Radiomic features analysis in computed tomography images of lung nodule classification

Abstract

Purpose: Radiomics, which extract large amount of quantification image features from diagnostic medical images had been widely used for prognostication, treatment response prediction and cancer detection. The treatment options for lung nodules depend on their diagnosis, benign or malignant. Conventionally, lung nodule diagnosis is based on invasive biopsy. Recently, radiomics features, a non-invasive method based on clinical images, have shown high potential in lesion classification, treatment outcome prediction.

Methods: Lung nodule classification using radiomics based on Computed Tomography (CT) image data was investigated and a 4-feature signature was introduced for lung nodule classification. Retrospectively, 72 patients with 75 pulmonary nodules were collected. Radiomics feature extraction was performed on non-enhanced CT images with contours which were delineated by an experienced radiation oncologist.

Result: Among the 750 image features in each case, 76 features were found to have significant differences between benign and malignant lesions. A radiomics signature was composed of the best 4 features which included Laws_LSL_min, Laws_SLL_energy, Laws_SSL_skewness and Laws_EEL_uniformity. The accuracy using the signature in benign or malignant classification was 84% with the sensitivity of 92.85% and the specificity of 72.73%.

Conclusion: The classification signature based on radiomics features demonstrated very good accuracy and high potential in clinical application.

Fig 1. Radiomics analysis workflow.

First, the clinical CT images of malignant and benign pulmonary nodules were collected. Second, image segmentation was used to delineate the pulmonary nodules. Next, the image features were extracted by the automated high-throughput feature analysis algorithm. Finally, the statistical analysis was applied and the sequential forward search was used for feature selection for the classification of lung nodules.

Fig 2. Examples of lung lesion segmentation.

Original CT image (a) and target segmentation (b) of a benign lung lesion (tuberculosis) in patient’s left upper lobe. Another original CT image (c) and target segmentation (d) of a malignant lung tumor (adenocarcinoma) in patient’s left upper lobe.

Fig 3. Heat map of the selected 4-features radiomics signature.

Radiomics features expression with Z-score. Hierarchical clustering of lung lesions is on the x axis (n = 75, B = Benign, M = Malignant). The 4-feature radiomics signature expression is on the y axis.

Fig 4. Prediction performance of the three different feature sets.

A leave-one-out cross-validation was performed and the accuracies in the malignant and benign nodules were plotted. The randomly selected 4 features group was examined in a 1000-time permutation test.