ABSTRACT
BACKGROUND AND PURPOSE: O6-Methylguanine-DNA methyltransferase (MGMT) promoter methylation confers an improved prognosis and treatment response in gliomas. We developed a deep learning network for determining MGMT promoter methylation status using T2 weighted Images (T2WI) only. MATERIALS AND METHODS: Brain MR imaging and corresponding genomic information were obtained for 247 subjects from The Cancer Imaging Archive and The Cancer Genome Atlas. One hundred sixty-three subjects had a methylated MGMT promoter. A T2WI-only network (MGMT-net) was developed to determine MGMT promoter methylation status and simultaneous single-label tumor segmentation. The network was trained using 3D-dense-UNets. Three-fold cross-validation was performed to generalize the performance of the networks. Dice scores were computed to determine tumor-segmentation accuracy. RESULTS: The MGMT-net demonstrated a mean cross-validation accuracy of 94.73% across the 3 folds (95.12%, 93.98%, and 95.12%, [SD, 0.66%]) in predicting MGMT methylation status with a sensitivity and specificity of 96.31% [SD, 0.04%] and 91.66% [SD, 2.06%], respectively, and a mean area under the curve of 0.93 [SD, 0.01]. The whole tumor-segmentation mean Dice score was 0.82 [SD, 0.008]. CONCLUSIONS: We demonstrate high classification accuracy in predicting MGMT promoter methylation status using only T2WI. Our network surpasses the sensitivity, specificity, and accuracy of histologic and molecular methods. This result represents an important milestone toward using MR imaging to predict prognosis and treatment response.
Subject(s)
Brain Neoplasms/diagnostic imaging , Brain Neoplasms/genetics , DNA Modification Methylases/genetics , DNA Repair Enzymes/genetics , Deep Learning , Glioma/diagnostic imaging , Glioma/genetics , Magnetic Resonance Imaging/methods , Tumor Suppressor Proteins/genetics , Adult , Aged , Area Under Curve , DNA Methylation , Humans , Male , Middle Aged , Neural Networks, Computer , Promoter Regions, Genetic , Reproducibility of Results , Sensitivity and SpecificityABSTRACT
BACKGROUND AND PURPOSE: SWI is an advanced imaging modality that is especially useful in cerebral microhemorrhage detection. Such microhemorrhages have been identified in adult contact sport athletes, and the sequelae of these focal bleeds are thought to contribute to neurodegeneration. The purpose of this study was to utilize SWI to determine whether the prevalence and incidence of microhemorrhages in adolescent football players are significantly greater than those of adolescent noncontact athletes. MATERIALS AND METHODS: Preseason and postseason SWI was performed and evaluated on 78 adolescent football players. SWI was also performed on 27 adolescent athletes who reported no contact sport history. Two separate one-tailed Fisher exact tests were performed to determine whether the prevalence and incidence of microhemorrhages in adolescent football players are greater than those of noncontact athlete controls. RESULTS: Microhemorrhages were observed in 12 football players. No microhemorrhages were observed in any controls. Adolescent football players demonstrated a significantly greater prevalence of microhemorrhages than adolescent noncontact controls (P = .02). Although 2 football players developed new microhemorrhages during the season, microhemorrhage incidence during 1 football season was not statistically greater in the football population than in noncontact control athletes (P = .55). CONCLUSIONS: Adolescent football players have a greater prevalence of microhemorrhages compared with adolescent athletes who have never engaged in contact sports. While microhemorrhage incidence during 1 season is not significantly greater in adolescent football players compared to adolescent controls, there is a temporal association between playing football and the appearance of new microhemorrhages.
Subject(s)
Cerebral Hemorrhage, Traumatic/diagnostic imaging , Cerebral Hemorrhage, Traumatic/etiology , Football/injuries , Neuroimaging/methods , Adolescent , Athletes , Humans , Incidence , Magnetic Resonance Imaging/methods , Male , PrevalenceSubject(s)
Anger , Depressive Disorder/psychology , Hostility , Spouse Abuse , Violence , Humans , Jealousy , MaleABSTRACT
Photoplastic film was prepared as a dispersion of 1% Cu-doped CdS in a deformable polymer matrix of plasticized polystyrene. Spectral response, determined by measuring the rate of photoinduced charge decay, was approximately constant in the range of 380-500 mmicro. Sensitivity was about 1 microJ/cm(2) under specified conditions of charge and spatial frequency. Resolving power was between 50-100 lp/mm. Signal-to-noise ratio and reusability characteristics are discussed.