CNS paraganglioma: 15-year experience in a tertiary care hospital with literature review.

Paraganglioma that involves the CNS may mimic clinico-radiologically many other commoner entities. The current study presents a wide view of the clinical, radiological, and histomorphological spectrum along with rare associations that can occur concurrently with this lesion. The most common site of infliction in CNS is the spine and, in the current series, involvement of the lumbar spine was most frequent. Both clinical and radiological features point towards other more common differentials, including neurofibroma/schwannoma and ependymoma. Some studies suggest rich vascularity (cap sign) and salt pepper appearance in T2-weighted images to serve as soft pointers towards diagnosing it on magnetic resonance imaging, however, in our series we did not encounter the same.

Frequency-domain loss function for deep exposure correction of dark images.

We address the problem of exposure correction of dark, blurry and noisy images captured in low-light conditions in the wild. Classical image-denoising filters work well in the frequency space but are constrained by several factors such as the correct choice of thresholds and frequency estimates. On the other hand, traditional deep networks are trained end to end in the RGB space by formulating this task as an image translation problem. However, that is done without any explicit constraints on the inherent noise of the dark images and thus produces noisy and blurry outputs. To this end, we propose a DCT/FFT-based multi-scale loss function, which when combined with traditional losses, trains a network to translate the important features for visually pleasing output. Our loss function is end to end differentiable, scale-agnostic and generic; i.e., it can be applied to both RAW and JPEG images in most existing frameworks without additional overhead. Using this loss function, we report significant improvements over the state of the art using quantitative metrics and subjective tests.