Machine learning-based multiparametric magnetic resonance imaging radiomics model for distinguishing central neurocytoma from glioma of lateral ventricle.

OBJECTIVES: To develop a machine learning-based radiomics model based on multiparametric magnetic resonance imaging (MRI) for preoperative discrimination between central neurocytomas (CNs) and gliomas of lateral ventricles. METHODS: A total of 132 patients from two medical centers were enrolled in this retrospective study. Patients from the first medical center were divided into a training cohort (n = 74) and an internal validation cohort (n = 30). Patients from the second medical center were used as the external validation cohort (n = 28). Features were extracted from contrast-enhanced T1-weighted and T2-weighted images. A support vector machine was used for radiomics model investigation. Performance was evaluated using the sensitivity, specificity, and the area under the receiver operating characteristic curve (AUC). The model's performance was also compared with those of three radiologists. RESULTS: The radiomics model achieved an AUC of 0.986 in the training cohort, 0.933 in the internal validation cohort, and 0.903 in the external validation cohort. In the three cohorts, the AUC values were 0.657, 0.786, and 0.708 for radiologist 1; 0.838, 0.799, and 0.790 for radiologist 2; and 0.827, 0.871, and 0.862 for radiologist 3. When assisted by the radiomics model, two radiologists improved their performance in the training cohort (p < 0.05) but not in the internal or external validation cohorts. CONCLUSIONS: The machine learning radiomics model based on multiparametric MRI showed better performance for distinguishing CNs from lateral ventricular gliomas than did experienced radiologists, and it showed the potential to improve radiologist performance. KEY POINTS: • The machine learning radiomics model shows excellent performance in distinguishing CNs from gliomas. • The radiomics model outweighs two experienced radiologists (area under the receiver operating characteristic curve, 0.90 vs 0.79 and 0.86, respectively). • The radiomics model has the potential to enhance radiologist performance.

Machine Learning-Based Multiparametric Magnetic Resonance Imaging Radiomic Model for Discrimination of Pathological Subtypes of Craniopharyngioma.

BACKGROUND: Preoperative, noninvasive discrimination of the craniopharyngioma subtypes is important because it influences the treatment strategy. PURPOSE: To develop a radiomic model based on multiparametric magnetic resonance imaging for noninvasive discrimination of pathological subtypes of craniopharyngioma. STUDY TYPE: Retrospective. POPULATION: A total of 164 patients from two medical centers were enrolled in this study. Patients from the first medical center were divided into a training cohort (N = 99) and an internal validation cohort (N = 33). Patients from the second medical center were used as the external independent validation cohort (N = 32). FIELD STRENGTH/SEQUENCE: Axial T1 -weighted (T1 -w), T2 -weighted (T2 -w), contrast-enhanced T1 -weighted (CET1 -w) on 3.0 T or 1.5 T magnetic resonance scanners. ASSESSMENT: Pathological subtypes (squamous papillary craniopharyngioma and adamantinomatous craniopharyngioma) were confirmed by surgery and hematoxylin and eosin staining. Optimal radiomic feature selection was performed by SelectKBest, the least absolute shrinkage and selection operator algorithm, and support vector machine (SVM) with a recursive feature elimination algorithm. Models based on each sequence or combinations of sequences were built using a SVM classifier and used to differentiate pathological subtypes of craniopharyngioma in the training cohort, internal validation, and external validation cohorts. STATISTICAL TESTS: The area under the receiver operating characteristic curve (AUC) was used to assess the diagnostic performance of the radiomic models. RESULTS: Seven texture features, three from T1 -w, two from T2 -w, and two from CET1 -w, were selected and used to construct the radiomic model. The AUC values of the radiomic model were 0.899, 0.810, and 0.920 in the training cohort, internal and external validation cohorts, respectively. The AUC values of the clinicoradiological model were 0.677, 0.655, and 0.671 in the training cohort, internal and external validation cohorts, respectively. DATA CONCLUSION: The model based on radiomic features from T1 -w, T2 -w, and CET1 -w has a high discriminatory ability for pathological subtypes of craniopharyngioma. LEVEL OF EVIDENCE: 4 TECHNICAL EFFICACY: 2.