22 papers · ranked by Valyu relevance
Authors not listed
Monolayer graphene is a suitable active material for several electronics and sensor applications, for which large-area individual sheets are necessary on insulating substrates. Chemical vapor deposition (CVD) enables the synthesis of large-area graphene of high quality on metallic supports. However, graphene grown in…
Dina Abdelhafiz, Jinbo Bi, Reda Ammar, Clifford Yang + 1 more
Automatic segmentation and localization of lesions in mammogram (MG) images are challenging even with employing advanced methods such as deep learning (DL) methods. We developed a new model based on the architecture of the semantic segmentation U-Net model to precisely segment mass lesions in MG images. The proposed…
Li-Ming Hsu, Shuai Wang, Lindsay Walton, Tzu-Wen Winnie Wang + 2 more
Brain extraction is a critical pre-processing step in brain magnetic resonance imaging (MRI) analytical pipelines. In rodents, this is often achieved by manually editing brain masks slice-by-slice, a time-consuming task where workloads increase with higher spatial resolution datasets. We recently demonstrated…
Junfeng Chen, Jonathan Viquerat, Elie Hachem
Machine learning is a popular tool that is being applied to many domains, from computer vision to natural language processing. It is not long ago that its use was extended to physics, but its capabilities remain to be accurately contoured. In this paper, we are interested in the prediction of 2D velocity and pressure…
Pius Kwao Gadosey, Yujian Li, Enock Adjei Agyekum, Ting Zhang + 3 more
'Zhaoying Liu' 'Peter T. Yamak' 'Firdaous Essaf'] During image segmentation tasks in computer vision, achieving high accuracy performance while requiring fewer computations and faster inference is a big challenge. This is especially important in medical imaging tasks but one metric is usually compromised for the other.…
Yanjun Guo, Xingguang Duan, Chengyi Wang, Huiqin Guo + 1 more
'Thippa Reddy Gadekallu'] This paper establishes a fully automatic real-time image segmentation and recognition system for breast ultrasound intervention robots. It adopts the basic architecture of a U-shaped convolutional network (U-Net), analyses the actual application scenarios of semantic segmentation of breast…
Mario Lino, Chris D. Cantwell, Stathi Fotiadis, Eduardo Pignatelli + 1 more
'Anil A. Bharath'] We investigate the performance of fully convolutional networks to simulate the motion and interaction of surface waves in open and closed complex geometries. We focus on a U-Net architecture and analyse how well it generalises to geometric configurations not seen during training. We demonstrate that…
Yunhee Jeong, Muhammad Febrian Rachmadi, Maria del C. Valdés-Hernández, Taku Komura
White matter hyperintensities(WMH) appear as regions of abnormally high signal intensity on T2-weighted magnetic resonance image(MRI) sequences. In particular, WMH have been noteworthy in age-related neuroscience for being a crucial biomarker for Alzheimer’ s disease and brain aging processes. However, the automatic…
Jathurshan Pradeepkumar, Mithunjha Anandakumar, Vinith Kugathasan, Andrew Seeber + 1 more
A key challenge in optical microscopy is to image fast at high-resolution. To address this problem, we propose “Physics Augmented U-Net”, which combines deep learning and structured illumination microscopy (SIM). In SIM, the structured illumination aliases out-of-band high-frequencies to the passband of the microscope…
Dilara Tank, Bianca G. S. Schor, Lisa M. Trommelen, Judith A. F. Huirne + 3 more
Models trained on the full dataset, only still images, and only video screenshots have the best performance with an image resolution of 256x256 pixels. The model trained on the 3D screenshots performs best with an image resolution of 128x128 pixels. This might imply that the still images and video screenshots benefit…
Lishen Qiu, Wenqiang Cai, Jie Yu, Jun Zhong + 4 more
Electrocardiogram (ECG) is an effective and non-invasive indicator for the detection and prevention of arrhythmia. ECG signals are susceptible to noise contamination, which can lead to errors in ECG interpretation. Therefore, ECG pretreatment is important for accurate analysis. In this paper, a method of noise…
Pranava Seth, Deepak Mishra, V. R. Krishna Iyer
This article describes the development of a novel U-Net-enhanced Wavelet Neural Operator (U-WNO),which combines wavelet decomposition, operator learning, and an encoder-decoder mechanism. This approach harnesses the superiority of the wavelets in time frequency localization of the functions, and the combine…
Xie Hui, Praveenbalaji Rajendran, Tong Ling, Xianjin Dai + 2 more
'Manojit Pramanik'] Accurate needle guidance is crucial for safe and effective clinical diagnosis and treatment procedures. Conventional ultrasound (US)-guided needle insertion often encounters challenges in consistency and precisely visualizing the needle, necessitating the development of reliable methods to track the…
Zuopeng Zhao, Chen Ye, Yanjun Hu, Ceng Li + 1 more
With the development of computed tomography (CT), the contrast-enhanced CT scan is widely used in the diagnosis of thyroid nodules. However, due to the artifacts and high complexity of thyroid CT images, traditional machine learning has difficulty in detecting thyroid nodules in contrast-enhanced CT. A fully automated…
Suman Gautam, Alexander F. I. Osman, Dylan Richeson, Somayeh Gholami + 3 more
UNET consists of three modules: an encoder for downsampling, a skip connection, and a decoder for upsampling. The encoder part consists of two consecutive 3 × 3 × 3 convolution layers, each followed sequentially by a batch normalization layer, a rectified linear unit (ReLu) activation function, and a 2 × 2 × 2 max…
Francesco Regazzoni, Stefano Pagani, Alfio Quarteroni
We introduce Universal Solution Manifold Network (USM-Net), a novel surrogate model, based on Artificial Neural Networks (ANNs), which applies to differential problems whose solution depends on physical and geometrical parameters. Our method employs a mesh-less architecture, thus overcoming the limitations associated…
Torsten Hoefler, Karen Schramm, Spada, Eric + 14 more
TORSTEN HOEFLER, ETH Zurich, Switzerland & Microsoft, USA KAREN SCHRAMM, Broadcom, USA ERIC SPADA, Broadcom, USA KEITH UNDERWOOD, Hewlett Packard Enterprise, USA CEDELL ALEXANDER, Broadcom, USA BOB ALVERSON, Hewlett Packard Enterprise, USA PAUL BOTTORFF, Hewlett Packard Enterprise, USA ADRIAN CAULFIELD, OpenAI, USA…
Authors not listed
Because topology plays a key role in many chemical and physical properties of materials, identification of topology from crystalline structures is a common and important task in materials science. We present here a new web application, CrystalNets, whose user-friendly interface allows scientists to identify and…
Salvador Dura-Bernal, Benjamin A Suter, Padraig Gleeson, Matteo Cantarelli + 12 more
'Matteo Cantarelli' 'Adrian Quintana' 'Facundo Rodriguez' 'David J Kedziora' 'George L Chadderdon' 'Cliff C Kerr' 'Samuel A Neymotin' 'Robert A McDougal' 'Michael Hines' 'Gordon MG Shepherd' 'William W Lytton' 'Upinder Singh Bhalla' 'Ronald L Calabrese'] Biophysical modeling of neuronal networks helps to integrate and…
Authors not listed
Real-world datasets in chemical engineering and bioengineering processes--such as those from catalytic reactors, multiphase flows, polymerization reactors, bioreactors, and clinical trials--can often be unlabelled or disorganized, rendering the training of existing supervised learning models ineffective at learning the…
Abdulkadir Çelik, Nasir Saeed, Basem Shihada, Tareq Y. Al-Naffouri + 1 more
'Mohamed‐Slim Alouini'] Abstract—In this paper, we envision a hybrid opto-acoustic network design for the internet of underwater things (IoUT). Software-defined underwater networking (SDUN) is presented as an enabler of hybridizing benefits of optic and acoustic systems and adapting IoUT nodes to the challenging and…
Sergio Pablo-García, Raúl Pérez-Soto, Albert Sabadell-Rendón, Diego Garay-Ruiz + 2 more
In the study of chemical reactions, visualizing reaction networks is pivotal for identifying crucial compounds and reactions. Traditional methods, such as network schematics and reaction path linear plots, often struggle to effectively represent complex reaction networks due to their size and intricate connectivity.…