A novel nomogram model to predict postoperative outcome of colorectal cancer lung metastasis patients

Unlike other distant metastases of colorectal cancer (CRC), lung metastases grow relatively slow, and patients with lung metastasses have superior prognosis. Therefore, treatment mode of metastases in other sites cannot be fully referred, and accurate prediction of outcomes of lung metastases of CRC patients remains challenging. A study at Fudan University (Shanghai, China) resulted in development of a nomogram model integrating deep learning-pathomics, radiomics, and immunoscore to predict postoperative outcome of colorectal cancer lung metastasis patients. The combined nomogram showed outstanding performance in predicting overall survival (AUC = 0.860) and disease-free survival (AUC = 0.875).