# Identification of KRAS mutation in rectal cancer based on a 2.5D deep learning model

## TL;DR

A 2.5D deep learning model can accurately identify KRAS mutations in rectal cancer patients using CT scans, offering a non-invasive alternative to traditional methods.

## Contribution

The study introduces a 2.5D deep transfer learning model for non-invasive detection of KRAS mutations in rectal cancer.

## Key findings

- The 2.5D deep learning model outperformed traditional radiomic models in distinguishing KRAS mutant and wild-type rectal cancer cases.
- The best-performing 2.5D model achieved an AUC of 0.913 in the validation set.
- The model provides a non-invasive preoperative method for assessing KRAS mutation status.

## Abstract

To explore the utility of a 2.5D deep transfer learning (DTL) model for distinguishing between Kirsten rat sarcoma viral oncogene (KRAS) mutant and wild-type phenotypes in patients with rectal cancer (RC).

We retrospectively analyzed 138 patients with pathologically confirmed RC who underwent next-generation sequencing to detect KRAS mutations. Among these, 43 KRAS mutant and 95 wild-type cases were enrolled and divided randomly into a training set (30 mutant, 66 wild-type) and a validation set (13 mutant, 29 wild-type) in a 7:3 ratio. Tumor regions of interest (ROIs) were delineated manually slice-by-slice in thin-section arterial-phase computed tomography images. DTL and radiomic features were extracted from ROIs using 2.5D deep learning and traditional radiomic approaches, respectively. After feature-dimensionality reduction and selection, six machine learning models were employed to construct radiomic models and 2.5D deep learning models. The diagnostic performance of each model was evaluated using the area under the receiver operating characteristic curve (AUC).

After feature selection, 10 radiomic features and 17 DTL features were included for model construction. The AUCs for the radiomic models ranged from 0.808–0.988 in the training set and 0.521–0.672 in the validation set, with the XGBoost classifier achieving the optimal performance (AUC = 0.672) in the validation set. The AUCs for the 2.5D deep learning models ranged from 0.950–1.000 in the training set and 0.788–0.913 in the validation set, with the support vector machine classifier demonstrating the best diagnostic efficacy (AUC = 0.913) in the validation set.

A 2.5D deep learning model can effectively distinguish between KRAS mutant and KRAS wild-type RC, outperforming traditional radiomic models. It provides a novel non-invasive approach for the preoperative assessment of KRAS mutation status.