Reversible Severe Parkinsonism Caused by Extra-Pontine Myelinolysis in a patient with Primary Adrenal Failure.

PURPOSE: Extrapontine myelinolysis (EPM) is a highly uncommon, life-threatening disease, particularly in individuals who initially appear with severe clinical symptoms. Here, we describe a case of EPM caused by the rapid correction of hyponatremia that had severe clinical signs at first but parkinsonism symptoms were fully improved after treatment. CASE REPORT: A 46-year-old female patient was admitted to the hospital due to impaired consciousness. Her medical history reveals that she has PAI, or primary adrenal insufficiency. Initial laboratory measurements showed that the serum's sodium (Na) concentration was 104 mEq/L, chloride (Cl) content was 70 mmol/L, potassium (K) content was 4.95 mEq/L, glucose was 42 mg/dL, hydrogen potential (Ph) was 7.12, and bicarbonate (HCO3) concentration was 10 mmol/l. The adrenocorticotropic hormone (ACTH) level was 21 mg/ml, while the cortisol level was 1.2ug/dl. Her mental state was unclear, she had sluggish hypophonic speech, generalized akinesia/rigidity in both upper and lower extremities, trouble swallowing solid and liquid meals, and sialorrhea were all discovered after the Na level was corrected. Hyperintense lesions were visible in the bilateral putamen and caudate nuclei of the Magnetic Resonance Imaging (MRI) T2 and flair-weighted scans, which indicate EPM. EPM was treated with corticosteroids and dopamine agonists, and she was eventually released after complete recovery. CONCLUSION: Even if there are severe clinical symptoms at first, prompt diagnosis and treatment, such as dopaminergic, corticosteroid, and palliative therapy, can save a patient's life.

HoughNet: Integrating Near and Long-Range Evidence for Visual Detection.

This paper presents HoughNet, a one-stage, anchor-free, voting-based, bottom-up object detection method. Inspired by the Generalized Hough Transform, HoughNet determines the presence of an object at a certain location by the sum of the votes cast on that location. Votes are collected from both near and long-distance locations based on a log-polar vote field. Thanks to this voting mechanism, HoughNet is able to integrate both near and long-range, class-conditional evidence for visual recognition, thereby generalizing and enhancing current object detection methodology, which typically relies on only local evidence. On the COCO dataset, HoughNet's best model achieves 46.4 AP (and 65.1 AP50), performing on par with the state-of-the-art in bottom-up object detection and outperforming most major one-stage and two-stage methods. We further validate the effectiveness of our proposal in other visual detection tasks, namely, video object detection, instance segmentation, 3D object detection and keypoint detection for human pose estimation, and an additional "labels to photo'' image generation task, where the integration of our voting module consistently improves performance in all cases.

One Metric to Measure Them All: Localisation Recall Precision (LRP) for Evaluating Visual Detection Tasks.

Despite being widely used as a performance measure for visual detection tasks, Average Precision (AP) is limited in (i) reflecting localisation quality, (ii) interpretability and (iii) robustness to the design choices regarding its computation, and its applicability to outputs without confidence scores. Panoptic Quality (PQ), a measure proposed for evaluating panoptic segmentation (Kirillov et al., 2019), does not suffer from these limitations but is limited to panoptic segmentation. In this paper, we propose Localisation Recall Precision (LRP) Error as the average matching error of a visual detector computed based on both its localisation and classification qualities for a given confidence score threshold. LRP Error, initially proposed only for object detection by Oksuz et al. (2018), does not suffer from the aforementioned limitations and is applicable to all visual detection tasks. We also introduce Optimal LRP (oLRP) Error as the minimum LRP Error obtained over confidence scores to evaluate visual detectors and obtain optimal thresholds for deployment. We provide a detailed comparative analysis of LRP Error with AP and PQ, and use nearly 100 state-of-the-art visual detectors from seven visual detection tasks (i.e. object detection, keypoint detection, instance segmentation, panoptic segmentation, visual relationship detection, zero-shot detection and generalised zero-shot detection) using ten datasets to empirically show that LRP Error provides richer and more discriminative information than its counterparts. Code available at: https://github.com/kemaloksuz/LRP-Error.

Imbalance Problems in Object Detection: A Review.

In this paper, we present a comprehensive review of the imbalance problems in object detection. To analyze the problems in a systematic manner, we introduce a problem-based taxonomy. Following this taxonomy, we discuss each problem in depth and present a unifying yet critical perspective on the solutions in the literature. In addition, we identify major open issues regarding the existing imbalance problems as well as imbalance problems that have not been discussed before. Moreover, in order to keep our review up to date, we provide an accompanying webpage which catalogs papers addressing imbalance problems, according to our problem-based taxonomy. Researchers can track newer studies on this webpage available at: https://github.com/kemaloksuz/ObjectDetectionImbalance.

Ear atresia: Is there a role of apoptosis-regulating miRNAs?

OBJECTIVE: The molecular events underlying ear development involve numerous regulatory molecules; however, the role of microRNAs (miRNAs) has not been explored in patients with ear atresia. Here, we aimed to investigate the expressions of 20-22 nucleotide noncoding RNAs. METHODS: We selected 12 miRNAs that function to control post-transcriptional gene expression in different pathways, including apoptosis, angiogenesis, and chondrogenesis. The altered miRNA expressions were analyzed by real-time PCR from serum samples of 7 patients with ear atresia and 8 controls. RESULTS: We found that the expression of apoptosis-regulating miRNAs was significantly downregulated in patients with ear atresia. TThe expressions of miR126, miR146a, miR222, and miR21 were significantly decreased by 76.2-(p=0.041), 61.8-(p=0.000), 30.5-(p=0.009), and 71.21-fold (p=0.042), respectively, compared with controls. CONCLUSION: Abnormal ear development in ear atresia patients, could possibly be due to the reduced expression of apoptosis regulating miRNAs. Changes in the regulation of tumor protein p53 (TP53), p53 upregulated modulator of apoptosis (PUMA), Fas cell surface death receptor (FAS), FAS ligand (FasL), and phosphatase and tensin homolog (PTEN) directly or within the apoptosis-related cascades may play important roles during development, particularly in the external ear. This is the first report to present the possible association between apoptosis-regulating miRNAs and ear atresia/microtia.

Object detection through search with a foveated visual system.

Humans and many other species sense visual information with varying spatial resolution across the visual field (foveated vision) and deploy eye movements to actively sample regions of interests in scenes. The advantage of such varying resolution architecture is a reduced computational, hence metabolic cost. But what are the performance costs of such processing strategy relative to a scheme that processes the visual field at high spatial resolution? Here we first focus on visual search and combine object detectors from computer vision with a recent model of peripheral pooling regions found at the V1 layer of the human visual system. We develop a foveated object detector that processes the entire scene with varying resolution, uses retino-specific object detection classifiers to guide eye movements, aligns its fovea with regions of interest in the input image and integrates observations across multiple fixations. We compared the foveated object detector against a non-foveated version of the same object detector which processes the entire image at homogeneous high spatial resolution. We evaluated the accuracy of the foveated and non-foveated object detectors identifying 20 different objects classes in scenes from a standard computer vision data set (the PASCAL VOC 2007 dataset). We show that the foveated object detector can approximate the performance of the object detector with homogeneous high spatial resolution processing while bringing significant computational cost savings. Additionally, we assessed the impact of foveation on the computation of bottom-up saliency. An implementation of a simple foveated bottom-up saliency model with eye movements showed agreement in the selection of top salient regions of scenes with those selected by a non-foveated high resolution saliency model. Together, our results might help explain the evolution of foveated visual systems with eye movements as a solution that preserves perceptual performance in visual search while resulting in computational and metabolic savings to the brain.

Humans, but Not Deep Neural Networks, Often Miss Giant Targets in Scenes.

Even with great advances in machine vision, animals are still unmatched in their ability to visually search complex scenes. Animals from bees [1, 2] to birds [3] to humans [4-12] learn about the statistical relations in visual environments to guide and aid their search for targets. Here, we investigate a novel manner in which humans utilize rapidly acquired information about scenes by guiding search toward likely target sizes. We show that humans often miss targets when their size is inconsistent with the rest of the scene, even when the targets were made larger and more salient and observers fixated the target. In contrast, we show that state-of-the-art deep neural networks do not exhibit such deficits in finding mis-scaled targets but, unlike humans, can be fooled by target-shaped distractors that are inconsistent with the expected target's size within the scene. Thus, it is not a human deficiency to miss targets when they are inconsistent in size with the scene; instead, it is a byproduct of a useful strategy that the brain has implemented to rapidly discount potential distractors.

Optimal and human eye movements to clustered low value cues to increase decision rewards during search.

Rewards have important influences on the motor planning of primates and the firing of neurons coding visual information and action. When eye movements to a target are differentially rewarded across locations, primates execute saccades towards the possible target location with the highest expected value, a product of sensory evidence and potentially earned reward (saccade to maximum expected value model, sMEV). Yet, in the natural world eye movements are not directly rewarded. Their role is to gather information to support subsequent rewarded search decisions and actions. Less is known about the effects of decision rewards on saccades. We show that when varying the decision rewards across cued locations following visual search, humans can plan their eye movements to increase decision rewards. Critically, we report a scenario for which five of seven tested humans do not preferentially deploy saccades to the possible target location with the highest reward, a strategy which is optimal when rewarding eye movements. Instead, these humans make saccades towards lower value but clustered locations when this strategy optimizes decision rewards consistent with the preferences of an ideal Bayesian reward searcher that takes into account the visibility of the target across eccentricities. The ideal reward searcher can be approximated with a sMEV model with pooling of rewards from spatially clustered locations. We also find observers with systematic departures from the optimal strategy and inter-observer variability of eye movement plans. These deviations often reflect multiplicity of fixation strategies that lead to near optimal decision rewards but, for some observers, it relates to suboptimal choices in eye movement planning.

Low-Level Hierarchical Multiscale Segmentation Statistics of Natural Images.

This paper is aimed at obtaining the statistics as a probabilistic model pertaining to the geometric, topological and photometric structure of natural images. The image structure is represented by its segmentation graph derived from the low-level hierarchical multiscale image segmentation. We first estimate the statistics of a number of segmentation graph properties from a large number of images. Our estimates confirm some findings reported in the past work, as well as provide some new ones. We then obtain a Markov random field based model of the segmentation graph which subsumes the observed statistics. To demonstrate the value of the model and the statistics, we show how its use as a prior impacts three applications: image classification, semantic image segmentation and object detection.