Radiogenomic Models Using Machine Learning Techniques to Predict EGFR Mutations in Non-Small Cell Lung Cancer.

BACKGROUND: The purpose of this study was to build radiogenomics models from texture signatures derived from computed tomography (CT) and 18F-FDG PET-CT (FDG PET-CT) images of non-small cell lung cancer (NSCLC) with and without epidermal growth factor receptor (EGFR) mutations. METHODS: Fifty patients diagnosed with NSCLC between 2011 and 2015 and with known EGFR mutation status were retrospectively identified. Texture features extracted from pretreatment CT and FDG PET-CT images by manual contouring of the primary tumor were used to develop multivariate logistic regression (LR) models to predict EGFR mutations in exon 19 and exon 20. RESULTS: An LR model evaluating FDG PET-texture features was able to differentiate EGFR mutant from wild type with an area under the curve (AUC), sensitivity, specificity, and accuracy of 0.87, 0.76, 0.66, and 0.71, respectively. The model derived from CT texture features had an AUC, sensitivity, specificity, and accuracy of 0.83, 0.84, 0.73, and 0.78, respectively. FDG PET-texture features that could discriminate between mutations in EGFR exon 19 and 21 demonstrated AUC, sensitivity, specificity, and accuracy of 0.86, 0.84, 0.73, and 0.78, respectively. Based on CT texture features, the AUC, sensitivity, specificity, and accuracy were 0.75, 0.81, 0.69, and 0.75, respectively. CONCLUSION: Non-small cell lung cancer texture analysis using FGD-PET and CT images can identify tumors with mutations in EGFR. Imaging signatures could be valuable for pretreatment assessment and prognosis in precision therapy.

Atypical resting state functional connectivity in mild traumatic brain injury.

OBJECTIVES: This study aimed to investigate changes in three intrinsic functional connectivity networks (IFCNs; default mode network [DMN], salience network [SN], and task-positive network [TPN]) in individuals who had sustained a mild traumatic brain injury (mTBI). METHODS: Resting-state functional magnetic resonance imaging (rs-fMRI) data were acquired from 27 mTBI patients with persistent postconcussive symptoms, along with 26 age- and sex-matched controls. These individuals were recruited from a Level-1 trauma center, at least 3 months after a traumatic episode. IFCNs were established based on seed-to-voxel, region-of-interest (ROI) to ROI, and independent component analyses (ICA). Subsequently, we analyzed the relationship between functional connectivity and postconcussive symptoms. RESULTS: Seed-to-voxel analysis of rs-fMRI demonstrated decreased functional connectivity in the right lateral parietal lobe, part of the DMN, and increased functional connectivity in the supramarginal gyrus, part of the SN. Our TPN showed both hypo- and hyperconnectivity dependent on seed location. Within network hypoconnectivity was observed in the visual network also using group comparison. Using an ICA, we identified altered network functional connectivity in regions within four IFCNs (sensorimotor, visual, DMN, and dorsal attentional). A significant negative correlation between dorsal attentional network connectivity and behavioral symptoms score was also found. CONCLUSIONS: Our findings indicate that rs-fMRI may be of use clinically in order to assess disrupted functional connectivity among IFCNs in mTBI patients. Improved mTBI diagnostic and prognostic information could be especially relevant for athletes looking to safely return to play, as well for individuals from the general population with persistent postconcussive symptoms months after injury, who hope to resume activity.