Preoperative Radiomics Analysis of 1p/19q Status in WHO Grade II Gliomas

Abstract

PurposeThe present study aimed to preoperatively predict the status of 1p/19q based on radiomics analysis in patients with World Health Organization (WHO) grade II gliomas.MethodsThis retrospective study enrolled 157 patients with WHO grade II gliomas (76 patients with astrocytomas with mutant IDH, 16 patients with astrocytomas with wild-type IDH, and 65 patients with oligodendrogliomas with mutant IDH and 1p/19q codeletion). Radiomic features were extracted from magnetic resonance images, including T1-weighted, T2-weighted, and contrast T1-weighted images. Elastic net and support vector machines with radial basis function kernel were applied in nested 10-fold cross-validation loops to predict the 1p/19q status. Receiver operating characteristic analysis and precision-recall analysis were used to evaluate the model performance. Student’s t-tests were then used to compare the posterior probabilities of 1p/19q co-deletion prediction in the group with different 1p/19q status.ResultsSix valuable radiomic features, along with age, were selected with the nested 10-fold cross-validation loops. Five features showed significant difference in patients with different 1p/19q status. The area under curve and accuracy of the predictive model were 0.8079 (95% confidence interval, 0.733–0.8755) and 0.758 (0.6879–0.8217), respectively, and the F1-score of the precision-recall curve achieved 0.6667 (0.5201–0.7705). The posterior probabilities in the 1p/19q co-deletion group were significantly different from the non-deletion group.ConclusionCombined radiomics analysis and machine learning showed potential clinical utility in the preoperative prediction of 1p/19q status, which can aid in making customized neurosurgery plans and glioma management strategies before postoperative pathology.

Identifying IDH-mutant and 1p/19q noncodeleted astrocytomas from nonenhancing gliomas: Manual recognition followed by artificial intelligence recognition

“…Previous studies have shown that astrocytomas and oligodendrogliomas exhibit heterogeneous radiomic features, and machine learning can significantly improve the identification of the 2 tumors. 33–35 In our research, we used 6 radiomic features to establish a prediction model, we found that the established model with the AUC, accuracy, sensitivity, and specificity were 0.845/0.800, 0.767/0.731, 0.712/0.789, and 0.817/0.676 in the training set and validation set, respectively. Each of these 6 features represents a texture feature of the image, this is consistent with the phenomenon that oligodendrogliomas and astrocytomas exhibit different signal uniformity on T2WI.…”

Artificial Intelligence Applications in Glioma With 1p/19q Co‐Deletion: A Systematic Review

“…The sample size ranged from 42 to 1748. Most studies focused on WHO 2–4 glioma or WHO 2–3, with one study including only WHO 2 glioma 24 and one study including only WHO 4 glioma 25 . For the target condition, 10 studies focused on IDH mutation combined 1p/19q co‐deletion, while 18 studies on 1p/19q co‐deletion only.…”

Molecular pathology and clinical implications of diffuse glioma

“…Accumulating studies have successfully predicted the status of IDH , 1p/19q codeletion, and TERT mutation by using AI models. [ 39 , 40 ] The increasing accuracy of these predictive models has brought them close to being used in clinical diagnosis, and enlarging the sample size and improving their advanced algorithms have the potential to further improve the accuracy and robustness of these models. We believe that validation of these predictive models through prospective clinical trials will make the use of molecular features for guiding tumor resection a reality in the near future.…”

“…Fortunately, with the development of artificial intelligence (AI) and radiomics, predicting the molecular features of gliomas through models based on radiomic characteristics is a hopeful potential. Accumulating studies have successfully predicted the status of IDH , 1p/19q codeletion, and TERT mutation by using AI models [39,40] . The increasing accuracy of these predictive models has brought them close to being used in clinical diagnosis, and enlarging the sample size and improving their advanced algorithms have the potential to further improve the accuracy and robustness of these models.…”