Purpose: Patients with 1p/19q codeleted low-grade glioma (LGG) have longer overall survival and better treatment response than patients with 1p/19q intact tumors. Therefore, it is relevant to know the 1p/19q status. To investigate whether the 1p/19q status can be assessed prior to tumor resection, we developed a machine learning algorithm to predict the 1p/19q status of presumed LGG based on preoperative MRI. Experimental Design: Preoperative brain MR images from 284 patients who had undergone biopsy or resection of presumed LGG were used to train a support vector machine algorithm. The algorithm was trained on the basis of features extracted from post-contrast T1-weighted and T2-weighted MR images and on patients' age and sex. The performance of the algorithm compared with tissue diagnosis was assessed on an external validation dataset of MR images from 129 patients with LGG from The Cancer Imaging Archive (TCIA). Four clinical experts also predicted the 1p/19q status of the TCIA MR images. Results: The algorithm achieved an AUC of 0.72 in the external validation dataset. The algorithm had a higher predictive performance than the average of the neurosurgeons (AUC 0.52) but lower than that of the neuroradiologists (AUC of 0.81). There was a wide variability between clinical experts (AUC 0.45-0.83). Conclusions: Our results suggest that our algorithm can noninvasively predict the 1p/19q status of presumed LGG with a performance that on average outperformed the oncological neurosurgeons. Evaluation on an independent dataset indicates that our algorithm is robust and generalizable.

Computed tomography (CT) is commonly used for the diagnosis, treatment planning, and prognosis of pure orbital fractures of the orbital floor and medial wall. The aim of this study was to systematically review the current literature in order to establish an overview of CT parameters relevant to the choice of treatment and (long-term) clinical outcome for patients treated operatively and conservatively. The PRISMA guidelines were followed. Databases were searched using the terms 'orbital fracture' and 'computed tomography'. Studies evaluating the relationship between CT parameters and the treatment decision or clinical outcome (enophthalmos, diplopia, and/or limitation of ocular movement) were included. The search yielded 4448 results of which 31 were included (except for three, all were retrospective). The systematic use of CT imaging in orbital fractures of the floor and the medial wall can be of great value in the treatment decision and prediction of (long-term) clinical outcomes for both conservatively and surgically treated patients. The following parameters were found to be the most relevant: fracture size, fracture location, orbital volume, soft tissue involvement, and craniocaudal dimension. Although some show great individual potential, it is likely that incorporating all parameters into an algorithm will provide the best predictive power and thus would be the most practically applicable tool.

Cellular angiofibroma is a benign mesenchymal tumor most commonly located in the distal genital tract of both men and women. Although extragenital locations have been reported rarely, this is the first report of cellular angiofibroma of the orbit. A 58-year-old man presented with a mass in the left superomedial orbit since 2 years. Magnetic resonance imaging showed a well-demarcated lesion with a homogeneous intermediate signal intensity on both T1-and T2-weighted images, homogeneous contrast enhancement and high signal intensity on diffusion-weighted images. Complete excision was performed through a medial upper eyelid crease incision. Histopathology showed a vascular CD34-positive and STAT6-negative spindle cell tumor with monoallelic loss of FOXO1, indicating cellular angiofibroma.

MRI is preferred over CT in diagnostic imaging of dementia, in accordance with existing guidelines. However, these guidelines are mostly out-dated and modern multislice CT potential is relatively unknown among geriatricians. In memory clinics, multislice CT could offer a well suitable imaging alternative, but only if multiplanar reconstructions are performed consistently. Furthermore, radiology reports need to be improved by using more standardized assessment.

<p>Excluded patients from TCIA-1p19qDeletion dataset</p>

<p>Overview of importance of imaging and demographic features</p>

<p>Overview of the radiogenomics pipeline</p>

<div>AbstractPurpose:<p>Patients with 1p/19q codeleted low-grade glioma (LGG) have longer overall survival and better treatment response than patients with 1p/19q intact tumors. Therefore, it is relevant to know the 1p/19q status. To investigate whether the 1p/19q status can be assessed prior to tumor resection, we developed a machine learning algorithm to predict the 1p/19q status of presumed LGG based on preoperative MRI.</p>Experimental Design:<p>Preoperative brain MR images from 284 patients who had undergone biopsy or resection of presumed LGG were used to train a support vector machine algorithm. The algorithm was trained on the basis of features extracted from post-contrast T1-weighted and T2-weighted MR images and on patients' age and sex. The performance of the algorithm compared with tissue diagnosis was assessed on an external validation dataset of MR images from 129 patients with LGG from The Cancer Imaging Archive (TCIA). Four clinical experts also predicted the 1p/19q status of the TCIA MR images.</p>Results:<p>The algorithm achieved an AUC of 0.72 in the external validation dataset. The algorithm had a higher predictive performance than the average of the neurosurgeons (AUC 0.52) but lower than that of the neuroradiologists (AUC of 0.81). There was a wide variability between clinical experts (AUC 0.45–0.83).</p>Conclusions:<p>Our results suggest that our algorithm can noninvasively predict the 1p/19q status of presumed LGG with a performance that on average outperformed the oncological neurosurgeons. Evaluation on an independent dataset indicates that our algorithm is robust and generalizable.</p></div>