MRI Radiomics Signature as a Potential Biomarker for Predicting KRAS Status in Locally Advanced Rectal Cancer Patients

Abstract

Background and PurposeLocally advanced rectal cancer (LARC) is a heterogeneous disease with little information about KRAS status and image features. The purpose of this study was to analyze the association between T2 magnetic resonance imaging (MRI) radiomics features and KRAS status in LARC patients.Material and MethodsEighty-three patients with KRAS status information and T2 MRI images between 2012.05 and 2019.09 were included. Least absolute shrinkage and selection operator (LASSO) regression was performed to assess the associations between features and gene status. The patients were divided 7:3 into training and validation sets. The C-index and the average area under the receiver operator characteristic curve (AUC) were used for performance evaluation.ResultsThe clinical characteristics of 83 patients in the KRAS mutant and wild-type cohorts were balanced. Forty-two (50.6%) patients had KRAS mutations, and 41 (49.4%) patients had wild-type KRAS. A total of 253 radiomics features were extracted from the T2-MRI images of LARC patients. One radiomic feature named X.LL_scaled_std, a standard deviation value of scaled wavelet-transformed low-pass channel filter, was selected from 253 features (P=0.019). The radiomics-based C-index values were 0.801 (95% CI: 0.772-0.830) and 0.703 (95% CI: 0.620-0.786) in the training and validation sets, respectively.ConclusionRadiomics features could differentiate KRAS status in LARC patients based on T2-MRI images. Further validation in a larger dataset is necessary in the future.

A Deep Learning Model Based on MRI and Clinical Factors Facilitates Noninvasive Evaluation of KRAS Mutation in Rectal Cancer

“…Beyond the morphological information of rectal cancer, more mineable data within the medical images have been extracted using machine learning such as radiomics and DL, which could reflect tumor heterogeneity 38–40 . Prior MRI‐based radiomics models reported by Meng et al and Zhang et al achieved moderate performance in evaluating KRAS status in rectal cancer with AUCs of 0.651 and 0.703 39,40 .…”

“…Beyond the morphological information of rectal cancer, more mineable data within the medical images have been extracted using machine learning such as radiomics and DL, which could reflect tumor heterogeneity. [38][39][40] Prior MRIbased radiomics models reported by Meng et al and Zhang et al achieved moderate performance in evaluating KRAS status in rectal cancer with AUCs of 0.651 and 0.703. 39,40 Similar results were found in our prior study focusing on the value of MRI-based hand-crafted radiomics in identifying KRAS mutation in rectal cancer, moderate performance with AUCs of 0.682 and 0.714 were observed in the internal and external validation datasets.…”

“…[38][39][40] Prior MRIbased radiomics models reported by Meng et al and Zhang et al achieved moderate performance in evaluating KRAS status in rectal cancer with AUCs of 0.651 and 0.703. 39,40 Similar results were found in our prior study focusing on the value of MRI-based hand-crafted radiomics in identifying KRAS mutation in rectal cancer, moderate performance with AUCs of 0.682 and 0.714 were observed in the internal and external validation datasets. 40 In this current study, our constructed image DL model showed better performance in both the development and testing datasets than our prior radiomics model, which may benefit from the end-to-end training under supervision of DL networks.…”

MRI‐Based Artificial Intelligence in Rectal Cancer

“…Finally, one radiomic feature named X. LL_scaled_std was selected. In the validation set, the radiomics‐based C‐index value was 0.703 38 . Furthermore, applying AI to predict genotyping could reduce the cost of testing and the time and expense of treatment 39 …”

Role of radiomics in the diagnosis and treatment of gastrointestinal cancer

“…In 2016, the National Comprehensive Cancer Network guidelines recommended that all patients with suspected or confirmed metastatic CRC should be tested for KRAS / NRAS / BRAF mutations, but this requires pathological tissue specimens. It is gratifying that some radiogenomics studies have shown that the radiomic characteristics of CT and MRI may help to predict the genotype of CRC tumors before surgery[ 93 - 95 ]. Yang et al [ 96 ] reported that CT radiomic characteristics were associated with KRAS / NRAS / BRAF mutations.…”