This research focuses on utilizing liver CT scans in colorectal carcinoma genomics mutation classification. The liver is the most affected organ by distant metastasis in colon-rectal cancer patients. The study proposes a deep learning-based exploration of classification approach from patient medical imaging. It establishes a pipeline for managing undersized datasets of available CT scans and a baseline study for genomics mutation diagnosis support for preemptive patient follow-up. The method can identify CRC RAS mutation family from CT images with a 0.73 F1 score.
Publication date: 26 Jan 2024
Project Page: Not provided
Paper: https://arxiv.org/pdf/2401.14206
