Fig. 6From: Radiomic signature based on CT imaging to distinguish invasive adenocarcinoma from minimally invasive adenocarcinoma in pure ground-glass nodules with pleural contacta and b. The left image is the model heatmap of training samples. The right shows the model heatmap in testing samples. Unsupervised clustering of patients (N = 61) on the y-axis and expression of radiomics features (N = 7) on the x-axis reveals clusters of patients with similar radiomics expression patterns. There was a significant association of radiomics feature expression patterns with the two different P-pGGN groups. The indicators corresponding to the dark red squares are more predictiveBack to article page