Noninvasive KRAS mutation estimation in colorectal cancer using a deep learning method based on CT imaging

Abstract

Background: The detection of Kirsten rat sarcoma viral oncogene homolog ( KRAS )gene mutations in colorectal cancer (CRC) is key to the optimal design of individualized therapeutic strategies. The noninvasive prediction of the KRAS status in CRC is challenging. Deep learning (DL) in medical imaging has shown its high performance in diagnosis, classification, and prediction in recent years. In this paper, we investigated predictive performance by using a DL method with a residual neural network ( ResNet ) to estimate the KRAS mutation status in CRC patients based on pre-treatment contrast-enhanced CT imaging. Methods: We have collected a dataset consisting of 157 patients with pathology-confirmed CRC who were divided into a training cohort (n = 117) and a testing cohort (n = 40). We developed an ResNet model that used portal venous phase CT images to estimate KRAS mutations in the axial, coronal, and sagittal directions of the training cohort and evaluated the model in the testing cohort. Several groups of expended region of interest （ROI）patches were generated for the ResNet model，to explore whether tissues around the tumor can contribute to cancer assessment. We also explored a radiomics model with the random forest classifier (RFC) to predict KRAS mutations and compared it with the DL model. Results: The ResNet model in the axial direction achieved the higher area under the curve (AUC) value (0.90) in the testing cohort and peaked at 0.93 with an input of “ROI and 20-pixel” surrounding area. AUC of radiomics model in testing cohorts were 0.818. In comparison, the ResNet model showed better predictive ability . Conclusions: Our experiments reveal that the computerized assessment of the pre-treatment CT images of CRC patients using a DL model has the potential to precisely predict KRAS mutations. This new model has the potential to assist in noninvasive KRAS mutation estimation. Keywords: Colorectal Neoplasm, Mutation, Deep Learning

Application of Massive Parallel Deep Learning Algorithm in the Prediction of Colorectal Carcinogenesis of Familial Polyposis

“…According to the method of dividing points by sample as a threshold, it can be inferred that the value of the recall rate is gradually increasing, but it is not strictly increasing, because as the dividing point moves to the right, it seems that the positive example is divided into positive examples. The more and the accuracy rate is gradually decreasing, not strictly decreasing [43]. As the division point moves, the positive examples are judged as more positive examples, and the negative examples are judged as more negative examples.…”

Development and Validation of Radiomics Signatures to Predict KRAS Mutation Status Based on Triphasic Enhanced Computed Tomography in Patients with Colorectal Cancer

“…However, these studies involved small sample sizes and lacked validation. Radiomics provides a variety of parameters for quantitative analysis, and these parameters have been widely used in cancer diagnosis, classi cation, and prediction 10 . A previous study demonstrated a signi cant correlation between a CT-based radiomics signature and KRAS/NRAS/BRAF mutations in CRC patients 11 .…”

Colorectal Cancer Disease Classification and Segmentation Using A Novel Deep Learning Approach

“…In existing methods, two datasets are publicly accessible: NCT-CRC-HE-100K and Colorectal Histology based Ensemble Deep Neural Network to Tumor in images of Colorectal Histology, a framework using a classifier of CNN model and a generator of Cycle GAN [14][15][16][17]. Mask R-CNN and performance evaluation with different modern convolutional neural networks (CNN) as its feature extractor for polyp segmentation and detection and an ensemble method depending on the dataset of MICCAI polyp detection, (NCT) the National Center for Tumor diseases data sets, to classify the CRC histopathological images, the ResNet-50 model and transfer learning was used.…”