Differentiating tumor progression (TP) from treatment-related necrosis (TN) is critical for clinical management decisions in glioblastoma (GBM). Dynamic FDG PET (dPET), an advance from traditional static FDG PET, may prove advantageous in clinical staging. dPET includes novel methods of a model-corrected blood input function that accounts for partial volume averaging to compute parametric maps that reveal kinetic information. In a preliminary study, a convolution neural network (CNN) was trained to predict classification accuracy between TP and TN for $35$ brain tumors from $26$ subjects in the PET-MR image space. 3D parametric PET Ki (from dPET), traditional static PET standardized uptake values (SUV), and also the brain tumor MR voxels formed the input for the CNN. The average test accuracy across all leave-one-out cross-validation iterations adjusting for class weights was $0.56$ using only the MR, $0.65$ using only the SUV, and $0.71$ using only the Ki voxels. Combining SUV and MR voxels increased the test accuracy to $0.62$. On the other hand, MR and Ki voxels increased the test accuracy to $0.74$. Thus, dPET features alone or with MR features in deep learning models would enhance prediction accuracy in differentiating TP vs TN in GBM.
<p>The histopathologic feature that correlated most closely with the MRI finding of T2-FLAIR mismatch was the presence of numerous, highly packed microcysts with variable sizes that were noted in regions of moderate or low cell density. These findings were not homogeneous throughout the section, but varied from region to region and were typically associated with edema and neuropil vacuolization (H&E stain, 200X).</p>
<p>RPPA results comparing protein levels between the IDHmut-Noncodel gliomas from the TCGA/TCIA cohort differentiated by the T2-FLAIR mismatch sign.</p>
Background: Metastatic lesions to the brain are common in patients with melanoma. Imaging characteristics can support the diagnosis of metastatic melanoma, but alternative diagnoses should be considered. Case Description: Here, we present a case of a 57-year-old man in whom a metastatic melanoma initially mimicked the imaging characteristics of cortical laminar necrosis. Conclusion: This comprises the first report of melanoma brain metastasis presenting with these imaging characteristics and emphasizes the importance of maintaining a high index of suspicion for metastatic lesions in patients with known cancer.
Background and purposeClinical history is known to influence interpretation of a wide range of radiologic examinations. We sought to evaluate the influence of the clinical history on MRI interpretation of optic neuropathy.Materials and methods107 consecutive orbital MRI scans were retrospectively reviewed by three neuroradiologists. The readers independently evaluated the coronal STIR sequence for optic nerve hyperintensity and/or atrophy (yes/no) and the coronal post-contrast T1WI for optic nerve enhancement (yes/no). Readers initially evaluated the cases blinded to the clinical history. Following a two week washout period, readers again evaluated the cases with the clinical history provided. Inter-reader and reader-clinical radiologist agreement was assessed using Cohen's simple kappa coefficient.ResultsIntra-reader agreement, without and with provision of clinical history, was 0.564–0.716 on STIR and 0.270–0.495 on post-contrast T1WI. Inter-reader agreement was overall fair-moderate. On post-contrast T1WI, inter-reader agreement was significantly higher when the clinical history was provided (p = 0.001). Reader-clinical radiologist agreement improved with provision of the clinical history to the readers on both the STIR and post-contrast T1WI sequences.ConclusionsIn the MRI assessment of optic neuropathy, only modest levels of inter-reader agreement were achieved, even after provision of clinical history. Provision of clinical history improved inter-reader agreement, especially when assessing for optic nerve enhancement. These findings confirm the subjective nature of orbital MRI interpretation in cases of optic neuropathy, and point to the importance of an accurate clinical history. Of note, the accuracy of orbital MRI in the context of optic neuropathy was not assessed, and would require further investigation.
Accurate segmentation of different sub-regions of gliomas such as peritumoral edema, necrotic core, enhancing and non-enhancing tumor core from multimodal MRI scans has important clinical relevance in diagnosis, prognosis and treatment of brain tumors. However, due to the highly heterogeneous appearance and shape of these tumors, segmentation of the sub-regions is challenging. Recent developments using deep learning models has proved its effectiveness in various semantic and medical image segmentation tasks, many of which are based on the U-Net network structure with symmetric encoding and decoding paths for end-to-end segmentation due to its high efficiency and good performance. In brain tumor segmentation, the 3D nature of multimodal MRI poses challenges such as memory and computation limitations and class imbalance when directly adopting the U-Net structure. In this study we aim to develop a deep learning model using a 3D U-Net with adaptations in the training and testing strategies, network structures and model parameters for brain tumor segmentation. Furthermore, instead of picking one best model, an ensemble of multiple models trained with different hyper-parameters are used to reduce random errors from each model and yield improved performance. Preliminary results demonstrate the effectiveness of this method and achieved the 9th place in the very competitive 2018 Multimodal Brain Tumor Segmentation (BraTS) challenge. In addition, to emphasize the clinical value of the developed segmentation method, a linear model based on the radiomics features extracted from segmentation and other clinical features are developed to predict patient overall survival. Evaluation of these innovations shows high prediction accuracy in both low-grade glioma and glioblastoma patients, which achieved the 1st place in the 2018 BraTS challenge.
'%3e%3cpath fill='%23012169' d='M0 0v30h60V0z'/%3e%3cpath stroke='%23fff' stroke-width='6' d='m0 0 60 30m0-30L0 30'/%3e%3cpath stroke='%23C8102E' stroke-width='4' d='m0 0 60 30m0-30L0 30' clip-path='url(%23b)'/%3e%3cpath stroke='%23fff' stroke-width='10' d='M30 0v30M0 15h60'/%3e%3cpath stroke='%23C8102E' stroke-width='6' d='M30 0v30M0 15h60'/%3e%3c/g%3e%3c/svg%3e)
