• Home
  • SINTEF
  • Department of Medical technology
  • Erik Smistad
Erik Smistad

Erik Smistad
SINTEF | Stiftelsen for industriell og teknisk forskning · Department of Medical technology

PhD

About

66
Publications
23,270
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
1,185
Citations
Introduction
Research interests include medical imaging, deep learning, ultrasound, image segmentation and parallel/GPU computing. See my webpage www.eriksmistad.no for more details. For code related to my research, see my GitHub page www.github.com/smistad/
Additional affiliations
February 2016 - present
Norwegian University of Science and Technology
Position
  • PostDoc Position
Description
  • Ultrasound image segmentation
May 2013 - present
SINTEF
Position
  • Researcher
August 2010 - April 2015
Norwegian University of Science and Technology
Position
  • PhD Student
Description
  • Thesis title: Medical Image Segmentation for Improved Surgical Navigation

Publications

Publications (66)
Article
Funding Acknowledgements Type of funding sources: Public grant(s) – EU funding. Main funding source(s): PIC from European Union"s Horizon 2020 Marie Skłodowska-Curie Actions ITN Background The wall thickness of the left ventricle (LV) is an important parameter in the diagnosis of hypertension and more specifically in hypertrophic cardiomyopathy. A...
Article
Funding Acknowledgements Type of funding sources: Public Institution(s). Main funding source(s): Norwegian University of Science and Technology, St. Olavs University Hospital, Central-Norway Health Authority Background Left ventricular (LV) foreshortening is common in echocardiography and may impair reproducibility and estimation of LV function. Fe...
Article
Funding Acknowledgements Type of funding sources: Public grant(s) – National budget only. Main funding source(s): Norwegian University of Science and Technology, St. Olavs University Hospital, Central-Norway Health Authority OnBehalf Department of Circulation and Medical imaging, Norwegian University of Science and Technology, Trondheim, Norway Ba...
Article
Full-text available
Application of deep learning on histopathological whole slide images (WSIs) holds promise of improving diagnostic efficiency and reproducibility but is largely dependent on the ability to write computer code or purchase commercial solutions. We present a code-free pipeline utilizing free-to-use, open-source software (QuPath, DeepMIB, and FastPathol...
Data
The annotated colon biopsies is made openly available for any purpose on DataverseNO (https://doi.org/10.18710/TLA01U). The shared README.txt file contains description of the dataset and its content. The actual data and info about its origin can be found through the URL.
Data
This document contains the table with adjusted p-values from the pairwise Tukey's range tests referenced in section 3.3 (see Table S1). Red colour indicate no significance (p-value ≥ 0.05), green colour indicate slight significance (p-value ∈ [0.001, 0.05], and light green colour indicate strong significance (p-value < 0.001). Pairwise comparisons...
Preprint
Full-text available
Histopathological cancer diagnostics has become more complex, and the increasing number of biopsies is a challenge for most pathology laboratories. Thus, development of automatic methods for evaluation of histopathological cancer sections would be of value. In this study, we used 624 whole slide images (WSIs) of breast cancer from a Norwegian cohor...
Preprint
Full-text available
Application of deep learning on histopathological whole slide images (WSIs) holds promise of improving diagnostic efficiency and reproducibility but is largely dependent on the ability to write computer code or purchase commercial solutions. We present a code-free pipeline utilizing free-to-use, open-source software (QuPath, DeepMIB, and FastPathol...
Conference Paper
Most work on left ventricle (LV) ultrasound image segmentation using deep learning has focused on single-frame segmentation of end-diastole (ED) and end-systole (ES) frames. Using these neural network models on the entire cardiac cycle often results in segmentation flickering and sudden large segmentation errors. Neural networks that perform some f...
Article
Full-text available
Objectives This study sought to examine if fully automated measurements of global longitudinal strain (GLS) using a novel motion estimation technology based on deep learning and artificial intelligence (AI) are feasible and comparable with a conventional speckle-tracking application. Background GLS is an important parameter when evaluating left ve...
Article
Full-text available
Deep convolutional neural networks (CNNs) are the current state-of-the-art for digital analysis of histopathological images. The large size of whole-slide microscopy images (WSIs) requires advanced memory handling to read, display and process these images. There are several open-source platforms for working with WSIs, but few support deployment of...
Article
Full-text available
Deformation imaging in echocardiography has been shown to have better diagnostic and prognostic value than conventional anatomical measures such as ejection fraction. However, despite clinical availability and demonstrated efficacy, everyday clinical use remains limited at many hospitals. The reasons are complex, but practical robustness has been q...
Preprint
Full-text available
Deep convolutional neural networks (CNNs) are the current state-of-the-art for digital analysis of histopathological images. The large size of whole-slide microscopy images (WSIs) requires advanced memory handling to read, display and process these images. There are several open-source platforms for working with WSIs, but few support deployment of...
Article
Segmentation of cardiac structures is one of the fundamental steps to estimate volumetric indices of the heart. This step is still performed semi-automatically in clinical routine, and is thus prone to inter and intra observer variability. Recent studies have shown that deep learning has the potential to perform fully automatic segmentation. Howeve...
Preprint
Full-text available
Segmentation of cardiac structures is one of the fundamental steps to estimate volumetric indices of the heart. This step is still performed semi-automatically in clinical routine, and is thus prone to inter- and intra-observer variability. Recent studies have shown that deep learning has the potential to perform fully automatic segmentation. Howev...
Presentation
Funding Acknowledgements The Norwegian Health Association, South-Eastern Norway regional health Authority and the national program for clinical therapy research (KLINBEFORSK). Background Global longitudinal strain (GLS) by echocardiography has incremental prognostic value in patients with acute myocardial infarction and heart failure compared to l...
Conference Paper
It has been shown that deep neural networks can accuratly segment the left ventricle (LV), myocardium and left atrium in apical two and four chamber (A2C and A4C) views. While segmentation of apical long-axis (ALAX) views is quite similar to A2C and A4C, there is one major difference; the left ventricular outflow tract (LVOT) which restricts the my...
Preprint
Full-text available
Delineation of the cardiac structures from 2D echocardiographic images is a common clinical task to establish a diagnosis. Over the past decades, the automation of this task has been the subject of intense research. In this paper, we evaluate how far the state-of-the-art encoder-decoder deep convolutional neural network methods can go at assessing...
Preprint
Full-text available
We recently published a deep learning study on the potential of encoder-decoder networks for the segmentation of the 2D CAMUS ultrasound dataset. We propose in this abstract an extension of the evaluation criteria to anatomical assessment, as traditional geometric and clinical metrics in cardiac segmentation do not take into account the anatomical...
Article
Delineation of the cardiac structures from 2D echocardiographic images is a common clinical task to establish a diagnosis. Over the past decades, the automation of this task has been the subject of intense research. In this paper, we evaluate how far the state-of-the-art encoder-decoder deep convolutional neural network methods can go at assessing...
Article
Transthoracic echocardiography examinations are usually performed according to a protocol comprising different probe postures providing standard views of the heart. These are used as a basis when assessing cardiac function, and it is essential that the morphophysiological representations are correct. Clinical analysis is often initialized with the...
Chapter
Recent studies in the field of deep learning suggest that motion estimation can be treated as a learnable problem. In this paper we propose a pipeline for functional imaging in echocardiography consisting of four central components, (i) classification of cardiac view, (ii) semantic partitioning of the left ventricle (LV) myocardium, (iii) regional...
Conference Paper
Full-text available
Deep convolutional neural networks have achieved great results on image classification problems. In this paper, a new method using a deep convolutional neural network for detecting blood vessels in B-mode ultrasound images is presented. Automatic blood vessel detection may be useful in medical applications such as deep venous thrombosis detection,...
Article
Full-text available
Ultrasound-guided regional anesthesia can be challenging, especially for inexperienced physicians. The goal of the proposed methods is to create a system that can assist a user in performing ultrasound-guided femoral nerve blocks. The system indicates in which direction the user should move the ultrasound probe to investigate the region of interest...
Conference Paper
The measurement of blood flow velocities using either conventional color flow imaging (CFI), or more recent vector-Doppler or blood speckle tracking (BST) approaches are all hampered by regions of signal dropouts due to clutter filtering, as well as potentially high variance depending on the SNR in a given scenario. The aim of this work is to descr...
Article
Introduction: Our motivation is increased bronchoscopic diagnostic yield and optimized preparation, for navigated bronchoscopy. In navigated bronchoscopy, virtual 3D airway visualization is often used to guide a bronchoscopic tool to peripheral lesions, synchronized with the real time video bronchoscopy. Visualization during navigated bronchoscopy...
Article
Full-text available
Real-time 3D Echocardiography (RT3DE) has been proven to be an accurate tool for left ventricular (LV) volume assessment. However, identification of the LV endocardium remains a challenging task, mainly because of the low tissue/blood contrast of the images combined with typical artifacts. Several semi and fully automatic algorithms have been propo...
Article
Full-text available
The goal is to create an assistant for ultrasoundguided femoral nerve block. By segmenting and visualizing the important structures such as the femoral artery, we hope to improve the success of these procedures. This article is the first step towards this goal and presents novel real-time methods for identifying and reconstructing the femoral arter...
Conference Paper
Abstract Purpose: Our motivation is reduced preparation time for planning and navigation in bronchoscopy diagnostics, decreased procedure time, and an increased diagnostic yield in navigated bronchoscopy. Me thod: Visualization during navigated bronchoscopy, the segmentation time and methods differs. We compared three different approaches to obtain...
Article
Full-text available
Computer systems are becoming increasingly heterogeneous in the sense that they consist of different processors, such as multi-core CPUs and graphic processing units. As the amount of medical image data increases, it is crucial to exploit the computational power of these processors. However, this is currently difficult due to several factors, such...
Article
Full-text available
Gradient vector flow (GVF) is a feature-preserving spatial diffusion of image gradients. It was introduced to overcome the limited capture range in traditional active contour segmentation. However, the original iterative solver for GVF, using Euler’s method, converges very slowly. Thus, many iterations are needed to achieve the desired capture rang...
Article
A method for real-time automatic tracking of the left ventricle (LV) in 3D ultrasound is presented. A mesh model of the LV is deformed using mean value coordinates enabling large variations. Kalman filtering and edge detection is used to track the mesh in each frame. The method is evaluated using the framework of the Challenge on Endocardial Three-...
Conference Paper
Full-text available
Tube detection filters (TDFs) are useful for segmentation and centerline extraction of tubular structures such as blood vessels and airways in medical images. Most TDFs assume that the cross-sectional profile of the tubular structure is circular. This assumption is not always correct, for instance in the case of abdominal aortic aneurysms (AAAs). A...
Conference Paper
Full-text available
A method for real-time automatic tracking of the left ven-tricle (LV) in 3D ultrasound is presented. A mesh model of the LV is deformed using mean value coordinates enabling large variations. Kalman filtering and edge detection is used to track the mesh in each frame. The method is evaluated using the framework of the Challenge on Endocardial Three...
Article
The VESSEL12 (VESsel SEgmentation in the Lung) challenge objectively compares the performance of different algorithms to identify vessels in thoracic computed tomography (CT) scans. Vessel segmentation is fundamental in computer aided processing of data generated by 3D imaging modalities. As manual vessel segmentation is prohibitively time consumin...
Article
Full-text available
To create a fast and generic method with sufficient quality for extracting tubular structures such as blood vessels and airways from different modalities (CT, MR and US) and organs (brain, lungs and liver) by utilizing the computational power of graphic processing units (GPUs). A cropping algorithm is used to remove unnecessary data from the datase...
Article
Full-text available
The Gradient Vector Flow (GVF) is a feature-preserving spatial diffusion of gradients. It is used extensively in several image segmentation and skeletonization algorithms. Calculating the GVF is slow as many iterations are needed to reach convergence. However, each pixel or voxel can be processed in parallel for each iteration. This makes GVF ideal...
Conference Paper
Full-text available
Bronchoscopy is an important minimal-invasive procedure for both diagnosis and therapy of several lung disorders, including lung cancer. However, narrow airways and complex branching structure increases the difficulty of navigating to the target site inside the lungs. It is possible to improve navigation by extracting a map of the airways from CT i...
Conference Paper
Full-text available
Marching Cubes (MC) is an algorithm that extracts surfaces from volumetric data. It is used extensively in visualization and analy-sis of medical data from modalities like CT and MR, often after a 3D segmentation of the interesting structures is performed. Traditional im-plementations of MC on modern CPUs are slow, using several seconds (even minut...

Network

Cited By

Projects

Project (1)
Project
FAST is an open-source cross-platform framework with the main goal of making it easier to do highly efficient processing and visualization of medical images on heterogeneous systems with multi-core CPUs and GPUs.