Differentiation of Enhancing Glioma and Primary Central Nervous System Lymphoma by Texture-Based Machine Learning

Abstract

Background and purpose: Accurate preoperative differentiation of primary central nervous system lymphoma and enhancing glioma is essential to avoid unnecessary neurosurgical resection in patients with primary central nervous system lymphoma. The purpose of the study was to evaluate the diagnostic performance of a machine-learning algorithm by using texture analysis of contrast-enhanced T1-weighted images for differentiation of primary central nervous system lymphoma and enhancing glioma.

Materials and methods: Seventy-one adult patients with enhancing gliomas and 35 adult patients with primary central nervous system lymphomas were included. The tumors were manually contoured on contrast-enhanced T1WI, and the resulting volumes of interest were mined for textural features and subjected to a support vector machine-based machine-learning protocol. Three readers classified the tumors independently on contrast-enhanced T1WI. Areas under the receiver operating characteristic curves were estimated for each reader and for the support vector machine classifier. A noninferiority test for diagnostic accuracy based on paired areas under the receiver operating characteristic curve was performed with a noninferiority margin of 0.15.

Results: The mean areas under the receiver operating characteristic curve were 0.877 (95% CI, 0.798-0.955) for the support vector machine classifier; 0.878 (95% CI, 0.807-0.949) for reader 1; 0.899 (95% CI, 0.833-0.966) for reader 2; and 0.845 (95% CI, 0.757-0.933) for reader 3. The mean area under the receiver operating characteristic curve of the support vector machine classifier was significantly noninferior to the mean area under the curve of reader 1 (P = .021), reader 2 (P = .035), and reader 3 (P = .007).

Conclusions: Support vector machine classification based on textural features of contrast-enhanced T1WI is noninferior to expert human evaluation in the differentiation of primary central nervous system lymphoma and enhancing glioma.

Fig 1.

Receiver operating characteristic curves for discrimination of primary central nervous system lymphoma (positive) and glioblastoma (negative) of the support vector machine classifier (continuous line) and the 3 readers (dashed lines). The mean areas under the curve estimated under the nonparametric assumption were 0.877 (95% confidence interval, 0.798–0.955) for the SVM classifier; 0.878 (95% confidence interval, 0.807–0.949) for reader 1; 0.899 (95% confidence interval, 0.833–0.966) for reader 2; and 0.845 (95% confidence interval, 0.757–0.933) for reader 3.

Fig 2.

The chart shows the mean differences in area under the curve (95% confidence interval between the support vector machine classifier and reader 1 = −0.001 (95% CI, −0.096–0.094); between the SVM classifier and reader 2 = −0.022 (95% CI, −0.106–0.062); and between SVM classifier and reader 3 = 0.032 (95% CI, −0.074–0.138). All the confidence intervals sit wholly above the −0.15 limit (dashed line) representing the noninferiority margin.

Fig 3.

Comparison between the accuracy of the radiologists and the support vector machine classifier for each of the 106 cases. The horizontal axis shows the different cases sorted in order of decreasing SVM classifier accuracy. The left vertical axis shows the percentage of correctly classified trials by the SVM across 100 nested cross-validation trials. The right vertical axis shows the number of radiologists that classified the tumor correctly. For this graph, the results of the radiologists were simplified to 2 categories “glioma” and “lymphoma” without taking into account the degree of certainty. Although agreement is slightly better among radiologists than between radiologists and the SVM classifier, the cases in which the SVM provides different results for different trials (midright area of the graph) correspond to cases with more disagreements among the radiologists.

Fig 4.

A, Axial contrast-enhanced T1-weighted image of a 51-year-old woman with a grade IV glioma. All 3 radiologists incorrectly classified the tumor as PCNSL, whereas the SVM classified it correctly in 92% of the trials. B and C, Axial contrast-enhanced T1WI of a 47-year-old woman with a grade IV glioma. All 3 radiologists incorrectly classified the tumor as PCNSL, whereas the SVM classifier provided the right diagnosis in 88% of the trials.