External Validation of a Convolutional Neural Network for IDH Mutation Prediction.

Background and Objectives: The IDH (isocitrate dehydrogenase) status represents one of the main prognosis factors for gliomas. However, determining it requires invasive procedures and specialized surgical skills. Medical imaging such as MRI is essential in glioma diagnosis and management. Lately, fields such as Radiomics and Radiogenomics emerged as pertinent prediction tools for extracting molecular information out of medical images. These fields are based on Artificial Intelligence algorithms that require external validation in order to evaluate their general performance. The aim of this study was to provide an external validation for the algorithm formulated by Yoon Choi et al. of IDH status prediction using preoperative common MRI sequences and patient age. Material and Methods: We applied Choi's IDH status prediction algorithm on T1c, T2 and FLAIR preoperative MRI images of gliomas (grades WHO II-IV) of 21 operated adult patients from the Neurosurgery clinic of the Cluj County Emergency Clinical Hospital (CCECH), Cluj-Napoca Romania. We created a script to automate the testing process with DICOM format MRI sequences as input and IDH predicted status as output. Results: In terms of patient characteristics, the mean age was 48.6 ± 15.6; 57% were female and 43% male; 43% were IDH positive and 57% IDH negative. The proportions of WHO grades were 24%, 14% and 62% for II, III and IV, respectively. The validation test achieved a relative accuracy of 76% with 95% CI of (53%, 92%) and an Area Under the Curve (AUC) through DeLong et al. method of 0.74 with 95% CI of (0.53, 0.91) and a p of 0.021. Sensitivity and Specificity were 0.78 with 95% CI of (0.45, 0.96) and 0.75 with 95% CI of (0.47, 0.91), respectively. Conclusions: Although our results match the external test the author made on The Cancer Imaging Archive (TCIA) online dataset, performance of the algorithm on external data is still not high enough for clinical application. Radiogenomic approaches remain a high interest research field that may provide a rapid and accurate diagnosis and prognosis of patients with intracranial glioma.

The Roles of miRNA in Glioblastoma Tumor Cell Communication: Diplomatic and Aggressive Negotiations.

Glioblastoma (GBM) consists of a heterogeneous collection of competing cellular clones which communicate with each other and with the tumor microenvironment (TME). MicroRNAs (miRNAs) present various exchange mechanisms: free miRNA, extracellular vesicles (EVs), or gap junctions (GJs). GBM cells transfer miR-4519 and miR-5096 to astrocytes through GJs. Oligodendrocytes located in the invasion front present high levels of miR-219-5p, miR-219-2-3p, and miR-338-3p, all related to their differentiation. There is a reciprocal exchange between GBM cells and endothelial cells (ECs) as miR-5096 promotes angiogenesis after being transferred into ECs, whereas miR-145-5p acts as a tumor suppressor. In glioma stem cells (GSCs), miR-1587 and miR-3620-5p increase the proliferation and miR-1587 inhibits the hormone receptor co-repressor-1 (NCOR1) after EVs transfers. GBM-derived EVs carry miR-21 and miR-451 that are up-taken by microglia and monocytes/macrophages, promoting their proliferation. Macrophages release EVs enriched in miR-21 that are transferred to glioma cells. This bidirectional miR-21 exchange increases STAT3 activity in GBM cells and macrophages, promoting invasion, proliferation, angiogenesis, and resistance to treatment. miR-1238 is upregulated in resistant GBM clones and their EVs, conferring resistance to adjacent cells via the CAV1/EGFR signaling pathway. Decrypting these mechanisms could lead to a better patient stratification and the development of novel target therapies.