Distinguishing True Progression From Radionecrosis After Stereotactic Radiation Therapy for Brain Metastases With Machine Learning and Radiomics.

PURPOSE: Treatment effect or radiation necrosis after stereotactic radiosurgery (SRS) for brain metastases is a common phenomenon often indistinguishable from true progression. Radiomics is an emerging field that promises to improve on conventional imaging. In this study, we sought to apply a radiomics-based prediction model to the problem of diagnosing treatment effect after SRS. METHODS AND MATERIALS: We included patients in the Johns Hopkins Health System who were treated with SRS for brain metastases who subsequently underwent resection for symptomatic growth. We also included cases of likely treatment effect in which lesions grew but subsequently regressed spontaneously. Lesions were segmented semiautomatically on preoperative T1 postcontrast and T2 fluid-attenuated inversion recovery magnetic resonance imaging, and radiomic features were extracted with software developed in-house. Top-performing features on univariate logistic regression were entered into a hybrid feature selection/classification model, IsoSVM, with parameter optimization and further feature selection performed using leave-one-out cross-validation. Final model performance was assessed by 10-fold cross-validation with 100 repeats. All cases were independently reviewed by a board-certified neuroradiologist for comparison. RESULTS: We identified 82 treated lesions across 66 patients, with 77 lesions having pathologic confirmation. There were 51 radiomic features extracted per segmented lesion on each magnetic resonance imaging sequence. An optimized IsoSVM classifier based on top-ranked radiomic features had sensitivity and specificity of 65.38% and 86.67%, respectively, with an area under the curve of 0.81 on leave-one-out cross-validation. Only 73% of cases were classifiable by the neuroradiologist, with a sensitivity of 97% and specificity of 19%. CONCLUSIONS: Radiomics holds promise for differentiating between treatment effect and true progression in brain metastases treated with SRS. A predictive model built on radiomic features from an institutional cohort performed well on cross-validation testing. These results warrant further validation in independent datasets. Such work could prove invaluable for guiding management of individual patients and assessing outcomes of novel interventions.

Author Correction: Nociceptor sensory neurons suppress neutrophil and γδ T cell responses in bacterial lung infections and lethal pneumonia.

In the version of this article initially published, the line graph showing TNF-α levels in Fig. 2d was inadvertently duplicated. A graph of IL-6 levels should be shown in place of the duplication.These results were also incorrectly described in the main text, which originally stated: "At an early time point of infection (6 h), RTX-treated mice showed higher induction of total inflammatory-protein levels in the bronchoalveolar lavage fluid (BALF) (Fig. 2c), as well as levels of the cytokines TNF-α and IL-6, and the chemokine CXCL-1 (Fig. 2d)". This should instead read: "At an early time point of infection (6 h), RTX-treated mice showed higher induction of total inflammatory-protein levels in the bronchoalveolar lavage fluid (BALF) (Fig. 2c), as well as levels of the cytokine TNF-α and the chemokine CXCL-1 (Fig. 2d)".In the supplementary information initially posted online, incorrect bar graphs were presented in Supplementary Fig. 1b (VG, TRPV1+ data, top panel) and Supplementary Fig. 4b (DRG, CGRP+ data, middle panel).

Nociceptor sensory neurons suppress neutrophil and γδ T cell responses in bacterial lung infections and lethal pneumonia.

Lung-innervating nociceptor sensory neurons detect noxious or harmful stimuli and consequently protect organisms by mediating coughing, pain, and bronchoconstriction. However, the role of sensory neurons in pulmonary host defense is unclear. Here, we found that TRPV1+ nociceptors suppressed protective immunity against lethal Staphylococcus aureus pneumonia. Targeted TRPV1+-neuron ablation increased survival, cytokine induction, and lung bacterial clearance. Nociceptors suppressed the recruitment and surveillance of neutrophils, and altered lung γδ T cell numbers, which are necessary for immunity. Vagal ganglia TRPV1+ afferents mediated immunosuppression through release of the neuropeptide calcitonin gene-related peptide (CGRP). Targeting neuroimmunological signaling may be an effective approach to treat lung infections and bacterial pneumonia.