Delta Radiomics Analysis for Local Control Prediction in Pancreatic Cancer Patients Treated Using Magnetic Resonance Guided Radiotherapy

Abstract

The aim of this study is to investigate the role of Delta Radiomics analysis in the prediction of one-year local control (1yLC) in patients affected by locally advanced pancreatic cancer (LAPC) and treated using Magnetic Resonance guided Radiotherapy (MRgRT). A total of 35 patients from two institutions were enrolled: A 0.35 Tesla T2*/T1 MR image was acquired for each case during simulation and on each treatment fraction. Physical dose was converted in biologically effective dose (BED) to compensate for different radiotherapy schemes. Delta Radiomics analysis was performed considering the gross tumour volume (GTV) delineated on MR images acquired at BED of 20, 40, and 60 Gy. The performance of the delta features in predicting 1yLC was investigated in terms of Wilcoxon Mann–Whitney test and area under receiver operating characteristic (ROC) curve (AUC). The most significant feature in predicting 1yLC was the variation of cluster shade calculated at BED = 40 Gy, with a p-value of 0.005 and an AUC of 0.78 (0.61–0.94). Delta Radiomics analysis on low-field MR images might play a promising role in 1yLC prediction for LAPC patients: further studies including an external validation dataset and a larger cohort of patients are recommended to confirm the validity of this preliminary experience.

Delta radiomics analysis of Magnetic Resonance guided radiotherapy imaging data can enable treatment response prediction in pancreatic cancer

“…Previous reports showed that radiomics may potentially be used to quantify image textures in MRgRT data, and relate them to outcome in pancreatic [ 12 ] and rectal cancers [ 10 , 11 ] both in static and delta radiomic setting. Given the large number of features tested in small patient cohorts, as well as lack of image normalization, the results presented will require further validation.…”

“…This will soon allow for well-powered retrospective studies with 100 s of patients to be conducted. The uniformity of the acquisition settings between patients and imaging centers, especially on the 0.35T systems, will further accelerate the process, allowing for simpler multi-center collaborations, as already reported on a small scale [ 11 ]. Open access to the analytical pipeline developed in this study, including the necessary image processing and quantification code, may contribute to further simplification of the process.…”

“…Employing automated high-throughput image feature extraction methods to quantify subtle patterns in the daily images, radiomic analyses [ 8 ] have shown great promise for disease prognosis or prediction of treatment response, including radiotherapy [ 9 ]. In early proof-of-concept MRgRT radiomic studies, Boldrini et al [ 10 ] considered changes in extracted features using ratios pre- to post-treatment in 16 rectal cancer patients treated on a 0.35T MRgRT system showing promise for response correlation, later they followed up with another study in pancreatic cancer [ 11 ]. Simpson et al [ 12 ] looked at static, absolute values of radiomic features derived from 0.35T MRgRT scans for response prediction in 20 pancreatic cancer patients.…”

A Predictive Model of 2yDFS During MR-Guided RT Neoadjuvant Chemoradiotherapy in Locally Advanced Rectal Cancer Patients

“…All the imported MR images were processed using signal normalization as described in similar experiences dealing with the same topic ( 21 , 32 ).…”

“…Besides the blatant advantages related to image quality, the potential role of online MRI as predictors has been investigated in different frameworks ( 16 , 18 , 19 , 21 ).…”