| Sumario: | Background: The Ki-67 antigen, a marker of cell proliferation, serves as a biomarker for assessing tumor malignancy. However, measuring Ki-67 levels through immunohistochemistry is often challenging due to difficulties in specimen collection and individual health issues. Radiological analysis has emerged as a potential alternative for predicting Ki-67 levels, although its accuracy has been limited. This study aims to enhance the prediction of Ki-67 levels using chest X-rays by employing a refined approach that combines detailed, manually delineated radiological features with conventional imaging characteristics. Methods: This study collected X-ray images and Ki-67 expression data from 109 patients diagnosed with Non-Small Cell Lung Cancer (NSCLC). Seven radiological features related to tumor progression were annotated on each image by clinical professionals. Tumor areas were delineated using Python, resulting in the generation of 5 types of data from these regions. Data integration facilitated the development of predictive models utilizing Logistic Regression (LR), Support Vector Machine (SVM), Random Forest (RF), and Deep Neural Networks (DNN), with feature selection processes applied. Results: Using the RF, 8 predictive features were selected from the datasets, of which 7 exhibited a linear correlation with Ki-67 levels (Mantel-Haenszel test, P <.05). The model demonstrated robust performance metrics: Accuracy: 0.818, Precision: 0.823, Recall: 0.849, and F1 Score: 0.783. Conclusions: This research underscores the effectiveness of integrating specific radiological features, manually delineated regions of interest (ROIs), with traditional imaging characteristics and machine learning techniques. This approach significantly enhances the predictive accuracy of chest X-rays for Ki-67 levels, offering a non-invasive method for Ki-67 estimation.
|
|---|