrent chemo-radiation is the standard treatment for locally advanced NPC patients, these parametric maps might be useful in monitoring angiogenic changes during chemo-radiation treatments [45] . Since we acquired the scans with an MR Simulator in which the patients were scanned in the same positions as their radiation treatment positions, the parametric maps had the same frame of reference as their radiation treatment plans.…”