LIVIVO - Search results -

Search results

Result 1 - 10 of total 19

Search options

Article ; Online: First-in-paediatric uses of a mechanical aspiration system for percutaneous removal of right atrial masses.

Daniels, Zachary / Armstrong, Aimee K / Salavitabar, Arash

2023 Volume 33, Issue 9, Page(s) 1730–1732

Abstract: We present the first-in-paediatric uses of a mechanical aspiration system for percutaneous removal of right atrial masses in three patients, including central line-related thrombus and metastatic tumour. Percutaneous mechanical removal of right atrial ... ...

Abstract	We present the first-in-paediatric uses of a mechanical aspiration system for percutaneous removal of right atrial masses in three patients, including central line-related thrombus and metastatic tumour. Percutaneous mechanical removal of right atrial masses can be performed safely and effectively.
MeSH term(s)	Humans ; Child ; Thrombectomy ; Suction ; Atrial Fibrillation ; Heart Diseases ; Thrombosis/surgery
Language	English
Publishing date	2023-03-16
Publishing country	England
Document type	Journal Article
ZDB-ID	1078466-4
ISSN	1467-1107 ; 1047-9511
ISSN (online)	1467-1107
ISSN	1047-9511
DOI	10.1017/S1047951123000318
Database	MEDical Literature Analysis and Retrieval System OnLINE

Full text online

Accessible to users with ZB MED library card

In stock of ZB MED Cologne/Königswinter

Zs.A 4050: Show issues

Location:
Je nach Verfügbarkeit (siehe Angabe bei Bestand)
bis Jg. 1994: Bestellungen von Artikeln über das Online-Bestellformular
Jg. 1995 - 2021: Lesesall (2.OG)
ab Jg. 2022: Lesesaal (EG)

Order via subito

This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

Details ▾

Book ; Online: A Dynamic Data Driven Approach for Explainable Scene Understanding

Daniels, Zachary A / Metaxas, Dimitris

2022

Abstract: Scene-understanding is an important topic in the area of Computer Vision, and illustrates computational challenges with applications to a wide range of domains including remote sensing, surveillance, smart agriculture, robotics, autonomous driving, and ... ...

Abstract	Scene-understanding is an important topic in the area of Computer Vision, and illustrates computational challenges with applications to a wide range of domains including remote sensing, surveillance, smart agriculture, robotics, autonomous driving, and smart cities. We consider the active explanation-driven understanding and classification of scenes. Suppose that an agent utilizing one or more sensors is placed in an unknown environment, and based on its sensory input, the agent needs to assign some label to the perceived scene. The agent can adjust its sensor(s) to capture additional details about the scene, but there is a cost associated with sensor manipulation, and as such, it is important for the agent to understand the scene in a fast and efficient manner. It is also important that the agent understand not only the global state of a scene (e.g., the category of the scene or the major events taking place in the scene) but also the characteristics/properties of the scene that support decisions and predictions made about the global state of the scene. Finally, when the agent encounters an unknown scene category, it must be capable of refusing to assign a label to the scene, requesting aid from a human, and updating its underlying knowledge base and machine learning models based on feedback provided by the human. We introduce a dynamic data driven framework for the active explanation-driven classification of scenes. Our framework is entitled ACUMEN: Active Classification and Understanding Method by Explanation-driven Networks. To demonstrate the utility of the proposed ACUMEN approach and show how it can be adapted to a domain-specific application, we focus on an example case study involving the classification of indoor scenes using an active robotic agent with vision-based sensors, i.e., an electro-optical camera. Comment: Unpublished draft of book chapter
Keywords	Computer Science - Computer Vision and Pattern Recognition
Subject code	004
Publishing date	2022-06-17
Publishing country	us
Document type	Book ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Article ; Online: Pediatric extracorporeal cardiopulmonary resuscitation for yew cardiotoxicity.

Daniels, Zachary / Hays, Hannah / Carrillo, Sergio / Kamp, Anna / Gauntt, Jennifer

Perfusion

2023 , Page(s) 2676591231210452

Abstract: Introduction: English yew is an evergreen conifer frequently planted in household gardens and, when ingested in large doses, results in severe cardiotoxicity characterized by difficult to control ventricular arrhythmias with high rates of mortality.: ... ...

Abstract	Introduction: English yew is an evergreen conifer frequently planted in household gardens and, when ingested in large doses, results in severe cardiotoxicity characterized by difficult to control ventricular arrhythmias with high rates of mortality. Case report: A previously healthy teenage female presented as an out-of-hospital cardiac arrest with refractory ventricular arrhythmias and severe biventricular dysfunction. Due to rapid deterioration in her clinical status, she was cannulated onto venoarterial extracorporeal membrane oxygenation (ECMO) which resulted in rapid normalization of her rhythm and ventricular function. Discussion: Our case highlights the importance of keeping a broad differential diagnosis when considering etiologies of ventricular arrhythmias in the pediatric population. The final diagnosis was not made until after discharge and implantable cardiac defibrillator (ICD) placement. Conclusion: The delayed diagnosis of this intentional English yew ingestion ultimately resulted subsequent ICD removal. Early ECMO activation in cases of English yew toxicity can be essential for patient survival.
Language	English
Publishing date	2023-10-24
Publishing country	England
Document type	Journal Article
ZDB-ID	645038-6
ISSN	1477-111X ; 0267-6591
ISSN (online)	1477-111X
ISSN	0267-6591
DOI	10.1177/02676591231210452
Database	MEDical Literature Analysis and Retrieval System OnLINE

In stock of ZB MED Cologne/Königswinter

Zs.A 2424: Show issues

Location:
Je nach Verfügbarkeit (siehe Angabe bei Bestand)
bis Jg. 1994: Bestellungen von Artikeln über das Online-Bestellformular
Jg. 1995 - 2021: Lesesall (2.OG)
ab Jg. 2022: Lesesaal (EG)

Order via subito

Details ▾
- See ZB MED holdings
- Order with fees

Book ; Online: Learning with Local Gradients at the Edge

Lomnitz, Michael / Daniels, Zachary / Zhang, David / Piacentino, Michael

2022

Abstract: To enable learning on edge devices with fast convergence and low memory, we present a novel backpropagation-free optimization algorithm dubbed Target Projection Stochastic Gradient Descent (tpSGD). tpSGD generalizes direct random target projection to ... ...

Abstract	To enable learning on edge devices with fast convergence and low memory, we present a novel backpropagation-free optimization algorithm dubbed Target Projection Stochastic Gradient Descent (tpSGD). tpSGD generalizes direct random target projection to work with arbitrary loss functions and extends target projection for training recurrent neural networks (RNNs) in addition to feedforward networks. tpSGD uses layer-wise stochastic gradient descent (SGD) and local targets generated via random projections of the labels to train the network layer-by-layer with only forward passes. tpSGD doesn't require retaining gradients during optimization, greatly reducing memory allocation compared to SGD backpropagation (BP) methods that require multiple instances of the entire neural network weights, input/output, and intermediate results. Our method performs comparably to BP gradient-descent within 5% accuracy on relatively shallow networks of fully connected layers, convolutional layers, and recurrent layers. tpSGD also outperforms other state-of-the-art gradient-free algorithms in shallow models consisting of multi-layer perceptrons, convolutional neural networks (CNNs), and RNNs with competitive accuracy and less memory and time. We evaluate the performance of tpSGD in training deep neural networks (e.g. VGG) and extend the approach to multi-layer RNNs. These experiments highlight new research directions related to optimized layer-based adaptor training for domain-shift using tpSGD at the edge.
Keywords	Computer Science - Machine Learning ; Computer Science - Artificial Intelligence
Subject code	006
Publishing date	2022-08-17
Publishing country	us
Document type	Book ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Article: High-Dose Midazolam for Pediatric Refractory Status Epilepticus: A Single-Center Retrospective Study.

Daniels, Zachary S / Srdanovic, Nina / Rychlik, Karen / Smith, Craig / Goldstein, Joshua / George, Alfred L

Pediatric critical care medicine : a journal of the Society of Critical Care Medicine and the World Federation of Pediatric Intensive and Critical Care Societies

2022 Volume 23, Issue 11, Page(s) 929–935

Abstract: Objectives: We sought to describe the prevalence of midazolam treatment failure in children with refractory status epilepticus (RSE) and define a threshold dose associated with diminishing frequency of seizure cessation.: Design: Single center ... ...

Abstract	Objectives: We sought to describe the prevalence of midazolam treatment failure in children with refractory status epilepticus (RSE) and define a threshold dose associated with diminishing frequency of seizure cessation. Design: Single center retrospective cohort study. Setting: Single-center, quaternary-care PICU. Patients: Children younger than 18 years old admitted to the PICU from 2009 to 2018 who had RSE requiring a continuous midazolam infusion. Interventions: None. Measurements and main results: We identified individuals with RSE through a data analytics inquiry. Receiver operating characteristic (ROC) curve analysis and Youden's index were used to assess the midazolam dose threshold associated with the highest sensitivity and specificity in identifying seizure cessation. A logistic regression model was used to determine if there was an association between maximum midazolam dose and seizure cessation. Of the 45 patients who met inclusion criteria for this study, 27 (60%) had seizure cessation with a midazolam infusion, whereas 18 (40%) required an additional pentobarbital infusion for seizure cessation. There was an association between maximum midazolam dose and seizure cessation, with patients more likely to fail treatment when midazolam was administered at higher doses. The maximum midazolam dose displayed high area under the ROC curve value for seizure cessation, and the Youden's J index cut-off point was 525 μg/kg/hr. Treatment above this dose was associated with diminishing frequency of seizure cessation. The median time spent titrating midazolam above 500 μg/kg/hr for those patients who required pentobarbital for seizure cessation was 3.83 hours (interquartile range, 2.28-5.58 hr). Conclusions: In pediatric patients with RSE requiring high dose midazolam, considerable time is spent titrating doses in a range (above 500 µg/kg/hr) that is associated with diminishing frequency of seizure cessation.
MeSH term(s)	Child ; Humans ; Adolescent ; Midazolam ; Retrospective Studies ; Pentobarbital/therapeutic use ; Anticonvulsants/therapeutic use ; Status Epilepticus/drug therapy
Chemical Substances	Midazolam (R60L0SM5BC) ; Pentobarbital (I4744080IR) ; Anticonvulsants
Language	English
Publishing date	2022-07-27
Publishing country	United States
Document type	Journal Article
ZDB-ID	2052349-X
ISSN	1947-3893 ; 1529-7535
ISSN (online)	1947-3893
ISSN	1529-7535
DOI	10.1097/PCC.0000000000003043
Database	MEDical Literature Analysis and Retrieval System OnLINE

In stock of ZB MED Cologne/Königswinter

Zs.A 5600: Show issues			Location: Je nach Verfügbarkeit (siehe Angabe bei Bestand) bis Jg. 1994: Bestellungen von Artikeln über das Online-Bestellformular Jg. 1995 - 2021: Lesesall (2.OG) ab Jg. 2022: Lesesaal (EG)
Zs.MO 472: Show issues

Order via subito

Details ▾
- See ZB MED holdings
- Order with fees

Article ; Online: Ventricular Arrhythmic Events After Transcatheter Pulmonary Valve Replacement in Adults with Repaired Tetralogy of Fallot.

Dodeja, Anudeep K / Daniels, Zachary / Mah, May Ling / Shay, Victoria / Bai, Shasha / Hor, Kan / Kertesz, Naomi / Daniels, Curt / Kamp, Anna

Pediatric cardiology

2023 Volume 44, Issue 6, Page(s) 1226–1231

Abstract: Arrhythmias are a major cause of morbidity and mortality in repaired Tetralogy of Fallot (rTOF). However, predicting those at risk for life-threatening ventricular arrhythmias (VA) remains difficult. Many centers approach risk assessment at the time of ... ...

Abstract	Arrhythmias are a major cause of morbidity and mortality in repaired Tetralogy of Fallot (rTOF). However, predicting those at risk for life-threatening ventricular arrhythmias (VA) remains difficult. Many centers approach risk assessment at the time of surgical pulmonary valve intervention. Increasing numbers of patients have undergone transcatheter pulmonary valve replacement (TPVR), yet there are no studies evaluating VA in rTOF undergoing TPVR and the approach to risk assessment for these patients. A single center retrospective study was performed. The institutional interventional database was queried to identify all adults ≥ 18 years of age with rTOF status who underwent TPVR from 2010 to 2019. A total of 81 patients with rTOF underwent TPVR from 2010 to 2019. Mean age at time of TPVR was 27 ± 13 years; follow up after TPVR was 6.4 ± 3.1 years. VA events occurred in 4 patients (5%). There was no significant difference in current era VA risk factors in rTOF patients between the VA event group and the non-VA event group. VA risk in this cohort of rTOF with TPVR was 5%, comparable to that reported in current era surgical cohort with similar follow up. Multi-center agreement on risk assessment protocol is needed for future studies.
MeSH term(s)	Adult ; Humans ; Adolescent ; Young Adult ; Pulmonary Valve/surgery ; Tetralogy of Fallot ; Heart Valve Prosthesis Implantation/methods ; Retrospective Studies ; Cardiac Catheterization/methods ; Treatment Outcome ; Pulmonary Valve Insufficiency/etiology ; Pulmonary Valve Insufficiency/surgery
Language	English
Publishing date	2023-02-10
Publishing country	United States
Document type	Journal Article
ZDB-ID	800857-7
ISSN	1432-1971 ; 0172-0643
ISSN (online)	1432-1971
ISSN	0172-0643
DOI	10.1007/s00246-023-03120-1
Database	MEDical Literature Analysis and Retrieval System OnLINE

Full text online

Accessible to users with ZB MED library card

In stock of ZB MED Cologne/Königswinter

Zs.A 1528: Show issues

Location:
Je nach Verfügbarkeit (siehe Angabe bei Bestand)
bis Jg. 1994: Bestellungen von Artikeln über das Online-Bestellformular
Jg. 1995 - 2021: Lesesall (1.OG)
ab Jg. 2022: Lesesaal (EG)

Order via subito

Details ▾

Article: Traumatic Facial Tattoo Injuries From Gunpowder and Ammunition: A Case Series.

Jenzer, Andrew C / Storrs, Bradley P / Daniels, Zachary / Hanlon, Jeremy J

Craniomaxillofacial trauma & reconstruction

2020 Volume 13, Issue 2, Page(s) 133–137

Abstract: Background and overview: Gunpowder inclusion injuries are rare occurrences in the civilian sector but are more frequently encountered in the military setting. The authors report a case series of 3 active duty military service members treated by an Army ... ...

Abstract	Background and overview: Gunpowder inclusion injuries are rare occurrences in the civilian sector but are more frequently encountered in the military setting. The authors report a case series of 3 active duty military service members treated by an Army hospital's Oral & Maxillofacial Surgery service for the removal of embedded gunpowder particles so as to avoid traumatic tattooing. Case description: Three otherwise healthy active duty military service members were treated for gunpowder inclusion injuries incurred while conducting live fire training exercises at a state-side military installation between 2018 and 2019. All 3 males presented with injuries of the same etiology: Their weapons malfunctioned, and while visually inspecting the action, a round exploded close to the face. This peppered the face with gunpowder particles that were both superficially and deeply embedded. Treatment focused on individual removal using fine forceps. The patients were followed up and healed quickly without any complications, specifically without traumatic tattooing from the gunpowder injuries. Conclusion and practical implications: Gunpowder inclusion injuries should be addressed quickly to remove the particles before epidermal healing occurs, thus avoiding the complication of traumatic tattooing. This surgical team recommends meticulous fine forceps removal as the treatment of choice for larger particles.
Language	English
Publishing date	2020-03-16
Publishing country	United States
Document type	Case Reports
ISSN	1943-3875
ISSN	1943-3875
DOI	10.1177/1943387520902893
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Book ; Online: Saccade Mechanisms for Image Classification, Object Detection and Tracking

Farkya, Saurabh / Daniels, Zachary / Raghavan, Aswin Nadamuni / Zhang, David / Piacentino, Michael

2022

Abstract: We examine how the saccade mechanism from biological vision can be used to make deep neural networks more efficient for classification and object detection problems. Our proposed approach is based on the ideas of attention-driven visual processing and ... ...

Abstract	We examine how the saccade mechanism from biological vision can be used to make deep neural networks more efficient for classification and object detection problems. Our proposed approach is based on the ideas of attention-driven visual processing and saccades, miniature eye movements influenced by attention. We conduct experiments by analyzing: i) the robustness of different deep neural network (DNN) feature extractors to partially-sensed images for image classification and object detection, and ii) the utility of saccades in masking image patches for image classification and object tracking. Experiments with convolutional nets (ResNet-18) and transformer-based models (ViT, DETR, TransTrack) are conducted on several datasets (CIFAR-10, DAVSOD, MSCOCO, and MOT17). Our experiments show intelligent data reduction via learning to mimic human saccades when used in conjunction with state-of-the-art DNNs for classification, detection, and tracking tasks. We observed minimal drop in performance for the classification and detection tasks while only using about 30\% of the original sensor data. We discuss how the saccade mechanism can inform hardware design via ``in-pixel'' processing. Comment: 4 Pages, 6 figures, will be presented at CVPR2022-NeuroVision workshop as a Lightning talk
Keywords	Computer Science - Computer Vision and Pattern Recognition ; Computer Science - Machine Learning ; Computer Science - Neural and Evolutionary Computing
Subject code	006
Publishing date	2022-06-10
Publishing country	us
Document type	Book ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Book ; Online: Model-Free Generative Replay for Lifelong Reinforcement Learning

Daniels, Zachary / Raghavan, Aswin / Hostetler, Jesse / Rahman, Abrar / Sur, Indranil / Piacentino, Michael / Divakaran, Ajay

Application to Starcraft-2

2022

Abstract: One approach to meet the challenges of deep lifelong reinforcement learning (LRL) is careful management of the agent's learning experiences, to learn (without forgetting) and build internal meta-models (of the tasks, environments, agents, and world). ... ...

Abstract	One approach to meet the challenges of deep lifelong reinforcement learning (LRL) is careful management of the agent's learning experiences, to learn (without forgetting) and build internal meta-models (of the tasks, environments, agents, and world). Generative replay (GR) is a biologically inspired replay mechanism that augments learning experiences with self-labelled examples drawn from an internal generative model that is updated over time. We present a version of GR for LRL that satisfies two desiderata: (a) Introspective density modelling of the latent representations of policies learned using deep RL, and (b) Model-free end-to-end learning. In this paper, we study three deep learning architectures for model-free GR, starting from a na\"ive GR and adding ingredients to achieve (a) and (b). We evaluate our proposed algorithms on three different scenarios comprising tasks from the Starcraft-2 and Minigrid domains. We report several key findings showing the impact of the design choices on quantitative metrics that include transfer learning, generalization to unseen tasks, fast adaptation after task change, performance wrt task expert, and catastrophic forgetting. We observe that our GR prevents drift in the features-to-action mapping from the latent vector space of a deep RL agent. We also show improvements in established lifelong learning metrics. We find that a small random replay buffer significantly increases the stability of training. Overall, we find that "hidden replay" (a well-known architecture for class-incremental classification) is the most promising approach that pushes the state-of-the-art in GR for LRL and observe that the architecture of the sleep model might be more important for improving performance than the types of replay used. Our experiments required only 6% of training samples to achieve 80-90% of expert performance in most Starcraft-2 scenarios. Comment: Accepted to the First Conference on Lifelong Learning Agents (CoLLAs 2022)
Keywords	Computer Science - Machine Learning ; Computer Science - Artificial Intelligence
Subject code	006
Publishing date	2022-08-09
Publishing country	us
Document type	Book ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Book ; Online: Efficient Model Adaptation for Continual Learning at the Edge

Daniels, Zachary A. / Hu, Jun / Lomnitz, Michael / Miller, Phil / Raghavan, Aswin / Zhang, Joe / Piacentino, Michael / Zhang, David

2023

Abstract: Most machine learning (ML) systems assume stationary and matching data distributions during training and deployment. This is often a false assumption. When ML models are deployed on real devices, data distributions often shift over time due to changes in ...

Abstract	Most machine learning (ML) systems assume stationary and matching data distributions during training and deployment. This is often a false assumption. When ML models are deployed on real devices, data distributions often shift over time due to changes in environmental factors, sensor characteristics, and task-of-interest. While it is possible to have a human-in-the-loop to monitor for distribution shifts and engineer new architectures in response to these shifts, such a setup is not cost-effective. Instead, non-stationary automated ML (AutoML) models are needed. This paper presents the Encoder-Adaptor-Reconfigurator (EAR) framework for efficient continual learning under domain shifts. The EAR framework uses a fixed deep neural network (DNN) feature encoder and trains shallow networks on top of the encoder to handle novel data. The EAR framework is capable of 1) detecting when new data is out-of-distribution (OOD) by combining DNNs with hyperdimensional computing (HDC), 2) identifying low-parameter neural adaptors to adapt the model to the OOD data using zero-shot neural architecture search (ZS-NAS), and 3) minimizing catastrophic forgetting on previous tasks by progressively growing the neural architecture as needed and dynamically routing data through the appropriate adaptors and reconfigurators for handling domain-incremental and class-incremental continual learning. We systematically evaluate our approach on several benchmark datasets for domain adaptation and demonstrate strong performance compared to state-of-the-art algorithms for OOD detection and few-/zero-shot NAS. Comment: Unpublished White Paper
Keywords	Computer Science - Machine Learning ; Computer Science - Artificial Intelligence ; Computer Science - Computer Vision and Pattern Recognition
Subject code	006
Publishing date	2023-08-03
Publishing country	us
Document type	Book ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

To top

Your last searches

Full text online

More links

Kategorien

In stock of ZB MED Cologne/Königswinter

Order via subito

Full text online

More links

Kategorien

Inter-library loan at ZB MED

More links

Kategorien

In stock of ZB MED Cologne/Königswinter

Order via subito

Full text online

More links

Kategorien

Inter-library loan at ZB MED

More links

Kategorien

In stock of ZB MED Cologne/Königswinter

Order via subito

Full text online

More links

Kategorien

In stock of ZB MED Cologne/Königswinter

Order via subito

More links

Kategorien

Order via subito

Inter-library loan at ZB MED

Full text online

More links

Kategorien

Inter-library loan at ZB MED

Full text online

More links

Kategorien

Inter-library loan at ZB MED

Full text online

More links

Kategorien

Inter-library loan at ZB MED