Piotr Jarosik
YOU?
Author Swipe
View article: Structural Component Identification and Damage Localization of Civil Infrastructure Using Semantic Segmentation
Structural Component Identification and Damage Localization of Civil Infrastructure Using Semantic Segmentation Open
Visual inspection of civil infrastructure for structural health assessment, as performed by structural engineers, is expensive and time-consuming. Therefore, automating this process is highly attractive, which has received significant atte…
View article: Implicit Neural Representations for Speed-of-Sound Estimation in Ultrasound
Implicit Neural Representations for Speed-of-Sound Estimation in Ultrasound Open
Accurate estimation of the speed-of-sound (SoS) is important for ultrasound (US) image reconstruction techniques and tissue characterization. Various approaches have been proposed to calculate SoS, ranging from tomography-inspired algorith…
View article: A High-Speed Ultrasound Full-Matrix Capture Acquisition System for Robotic Weld Inspection
A High-Speed Ultrasound Full-Matrix Capture Acquisition System for Robotic Weld Inspection Open
Phased-Array Ultrasonic Technique is traditionally used for the non-destructive inspection of welds and supported by industrial-grade inspection equipment. FullMatrix Capture (FMC) with Total Focusing Method (TFM) provide new capabilities …
View article: Parameter estimation of the homodyned K distribution based on neural networks and trainable fractional-order moments
Parameter estimation of the homodyned K distribution based on neural networks and trainable fractional-order moments Open
Homodyned K (HK) distribution has been widely used to describe the scattering phenomena arising in various research fields, such as ultrasound imaging or optics. In this work, we propose a machine learning based approach to the estimation …
View article: Estimating the ultrasound attenuation coefficient using convolutional neural networks -- a feasibility study
Estimating the ultrasound attenuation coefficient using convolutional neural networks -- a feasibility study Open
Attenuation coefficient (AC) is a fundamental measure of tissue acoustical properties, which can be used in medical diagnostics. In this work, we investigate the feasibility of using convolutional neural networks (CNNs) to directly estimat…
View article: Breast mass segmentation in ultrasound with selective kernel U-Net convolutional neural network
Breast mass segmentation in ultrasound with selective kernel U-Net convolutional neural network Open
View article: Breast mass segmentation based on ultrasonic entropy maps and attention\n gated U-Net
Breast mass segmentation based on ultrasonic entropy maps and attention\n gated U-Net Open
We propose a novel deep learning based approach to breast mass segmentation\nin ultrasound (US) imaging. In comparison to commonly applied segmentation\nmethods, which use US images, our approach is based on quantitative entropy\nparametri…
View article: Breast mass segmentation based on ultrasonic entropy maps and attention gated U-Net
Breast mass segmentation based on ultrasonic entropy maps and attention gated U-Net Open
We propose a novel deep learning based approach to breast mass segmentation in ultrasound (US) imaging. In comparison to commonly applied segmentation methods, which use US images, our approach is based on quantitative entropy parametric m…
View article: WaveFlow - Towards Integration of Ultrasound Processing with Deep Learning
WaveFlow - Towards Integration of Ultrasound Processing with Deep Learning Open
The ultimate goal of this work is a real-time processing framework for ultrasound image reconstruction augmented with machine learning. To attain this, we have implemented WaveFlow - a set of ultrasound data acquisition and processing tool…
View article: WaveFlow - Towards Integration of Ultrasound Processing with Deep\n Learning
WaveFlow - Towards Integration of Ultrasound Processing with Deep\n Learning Open
The ultimate goal of this work is a real-time processing framework for\nultrasound image reconstruction augmented with machine learning. To attain\nthis, we have implemented WaveFlow - a set of ultrasound data acquisition and\nprocessing t…
View article: Learning to Run challenge solutions: Adapting reinforcement learning methods for neuromusculoskeletal environments
Learning to Run challenge solutions: Adapting reinforcement learning methods for neuromusculoskeletal environments Open
In the NIPS 2017 Learning to Run challenge, participants were tasked with building a controller for a musculoskeletal model to make it run as fast as possible through an obstacle course. Top participants were invited to describe their algo…