This repository provides the PyTorch implementation and checkpoint for VDPA, a variance-driven dual-path attention network for CT-based prediction of KRAS mutation status in non-small cell lung cancer.

VDPA integrates local sparse attention and learnable global aggregation through a variance-driven fusion mechanism. The released model uses three tumor-containing CT slices as input and produces a patient-level KRAS mutation probability.

Core configuration:

Install a CUDA-compatible PyTorch build if GPU inference is required.

Run the following command after downloading the repository:

Expected output:

The evaluation script expects NPY files arranged by class and patient:

Each .npy file should contain one three-slice CT input in [3, H, W] format. [H, W, 3] arrays are also supported and are transposed automatically.

Class labels:

Outputs:

Patient-level probability is computed by averaging mutation probabilities across all inputs belonging to the same patient.

The repository includes a helper script for preparing three-slice NPY inputs from the public TCIA NSCLC Radiogenomics collection:

The script reads TCIA metadata, selects CT series, extracts three axial CT slices according to the recorded tumor lobe zone, and writes NPY inputs using the same class-folder format as the evaluation script.

The model checkpoint is larger than GitHub's standard 100 MB file limit. Use Git LFS before committing the checkpoint:

Institutional CT data are not included in this repository. Public TCIA data should be obtained from The Cancer Imaging Archive according to its data access policy.

This code is released under the MIT License.