Dataset Information

Magnetic Resonance-Based Texture Analysis Differentiating KRAS Mutation Status in Rectal Cancer.

ABSTRACT:

Purpose

Mutation of the Kirsten Ras (KRAS) oncogene is present in 30%-40% of colorectal cancers and has prognostic significance in rectal cancer. In this study, we examined the ability of radiomics features extracted from T2-weighted magnetic resonance (MR) images to differentiate between tumors with mutant KRAS and wild-type KRAS.

Materials and methods

Sixty patients with primary rectal cancer (25 with mutant KRAS, 35 with wild-type KRAS) were retrospectively enrolled. Texture analysis was performed in all regions of interest on MR images, which were manually segmented by two independent radiologists. We identified potentially useful imaging features using the two-tailed t test and used them to build a discriminant model with a decision tree to estimate whether KRAS mutation had occurred.

Results

Three radiomic features were significantly associated with KRASmutational status (p < 0.05). The mean (and standard deviation) skewness with gradient filter value was significantly higher in the mutant KRAS group than in the wild-type group (2.04±0.94 vs. 1.59±0.69). Higher standard deviations for medium texture (SSF3 and SSF4) were able to differentiate mutant KRAS (139.81±44.19 and 267.12±89.75, respectively) and wild-type KRAS (114.55±29.30 and 224.78±62.20). The final decision tree comprised three decision nodes and four terminal nodes, two of which designated KRAS mutation. The sensitivity, specificity, and accuracy of the decision tree was 84%, 80%, and 81.7%, respectively.

Conclusion

Using MR-based texture analysis, we identified three imaging features that could differentiate mutant from wild-type KRAS. T2-weighted images could be used to predict KRAS mutation status preoperatively in patients with rectal cancer.

SUBMITTER: Oh JE

PROVIDER: S-EPMC6962487 | biostudies-literature | 2020 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:IntroductionAnti-EGFR targeted therapy is of increasing importance in advanced colorectal cancer and prior KRAS mutation testing is mandatory for therapy. However, at which occasions this should be performed is still under debate. We aimed to assess in patients with locally advanced rectal cancer whether there is intra-specimen KRAS heterogeneity prior to and upon preoperative chemoradiotherapy (CRT), and if there are any changes in KRAS mutation status due to this intervention.Materials and methodsKRAS mutation status analyses were performed in 199 tumor samples from 47 patients with rectal cancer. To evaluate the heterogeneity between different tumor areas within the same tumor prior to preoperative CRT, 114 biopsies from 34 patients (mean 3 biopsies per patient) were analyzed (pre-therapeutic intratumoral heterogeneity). For the assessment of heterogeneity after CRT residual tumor tissue (85 samples) from 12 patients (mean 4.2 tissue samples per patient) were analyzed (post-therapeutic intratumoral heterogeneity) and assessment of heterogeneity before and after CRT was evaluated in corresponding patient samples (interventional heterogeneity). Primer extension method (SNaPshot™) was used for initial KRAS mutation status testing for Codon 12, 13, 61, and 146. Discordant results by this method were reevaluated by using the FDA-approved KRAS Pyro Kit 24, V1 and the RAS Extension Pyro Kit 24, V1 Kit (therascreen® KRAS test).ResultsFor 20 (43%) out of the 47 patients, a KRAS mutation was detected. With 12 out of 20, the majority of these mutations affected codon 35. We did not obtained evidence that CRT results in changes of the KRAS mutation pattern. In addition, no intratumoral heterogeneity in the KRAS mutational status could be proven. This was true for both the biopsies prior to CRT and the resection specimens thereafter. The discrepancy observed in some samples when using the SNaPshot™ assay was due to insufficient sensitivity of this technique upon massive tumor regression by CRT as application of the therascreen® KRAS test revealed concordant results.ConclusionOur results indicate that the KRAS mutation status at the primary tumor site of rectal cancer is homogenous. Its assessment for therapeutic decisions is feasible in pre-therapeutic biopsies as well as in post-therapeutic resected specimens. The amount of viable tumor cells seems to be an important determinant for assay sensitivity and should thus be considered for selection of the analytical method.

Project description:Background: The preoperative diagnosis of phyllodes tumors (PTs) of the breast is critical to appropriate surgical treatment. However, reliable differentiation between PT and fibroadenoma (FA) remains difficult in daily clinical practice. The purpose of this study was to investigate the utility of breast MRI texture analysis for differentiating PTs from FAs. Materials and Methods: Forty-two PTs and 42 FAs were enrolled in this retrospective study. Clinical and conventional MRI features (CCMF) and MRI texture analysis were used to distinguish between PT and FA. Texture features were extracted from the axial short TI inversion recovery T2-weighted (T2W-STIR), T1-weighted pre-contrast, and two contrast-enhanced series (first contrast and third contrast). The Mann-Whitney U test was used to select statistically significant features of texture analysis and CCMF. Using a linear discriminant analysis, the most discriminative features were determined from statistically significant features. The K-nearest neighbor classifier and ROC curve were applied to evaluate the diagnostic performance. Results: With a higher classification accuracy (89.3%) and an AUC of 0.89, the texture features on T2W-STIR outperformed the texture features on other MRI sequences and CCMF. The AUC of the combination of CCMF with texture features on T2W-STIR was significantly higher than that of CCMF or texture features on T2W-STIR alone (p < 0.05). Based on the result of the classification accuracy (95.2%) and AUC (0.95), the diagnostic performance of the combination strategy performed better than texture features on T2W-STIR or CCMF separately. Conclusions: Texture features on T2W-STIR showed better diagnostic performance compared to CCMF for the distinction between PTs and FAs. After further validation of multi-institutional large datasets, MRI-based texture features may become a potential biomarker and be a useful medical decision tool in clinical trials having patients with breast fibroepithelial neoplasms.

Project description:ObjectivesTo compare the predictive performance of different radiomics signatures from multiparametric magnetic resonance imaging (mpMRI), including four sequences when used individually or combined, and to establish and validate an optimal nomogram for predicting perineural invasion (PNI) in rectal cancer (RC) patients.MethodsOur retrospective study included 279 RC patients without preoperative antitumor therapy (194 in the training dataset and 85 in the test dataset) who underwent preoperative mpMRI scan between January 2017 and January 2021. Among them, 72 cases were PNI-positive. Then, clinical and radiological variables were collected, including carcinoembryonic antigen (CEA), radiological tumour stage (T1-4), lymph node stage (N0-2) and so on. Quantitative radiomics features were extracted and selected from oblique axial T2-weighted imaging (T2WI), T1-weighted imaging (T1WI), apparent diffusion coefficient (ADC), and enhanced T1WI (T1CE) sequences. The clinical model was constructed by integrating the final selected clinical and radiological variables. The radiomics signatures included four single-sequence signatures and one fusion signature were built using the respective remaining optimized features. And the nomogram was constructed based on the independent predictors by using multivariable logistic regression. The area under curve (AUC), DeLong test, calibration curve, and decision curve analysis (DCA) were used to evaluate the performance.ResultsUltimately, 20 radiomics features were retained from the four sequences-T1WI (n = 4), T2WI (n = 5), ADC (n = 5), and T1CE (n = 6)-to construct four single-sequence radiomics signatures and one fusion radiomics signature. The fusion radiomics signature performed better than four single-sequence radiomics signatures and clinical model (AUCs of 0.835 and 0.773 vs. 0.680-0.737 and 0.666-0.709 in the training and test datasets, respectively). The nomogram constructed by incorporating CEA, tumour stage and rad-score performed best, with AUCs of 0.869 and 0.864 in the training and test datasets, respectively. Delong test showed that the nomogram was significantly different from the clinical model and four single-sequence radiomics signatures (P < 0.05). Moreover, calibration curves demonstrated good agreement, and DCA highlighted benefits of the nomogram.ConclusionsThe comprehensive nomogram can preoperatively and noninvasively predict PNI status, provide a convenient and practical tool for treatment strategy, and help optimize individualized clinical decision-making in RC patients.

Project description:INTRODUCTION:Oncogenic mutation within the KRAS gene represents a negative predictor for treatment response to anti-epidermal growth factor receptor (EGFR) in patients with colorectal cancer. Recently, we have shown no relevant heterogeneity for KRAS mutation status within and between pre- and posttherapeutic samples from the primary tumor in patients with locally advanced rectal cancer. The aim of this study was to evaluate the intertumoral heterogeneity of KRAS mutation status between the primary tumor and the corresponding metastasis or local recurrence in the similar cohort and to evaluate the ideal representative tissue for KRAS mutation testing. MATERIALS AND METHODS:KRAS mutation status was analyzed from 47 patients with locally advanced rectal cancer, which were enrolled in the CAO/ARO/AIO-94 or CAO/ARO/AIO-04 trial. Mutations in KRAS codons 12, 13, and 61 were analyzed by using the KRAS RGQ PCR Kit (therascreen® KRAS test). Six patients needed to be excluded due to incomplete follow up data. 11 patients showed a relapse of the disease during the follow up presented by distant metastases or local recurrence. DNA from representative areas of metastatic tissue was obtained from formalin-fixed paraffin-embedded specimens. RESULTS:The mean patient age was 64.13 ± 10.64 years. In total, 19 patients showed a KRAS mutation (46.34%) in the primary tumor. Of the eleven patients with a metastatic disease or local recurrence, five patients showed a KRAS mutation whereas six patients had a KRAS wildtype status. Metastatic localizations included the liver (n = 2), lung (n = 4), local recurrence (n = 1), liver + lung (n = 3), lung + local recurrence (n = 1). For these eleven patients with paired data available for the primary tumor and metastatic tissue, a significant KRAS mutation status concordance was detected in 81.18% (9/11) of the patients (p = 0.03271). Only two patients showed intertumoral heterogeneity, which harbored in one patient a KRAS G12C mutation status in the primary tumor, but a G12V KRAS mutation status in the corresponding lung lesion, and in the other patient a G12A mutation in the primary lesion and a WT in the lung metastasis. CONCLUSIONS:We show a significant concordance of the KRAS mutation status between tumor samples obtained from the primary tumor and the corresponding metastasis and/ or local recurrence in patients with rectal cancer indicating no relevant intertumoral heterogeneity. Our data suggest that sampling either the primary (pre- or posttherapeutical tumor tissue) or metastatic lesion may be valid for the initial evaluation of KRAS mutation status predicting the response to anti-EGFR treatment and guiding clinical decisions.

Project description:BackgroundBreast Cancer (BC) is a highly heterogeneous and complex disease. Personalized treatment options require the integration of multi-omic data and consideration of phenotypic variability. Radiogenomics aims to merge medical images with genomic measurements but encounter challenges due to unpaired data consisting of imaging, genomic, or clinical outcome data. In this study, we propose the utilization of a well-trained conditional generative adversarial network (cGAN) to address the unpaired data issue in radiogenomic analysis of BC. The generated images will then be used to predict the mutations status of key driver genes and BC subtypes.MethodsWe integrated the paired MRI and multi-omic (mRNA gene expression, DNA methylation, and copy number variation) profiles of 61 BC patients from The Cancer Imaging Archive (TCIA) and The Cancer Genome Atlas (TCGA). To facilitate this integration, we employed a Bayesian Tensor Factorization approach to factorize the multi-omic data into 17 latent features. Subsequently, a cGAN model was trained based on the matched side-view patient MRIs and their corresponding latent features to predict MRIs for BC patients who lack MRIs. Model performance was evaluated by calculating the distance between real and generated images using the Fréchet Inception Distance (FID) metric. BC subtype and mutation status of driver genes were obtained from the cBioPortal platform, where 3 genes were selected based on the number of mutated patients. A convolutional neural network (CNN) was constructed and trained using the generated MRIs for mutation status prediction. Receiver operating characteristic area under curve (ROC-AUC) and precision-recall area under curve (PR-AUC) were used to evaluate the performance of the CNN models for mutation status prediction. Precision, recall and F1 score were used to evaluate the performance of the CNN model in subtype classification.ResultsThe FID of the images from the well-trained cGAN model based on the test set is 1.31. The CNN for TP53, PIK3CA, and CDH1 mutation prediction yielded ROC-AUC values 0.9508, 0.7515, and 0.8136 and PR-AUC are 0.9009, 0.7184, and 0.5007, respectively for the three genes. Multi-class subtype prediction achieved precision, recall and F1 scores of 0.8444, 0.8435 and 0.8336 respectively. The source code and related data implemented the algorithms can be found in the project GitHub at https://github.com/mattthuang/BC_RadiogenomicGAN .ConclusionOur study establishes cGAN as a viable tool for generating synthetic BC MRIs for mutation status prediction and subtype classification to better characterize the heterogeneity of BC in patients. The synthetic images also have the potential to significantly augment existing MRI data and circumvent issues surrounding data sharing and patient privacy for future BC machine learning studies.