Search

Background: The Node Reporting and Data System (Node-RADS) is a recently proposed classification system for the categorization of lymph nodes in radiological images. This study was conducted to retrospectively evaluate the diagnostic accuracy of the Node-RADS score for metastatic cervical lymph nodes on magnetic resonance imaging (MRI) of patients with nasopharyngeal carcinoma (NPC). Methods: We retrospectively analyzed cervical lymph nodes of NPC cases. Two radiologists independently evaluated each lymph node on the MRI scans using Node-RADS. Interobserver agreement between 2 radiologists for Node-RADS score assessment was evaluated by linear weighted kappa statistics. The correlation between metastasis and the Node-RADS score of each lymph node was analyzed using multivariate regression analysis. To investigate the diagnostic performance of the Node-RADS score, we further conducted receiver operating characteristic curve analysis. Correspondently, the sensitivity, specificity, positive predictive value, and negative predictive value of each different cutoff (>1, >2, >3, and >4) were computed. Results: In all, 119 patients with NPC were assessed, including 203 cervical lymph nodes consisting of 140 (69%) of 203 metastatic and 63 (31%) of 203 benign. The kappa agreement between the 2 readers for the Node-RADS score was 0.863 (95% CI = 0.830-0.897, P <.001). Node-RADS score on MRI scan was shown to be an independent predictive factor of lymph node metastasis after multivariate regression analysis (odds ratio [OR] = 6.745, 95% CI = 3.964-11.474, P <.001). Node-RADS achieved an area under the curve (AUC) of 0.950 (95% CI = 0.921-0.979) in diagnosing metastatic lymph nodes. When Node-RADS >2 was identified as the best cutoff based on balanced values, the sensitivity and positive predictive value were 0.92 and 0.94, respectively. Conclusions: Our study suggests that the Node-RADS score has high accuracy in predicting NPC cervical lymph node metastasis. Nevertheless, this conclusion requires confirmation in a larger cohort of patients with NPC. [ABSTRACT FROM AUTHOR]

Colorectal cancer is the third most prevalent cancer worldwide, and its treatment has been a demanding clinical problem. Beyond traditional surgical therapy and chemotherapy, newly revealed molecular mechanisms diversify therapeutic approaches for colorectal cancer. However, the selection of personalized treatment among multiple treatment options has become another challenge in the era of precision medicine. Artificial intelligence has recently been increasingly investigated in the treatment of colorectal cancer. This narrative review mainly discusses the applications of artificial intelligence in the treatment of colorectal cancer patients. A comprehensive literature search was conducted in MEDLINE, EMBASE, and Web of Science to identify relevant papers, resulting in 49 articles being included. The results showed that, based on different categories of data, artificial intelligence can predict treatment outcomes and essential guidance information of traditional and novel therapies, thus enabling individualized treatment strategy selection for colorectal cancer patients. Some frequently implemented machine learning algorithms and deep learning frameworks have also been employed for long-term prognosis prediction in patients with colorectal cancer. Overall, artificial intelligence shows encouraging results in treatment strategy selection and prognosis evaluation for colorectal cancer patients. [ABSTRACT FROM AUTHOR]