检索结果-内蒙古大学图书馆

Multi-modal Wound classification using wound image and location by deep neural network

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Anisuzzaman, D.M. Patel, Yash Rostami, Behrouz Niezgoda, Jeffrey Gopalakrishnan, Sandeep Yu, Zeyun Department of Computer Science University of Wisconsin-Milwaukee MilwaukeeWI United States Department of Electrical Engineering University of Wisconsin-Milwaukee MilwaukeeWI53211 United States Wound and Vascular Center MilwaukeeWI United States College of Nursing University of Wisconsin Milwaukee MilwaukeeWI United States Department of Biomedical Engineering University of Wisconsin-Milwaukee MilwaukeeWI United States

Wound classification is an essential step of wound diagnosis. An efficient classifier can assist wound specialists in classifying wound types with less financial and time costs and help them decide an optimal treatment procedure. This study developed a deep neural network-based multi-modal classifier using wound images and their corresponding locations to categorize wound images into multiple classes, including diabetic, pressure, surgical, and venous ulcers. A body map is also developed to prepare the location data, which can help wound specialists tag wound locations more efficiently. Three datasets containing images and their corresponding location information are designed with the help of wound specialists. The multi-modal network is developed by concatenating the image-based and location-based classifier's outputs with some other modifications. The maximum accuracy on mixed-class classifications (containing background and normal skin) varies from 77.33% to 100% on different experiments. The maximum accuracy on wound-class classifications (containing only diabetic, pressure, surgical, and venous) varies from 72.95% to 98.08% on different experiments. The proposed multi-modal network also shows a significant improvement in results from the previous works of literature. Copyright © 2021, The Authors. All rights reserved.

关键词： Location

Segmentation of lungs in chest X-ray image using generative adversarial networks

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Munawar, Faizan Azmat, Shoaib Iqbal, Talha Gronlund, Christer Ali, Hazrat Department of Electrical and Computer Engineering COMSATS University Islamabad Abbottabad Campus Pakistan Department of Medicine National University of Ireland Galway Ireland Department of Radiation Sciences Biomedical Engineering Umeå University Umeå Sweden

Chest X-ray (CXR) is a low-cost medical imaging technique. It is a common procedure for the identification of many respiratory diseases compared to MRI, CT, and PET scans. This paper presents the use of generative adversarial networks (GAN) to perform the task of lung segmentation on a given CXR. GANs are popular to generate realistic data by learning the mapping from one domain to another. In our work, the generator of the GAN is trained to generate a segmented mask of a given input CXR. The discriminator distinguishes between a ground truth and the generated mask, and updates the generator through the adversarial loss measure. The objective is to generate masks for the input CXR, which are as realistic as possible compared to the ground truth masks. The model is trained and evaluated using four different discriminators referred to as D1, D2, D3 and D4 respectively. Experimental results on three different CXR datasets reveal that the proposed model is able to achieve a dice-score of 0.9740, and IOU score of 0.943, which are better than other reported state-of-the art results. Copyright © 2020, The Authors. All rights reserved.

关键词： Generative adversarial networks

SCPM-Net: An Anchor-Free 3D Lung Nodule Detection Network using Sphere Representation and Center Points Matching

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Luo, Xiangde Song, Tao Wang, Guotai Chen, Jieneng Chen, Yinan Li, Kang Metaxas, Dimitris N. Zhang, Shaoting School of Mechanical and Electrical Engineering University of Electronic Science and Technology of China Chengdu China SenseTime Research Shanghai China College of Electronics and Information Engineering Tongji University Shanghai China West China Biomedical Big Data Center Sichuan University West China Hospital Chengdu China Department of Computer Science Rutgers University PiscatawayNJ08854 United States

Automatic and accurate lung nodule detection from 3D Computed Tomography (CT) scans plays a vital role in efficient lung cancer screening. Despite the state-of-the-art performance obtained by recent anchor-based detectors using Convolutional Neural Networks (CNNs) for this task, they require predetermined anchor parameters such as the size, number, and aspect ratio of anchors, and have limited robustness when dealing with lung nodules with a massive variety of sizes. To overcome these problems, we propose a 3D sphere representation-based center-points matching detection network (SCPM-Net) that is anchor-free and automatically predicts the position, radius, and offset of nodules without manual design of nodule/anchor parameters. The SCPM-Net consists of two novel components: sphere representation and center points matching. First, to match the nodule annotation in clinical practice, we replace the commonly used bounding box with our proposed bounding sphere to represent nodules with the centroid, radius, and local offset in 3D space. A compatible sphere-based intersection over-union loss function is introduced to train the lung nodule detection network stably and efficiently. Second, we empower the network anchor-free by designing a positive center-points selection and matching (CPM) process, which naturally discards pre-determined anchor boxes. An online hard example mining and re-focal loss subsequently enable the CPM process to be more robust, resulting in more accurate point assignment and mitigation of class imbalance. In addition, to better capture spatial information and 3D context for the detection, we propose to fuse multi-level spatial coordinate maps with the feature extractor and combine them with 3D squeeze-and-excitation attention modules. Experimental results on the LUNA16 dataset showed that our proposed SCPM-Net framework achieves superior performance compared with existing anchor-based and anchor-free methods for lung nodule detection with the avera

关键词： Spheres

Preemptive periodic epidemic control reduces life and healthcare system costs without aggravation of social and economic losses

学校读者我要写书评

暂无评论

arXiv 2021年

作者： De Nicolao, Giuseppe Colaneri, Marta Filippo, Alessandro Di Blanchini, Franco Bolzern, Paolo Colaneri, Patrizio Giordano, Giulia Bruno, Raffaele Department of Electrical Computer and Biomedical Engineering University of Pavia Pavia Italy Division of Infectious Diseases I Fondazione IRCCS Policlinico San Matteo Pavia Italy Department of Mathematics Computer Science and Physics University of Udine Udine Italy Department of Electronics Information and Bioengineering Politecnico di Milano Milan Italy Department of Industrial Engineering University of Trento Trento Italy Department of Clinical Surgical Diagnostic and Pediatric Sciences University of Pavia Pavia Italy

Many countries are managing COVID-19 epidemic by switching between lighter and heavier restrictions. While an open-close and a close-open cycle have comparable socio-economic costs, the former leads to a much heavier burden in terms of deaths and pressure on the healthcare system. An empirical demonstration of the toll ensuing from procrastination was recently observed in Israel, where both cycles were enforced from late August to mid-December 2020, yielding some 1,600 deaths with open-close compared to 440 with close-open. © 2021, CC BY.

关键词： Losses

Comparison of Feedback Approaches to Improve Training in Partial Weight-Bearing

学校读者我要写书评

暂无评论

Comparison of Feedback Approaches to Improve Training in Par...

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Ian Smith Satinder Gill Scott Bateman Erik Scheme Institute of Biomedical Engineering (IBME) University of New Brunswick (UNB) Fredericton Canada PDF with the IBME at UNB Faculty of Computer Science at UNB Department of Electrical and Computer Engineering at UNB New Brunswick Innovation Research Chair in Medical Devices and Technologies at the IBME

ISBN: (数字)9781728119908

ISBN: (纸本)9781728119915

Assistive devices, including canes or crutches, are used in partial weight-bearing (PWB) to offload weight from limbs weakened by disease or injury, promote recovery, and prevent reinjury. While weight must be offloaded accurately to target loads prescribed by healthcare providers for maximum benefit, current training methods result in poor adherence. It is, however, currently unknown how best to provide feedback during training so that users can build an accurate internal model for PWB. In this work, we investigate seven feedback schemes using an instrumented cane, which vary the modality, timing, and the level of detail provided. We find that auditory schemes and a retrospective visual scheme outperform current clinical practices for PWB training. These findings provide results that can be applied directly to improve current clinical practices and provide valuable new insight into the design of feedback for training internal models in force-based motor control tasks. Clinically, this work presents a simple modification to clinical PWB training practices that can improve compliance by up to 75%, positively influencing rehabilitation outcomes and reducing the risk of complications.

关键词： Training Visualization Bandwidth Haptic interfaces Loading Instruments Task analysis

3D-Printed electrochemical sensor-integrated transwell systems

学校读者我要写书评

暂无评论

Microsystems & Nanoengineering 2020年第1期6卷 357-368页

作者： Pradeep Ramiah Rajasekaran Ashley Augustiny Chapin David N.Quan Jens Herberholz William E.Bentley Reza Ghodssi Institute for Systems Research University of MarylandCollege ParkMDUSA Fischell Department of Bioengineering University of MarylandCollege ParkMDUSA Department of Psychology and Neuroscience and Cognitive Science Program University of MarylandCollege ParkMDUSA Institute for Bioscience and Biotechnology Research University of MarylandCollege ParkMDUSA Robert E.Fischell Institute for Biomedical Devices University of MarylandCollege ParkMDUSA Department of Electrical and Computer Engineering University of MarylandCollege ParkMDUSA

This work presents a 3D-printed,modular,electrochemical sensor-integrated transwell system for monitoring cellular and molecular events in situ without sample extraction or microfluidics-assisted downstream *** additive manufacturing techniques such as 3D printing,shadow masking,and molding are used to fabricate this modular system,which is autoclavable,biocompatible,and designed to operate following standard operating protocols(SOPs)of cellular *** to the platform is a flexible porous membrane,which is used as a cell culture substrate similarly to a commercial transwell *** electrochemical sensors fabricated on the membrane allow direct access to cells and their products.A pair of gold electrodes on the top side of the membrane measures impedance over the course of cell attachment and growth,characterized by an exponential decrease(~160%at 10Hz)due to an increase in the double layer capacitance from secreted extracellular matrix(ECM)*** voltammetry(CV)sensor electrodes,fabricated on the bottom side of the membrane,enable sensing of molecular release at the site of cell culture without the need for downstream ***-time detection of ferrocene dimethanol injection across the membrane showed a three order-of-magnitude higher signal at the membrane than in the bulk media after reaching *** modular sensor-integrated transwell system allows unprecedented direct,real-time,and noninvasive access to physical and biochemical information,which cannot be obtained in a conventional transwell system.

关键词： transwell electrochemical culture

Comparison of convolutional neural and fully convolutional networks for segmentation of 3D in vivo multiphoton microscopy images of brain vasculature

学校读者我要写书评

暂无评论

Comparison of convolutional neural and fully convolutional n...

Optics and the Brain, BRAIN 2019 - Part of Biophotonics Congress: Optics in the Life Sciences Congress 2019

作者： Haft-Javaherian, Mohammad Schaffer, Chris B. Nishimura, Nozomi Sabuncu, Mert R. Nancy E. and Peter C. Meinig School of Biomedical Engineering Cornell University IthacaNY United States School of Electrical and Computer Engineering Cornell University IthacaNY United States

We optimized DeepVess, a convolutional neural network, to segment multiphoton microscopy images of brain blood vessels that outperformed the state-of-the-art machine learning methods and a trained human annotator. ... 详细信息

ISBN: (纸本)9781943580545

关键词： Convolution

Implementing Arbitrary CRNs Using Strand Displacing Polymerase 1

学校读者我要写书评

暂无评论

25th International Conference on DNA Computing and Molecular Programming, DNA 2019

作者： Shah, Shalin Song, Tianqi Song, Xin Yang, Ming Reif, John Department of Electrical and Computer Engineering Duke University DurhamNC27701 United States Department of Computer Science Duke University DurhamNC27701 United States Department of Biomedical Engineering Duke University DurhamNC27701 United States

ISBN: (数字)9783030268077

ISBN: (纸本)9783030268060

The regulation of cellular and molecular processes typically involves complex biochemical networks. Synthetic nucleic acid reaction networks (both enzyme-based and enzyme-free) can be systematically designed to approximate sophisticated biochemical processes. However, most of the prior experimental protocols for reaction networks relied on either strand-displacement hybridization or restriction and exonuclease enzymatic reactions. These resulting synthetic systems usually suffer from either slow rates or leaky reactions. In this work, we propose an alternative architecture to implement arbitrary reaction networks, that is based entirely on strand-displacing polymerase reactions with non-overlapping I/O sequences. We first design a simple protocol that approximates arbitrary unimolecular and bimolecular reactions using polymerase strand displacement reactions. Then we use these fundamental reaction systems as modules to show three large-scale applications of our architecture, including an autocatalytic amplifier, a molecular-scale consensus protocol, and a dynamic oscillatory system. © 2019, Springer Nature Switzerland AG.

关键词： Enzymes

On the Design of High Switching Frequency DC-DC Buck Converter Power Stages for Automotive Post-Regulated Applications

学校读者我要写书评

暂无评论

On the Design of High Switching Frequency DC-DC Buck Convert...

IEEE International Symposium on Circuits and Systems (ISCAS)

作者： Filippo Boera Bernd Pflaum Giuseppe Torti Franco Maloberti Edoardo Bonizzoni Dept. of Electrical Computer and Biomedical Engineering University of Pavia Pavia Italy Infineon Technologies AG Neubiberg Germany Infineon Technologies Italy Pavia Italy

ISBN: (数字)9781728133201

ISBN: (纸本)9781728133218

This paper describes the design and the performance comparison of four different configurations of power stages of switching DC-DC buck converters with high switching frequency (f = 100 MHz), studied for automotive applications in the post-regulated domain. Different transistors are used for both power stage and pre-driver chain, and the solutions are compared in terms of efficiency and maximum input voltage. A rough estimation of the area consumption of each of the four configuration is also provided. The circuits have been optimized to have maximum efficiency with V in = 3.6 V, V out = 1.8 V and I load = 1 A, which are typical values in automotive post-regulated applications.

关键词： Switching frequency MOSFET Voltage control Switches Inductors Hybrid power systems