RESUMEN
@#Objective To establish a machine learning model based on computed tomography (CT) radiomics for preoperatively predicting invasive degree of lung ground-glass nodules (GGNs). Methods We retrospectively analyzed the clinical data of GGNs patients whose solid component less than 3 cm in the Department of Thoracic Surgery of Shanghai Pulmonary Hospital from March 2021 to July 2021 and the First Hospital of Lanzhou University from January 2019 to May 2022. The lesions were divided into pre-invasiveness and invasiveness according to postoperative pathological results, and the patients were randomly divided into a training set and a test set in a ratio of 7∶3. Radiomic features (1 317) were extracted from CT images of each patient, the max-relevance and min-redundancy (mRMR) was used to screen the top 100 features with the most relevant categories, least absolute shrinkage and selection operator (LASSO) was used to select radiomic features, and the support vector machine (SVM) classifier was used to establish the prediction model. We calculated the area under the curve (AUC), sensitivity, specificity, accuracy, negative predictive value, positive predictive value to evaluate the performance of the model, drawing calibration and decision curves of the prediction model to evaluate the accuracy and clinical benefit of the model, analyzed the performance in the training set and subgroups with different nodule diameters, and compared the prediction performance of this model with Mayo and Brock models. Two primary thoracic surgeons were required to evaluate the invasiveness of GGNs to investigate the clinical utility of the mode. Results A total of 400 patients were divided into the training set (n=280) and the test set (n=120) according to the admission criteria. There were 267 females and 133 males with an ……
RESUMEN
Accurately predicting the risk of mediastinal lymph node metastasis before surgery is of great significance for tumor staging, treatment plan decision, and prognosis evaluation in patients with non-small cell lung cancer(NSCLC). Traditional imaging methods such as CT, MRI and PET/CT are currently the most commonly used clinical methods in clinical evaluation of lymph node status. However, it is subjective to judge lymph node metastasis only by the change of image morphological characteristics, and inflammatory lymphadenopathy will also lead to a high false positive rate. The clinicopathological characteristics obtained by analyzing the clinical data of patients with NSCLC can improve the accuracy of lymph node metastasis prediction to a certain extent. The clinical prediction model based on medical images combined with the clinical characteristics of patients can provide more intuitive and rational information for doctors and patients, but the performance and applicability of the model will inevitably decrease due to changes in disease risk factors and treatment measures. In recent years, with the significant improvement of image analysis technology and computing ability, radiomics models based on medical images can deeply dig into the data in radiological images for quantitative analysis, providing new ideas for predicting mediastinal lymph node metastasis in NSCLC patients, which has attracted extensive attention at home and abroad. This article reviews the progress and makes prospects of the above methods in the prediction of mediastinal lymph node metastasis in NSCLC.