Search

Background: We studied the evolution over time of diffusion weighted imaging (DWI) lesion volume and the factors involved on early and late infarct growth (EIG and LIG) in stroke patients undergoing endovascular treatment (EVT) according to the final revascularization grade. Methods: This is a prospective cohort of patients with anterior large artery occlusion undergoing EVT arriving at 1 comprehensive stroke center. Magnetic resonance imaging was performed on arrival (pre-EVT), Results: We included 98 patients (mean age 70, median National Institutes of Health Stroke Scale score 17, final mTICI≥2b 86%). Median EIG and LIG were 48 and 63.3 mL in patients with final mTICIρ =0.667; P ρ =0.614; P Conclusions: Infarct grows during and after EVT, especially in nonrecanalizers but also to a lesser extent in recanalizers. In recanalizers, number of passes and DWI volume influence EIG, while number of passes, DWI, and hypoperfused volume after the procedure determine LIG.

Introduction: After achieving successful reperfusion some acute stroke patients still exhibit persistent perfusion deficits. These deficits have been defined in a heterogeneous manner by using CBF, CBV or Tmax maps as a perfusion deficit in the previous ischemic penumbra (impaired microcirculation perfusion-IMP) or inside the infarcted tissue (no reflow-NR). The significance, frequency and pathophysiology of this phenomenon are so far unknown. Methods: Prospective cohort of patients with isolated anterior intracranial occlusion undergoing endovascular treatment (EVT) and achieving complete recanalization (final mTICI≥2B). Brain MRI was performed on arrival (pre-EVT) and &lt2h after EVT (post-EVT). Infarcted tissue was segmented on DWI pre-EVT. Pre and post-EVT perfusion maps were obtained with Olea software. NR was defined in the post-EVT perfusion maps as the region inside the infarcted tissue which showed a CBV&lt15% compared to the contralateral side, while IMP was the equivalent area inside the previous tissue in penumbra. We evaluated the association between both NR and IMP and NIHSS at 24h, NIHSS at discharge and modified Rankin score (mRS) at three months adjusting by baseline NIHSS and final mTICI. Results: Thirty-five patients were included. All of them had IMP areas and 25 (71%) had NR areas. The median volume of NR and IMP was 3.43ml [IQR 1.43-8.81], corresponding to 17.9% of the infarcted tissue [IQR 4.2-50.3] and 33.9ml [IQR 14.0-69.3] (27.7% [IQR 8.2-51.2] of the penumbra) respectively. Patients with NR areas had higher NIHSS at 24 h and at discharge and higher mRS at 3 months. Volume of NR was independently associated with higher NIHSS at 24 h and at discharge. No independent association was found with IMP volume. Neither NR nor IMP were associated with hemorrhagic transformation. Patients receiving rTPA previous to EVT showed higher perfusion values inside the infarct than patients with primary EVT (2.31 mL/100g [1.48-2.43] vs 0.92 [0.7-1.47] p=0.02), although NR areas appeared in the same proportion in both groups. Conclusions: No reflow phenomenon can be a marker of poor outcome in the early evaluation of successfully recanalized stroke patients especially when the persistent perfusion deficit is located inside the infarcted tissue.

A group of agents are said to collude if they share information or make joint decisions in a manner contrary to explicit or implicit social rules that results in an unfair advantage over non-colluding agents or other interested parties. For instance, collusion manifests as sharing answers in exams, as colluding bidders in auctions, or as colluding participants (e.g., Turkers) in crowd sourcing. This paper studies the latter, where the goal of the colluding participants is to "earn" money without doing the actual work, for instance by copying product ratings of another colluding participant, adding limited noise as attempted obfuscation. Such collusion not only yields fewer independent ratings, but may also introduce strong biases in aggregate results if undetected. Our proposed unsupervised collusion detection algorithm identifies colluding groups in crowd sourcing with fairly high accuracy both in synthetic and real data, and results in significant bias reduction, such as minimizing shifts from the true mean in rating tasks and recovering the true variance among raters.

While recent advances in computer vision have caused object recognition rates to spike, there is still much room for improvement. In this paper, we develop an algorithm to improve object recognition by integrating human-generated contextual information with vision algorithms. Specifically, we examine how interactive systems such as robots can utilize two types of context information--verbal descriptions of an environment and human-labeled datasets. We propose a re-ranking schema, MultiRank, for object recognition that can efficiently combine such information with the computer vision results. In our experiments, we achieve up to 9.4% and 16.6% accuracy improvements using the oracle and the detected bounding boxes, respectively, over the vision-only recognizers. We conclude that our algorithm has the ability to make a significant impact on object recognition in robotics and beyond.

We investigate machine learning methods for diagnostic screening of heart disease. Coronary heart disease is the leading cause of death in the US, causing more deaths than all types of cancers combined. Early diagnosis of heart disease in women is harder than it is in men and typically requires the administration of several clinical tests on the patient. Most risk stratification methods aggregate the results of such tests, including the risky, invasive procedures that cannot be administered on all patients. In this paper, our goal is to identify patients who are under high-risk of having heart disease and related adverse events, using a minimal number of diagnostic tests, especially less invasive ones. The low frequency of patients with severe heart disease in the dataset is challenging for most conventional machine learning methods. To overcome this problem, we develop and apply a cost-sensitive k nearest neighbor algorithm. Our contributions are two fold: First, we compare the predictive value of several diagnostic procedures for heart disease, including electrocardiography, angiography, radionuclide perfusion and conclude that in womens heart disease, certain combinations of noninvasive techniques are more predictive than some of the widely used invasive procedures. Then, we evaluate held out data and achieve an AUROC over 0.70, signifying valuable clinical utility, using only the least costly and least invasive tests.

Unsupervised discovery of synonymous phrases is useful in a variety of tasks ranging from text mining and search engines to semantic analysis and machine translation. This paper presents an unsupervised corpus-based conditional model: Near-Synonym System (NeSS) for finding phrasal synonyms and near synonyms that requires only a large monolingual corpus. The method is based on maximizing information-theoretic combinations of shared contexts and is parallelizable for large-scale processing. An evaluation framework with crowd-sourced judgments is proposed and results are compared with alternate methods, demonstrating considerably superior results to the literature and to thesaurus look up for multi-word phrases. Moreover, the results show that the statistical scoring functions and overall scalability of the system are more important than language specific NLP tools. The method is language-independent and practically useable due to accuracy and real-time performance via parallel decomposition.

Acral lentiginous melanoma is a very aggressive, malignant cutaneous tumor which has a predilection for the plantar surface of the feet, palms of the hand, and the digits. The lesion presents as a rapidly spreading, darkly pigmented patch and may display varying degrees of pigmentation. These lesions have a propensity to metastasize to the central nervous system, liver, lungs, bone, and lymph nodes. Due to the aggressive nature of these lesions, early recognition and treatment, consisting of excision in toto with clean margins, are imperative. The authors present a thorough review of the literature and an illustrative case of acral lentiginous melanoma of the lower extremity.

Angioleiomyomas are benign soft tissue lesions that should be included in the differential diagnosis of any pedal soft tissue mass. There should be an increased index of suspicion for angioleiomyoma, especially when a freely movable subcutaneous mass is encountered in a middle-aged female patient. Treatment of such masses should involve surgical excision to relieve the symptomatology and to obtain tissue for a definitive histologic analysis. If the mass recurs, then the possibility of leiomyosarcoma should be explored.

A case of laryngeal leishmaniasis, with symptoms of hoarseness and odinophagia which had developed over the past year, is presented. Clinical features and histological findings are discussed. Visceral leishmaniasis is increasingly associated with HIV infection and some authors have suggested the possibility of including it as a diagnostic criterium for AIDS in HIV-positive patients.When any case of leishmaniasis presents atypical clinical features, localization or treatment response in endemic areas, HIV infection should be ruled out.