Phenotyping the Histopathological Subtypes of Non-Small-Cell Lung Carcinoma: How Beneficial Is Radiomics?

Abstract

The aim of this study was to investigate the usefulness of radiomics in the absence of well-defined standard guidelines. Specifically, we extracted radiomics features from multicenter computed tomography (CT) images to differentiate between the four histopathological subtypes of non-small-cell lung carcinoma (NSCLC). In addition, the results that varied with the radiomics model were compared. We investigated the presence of the batch effects and the impact of feature harmonization on the models' performance. Moreover, the question on how the training dataset composition influenced the selected feature subsets and, consequently, the model's performance was also investigated. Therefore, through combining data from the two publicly available datasets, this study involves a total of 152 squamous cell carcinoma (SCC), 106 large cell carcinoma (LCC), 150 adenocarcinoma (ADC), and 58 no other specified (NOS). Through the matRadiomics tool, which is an example of Image Biomarker Standardization Initiative (IBSI) compliant software, 1781 radiomics features were extracted from each of the malignant lesions that were identified in CT images. After batch analysis and feature harmonization, which were based on the ComBat tool and were integrated in matRadiomics, the datasets (the harmonized and the non-harmonized) were given as an input to a machine learning modeling pipeline. The following steps were articulated: (i) training-set/test-set splitting (80/20); (ii) a Kruskal-Wallis analysis and LASSO linear regression for the feature selection; (iii) model training; (iv) a model validation and hyperparameter optimization; and (v) model testing. Model optimization consisted of a 5-fold cross-validated Bayesian optimization, repeated ten times (inner loop). The whole pipeline was repeated 10 times (outer loop) with six different machine learning classification algorithms. Moreover, the stability of the feature selection was evaluated. Results showed that the batch effects were present even if the voxels were resampled to an isotropic form and whether feature harmonization correctly removed them, even though the models' performances decreased. Moreover, the results showed that a low accuracy (61.41%) was reached when differentiating between the four subtypes, even though a high average area under curve (AUC) was reached (0.831). Further, a NOS subtype was classified as almost completely correct (true positive rate ~90%). The accuracy increased (77.25%) when only the SCC and ADC subtypes were considered, as well as when a high AUC (0.821) was obtained-although harmonization decreased the accuracy to 58%. Moreover, the features that contributed the most to models' performance were those extracted from wavelet decomposed and Laplacian of Gaussian (LoG) filtered images and they belonged to the texture feature class.. In conclusion, we showed that our multicenter data were affected by batch effects, that they could significantly alter the models' performance, and that feature harmonization correctly removed them. Although wavelet features seemed to be the most informative features, an absolute subset could not be identified since it changed depending on the training/testing splitting. Moreover, performance was influenced by the chosen dataset and by the machine learning methods, which could reach a high accuracy in binary classification tasks, but could underperform in multiclass problems. It is, therefore, essential that the scientific community propose a more systematic radiomics approach, focusing on multicenter studies, with clear and solid guidelines to facilitate the translation of radiomics to clinical practice.

Keywords: CT; NSCLC; harmonization; machine learning; multicenter; non-small-cell lung carcinoma; phenotyping; radiomics.

Figure 1

Data preparation workflow.

Figure 2

Feature extraction workflow.

Figure 3

Final dataset subdivision into the 4-classes dataset, 3-classes dataset, and the 2-classes dataset.

Figure 4

Batch analysis and harmonization pipeline.

Figure 5

Modeling pipeline. The feature selection process is in yellow and the model building process is in purple.

Figure 6

The PCA scatter plot on the (left) and the tSNE scatter plot on the (right) for the 4-classes dataset.

Figure 7

The PCA scatter plot on the (left) and the tSNE scatter plot on the (right) for the 3-classes dataset.

Figure 8

The PCA scatter plot on the (left) and the tSNE scatter plot on the (right) for the 2-classes dataset.

Figure 9

The PCA scatter plot after harmonization. The 4-classes are on the top-left, the 3-classes are on the top-right, the 2-classes are on the bottom-left.

Figure 10

Accuracy heatmaps: (a) The 4-classes datasets, (b) 3-classes datasets, and (c) 2-classes datasets.

Figure 11

AUC heatmaps: (a) The 4-classes datasets, (b) 3-classes datasets, and (c) 2-classes datasets.

Figure 12

Accuracy heatmaps for the harmonized datasets: (a) The 4-classes datasets, (b) 3-classes datasets, and (c) 2-classes datasets.

Figure 13

AUC heatmaps for the harmonized datasets: (a) The 4-classes datasets, (b) 3-classes datasets, and (c) 2-classes datasets.

Figure 14

ROC curves: (top) The 4-classes datasets, (middle) 3-classes datasets, and (bottom) 2-classes datasets.

Figure 14

ROC curves: (top) The 4-classes datasets, (middle) 3-classes datasets, and (bottom) 2-classes datasets.

Figure 15

ROC curves for the harmonized datasets: (top) The 4-classes datasets, (middle) 3-classes datasets, and (bottom) 2-classes datasets.

Figure 15

ROC curves for the harmonized datasets: (top) The 4-classes datasets, (middle) 3-classes datasets, and (bottom) 2-classes datasets.