• Age Estimation from B-mode Echocardiography with 3D Convolutional Neural Networks 

      Fiorito, Adrian Meidell (Master thesis, 2019)
      Ekkokardiografi er en ikke-invasiv og sikker metode som bruker ultralyd for avbildning av hjertet. Som på mange andre felt utfører metoder for dyp læring, spesifikt \textit{Convolutional neural networks} (CNNs), oppgaver ...
    • Annotation Web - An open-source web-based annotation tool for ultrasound images 

      Smistad, Erik; Østvik, Andreas; Løvstakken, Lasse (Peer reviewed; Journal article, 2021)
      The use of deep learning and other machine learning techniques requires large amounts of annotated image data. There exist several tools to annotate images, however to our knowledge there are no tools made specifically for ...
    • Artificial Intelligence for Automatic Measurement of Left Ventricular Strain in Echocardiography 

      Salte, Ivar M.; Østvik, Andreas; Smistad, Erik; Melichova, Daniela; Nguyen, Thuy Mi; Karlsen, Sigve; Brunvand, Harald; Haugaa, Kristina H.; Edvardsen, Thor; Løvstakken, Lasse; Grenne, Bjørnar (Journal article; Peer reviewed, 2021)
      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 ...
    • Automatic analysis in echocardiography using machine learning 

      Østvik, Andreas (Doctoral theses at NTNU, 2021:230, Doctoral thesis, 2021)
      Echocardiography is the cornerstone of modern cardiac imaging due to its availability, low cost and real-time functionality. The modality has enabled sophisticated non-invasive evaluation of the hearts morphophysiology, ...
    • Automatic Myocardial Strain Imaging in Echocardiography Using Deep Learning 

      Østvik, Andreas; Smistad, Erik; Espeland, Torvald; Berg, Erik Andreas Rye; Løvstakken, Lasse (Journal article; Peer reviewed, 2018)
      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 ...
    • Can a Dinosaur Think? Implementation of Artificial Intelligence in Extracorporeal Shock Wave Lithotripsy 

      Muller, Sebastien; Abildsnes, Håkon; Østvik, Andreas; Kragset, Oda; Gangås, Inger Sofie Hovd; Birke, Harriet; Langø, Thomas; Arum, Carl-Jørgen (Peer reviewed; Journal article, 2021)
      Background: Extracorporeal shock wave lithotripsy (ESWL) of kidney stones is losing ground to more expensive and invasive endoscopic treatments. Objective: This proof-of-concept project was initiated to develop artificial ...
    • Deep Learning based Classification of Cardiac Events in Echocardiography 

      Langerud, Maren Andrea (Master thesis, 2022)
      Abstract will be available on 2023-01-29
    • Fully automatic real-time ejection fraction and MAPSE measurements in 2D echocardiography using deep neural networks 

      Smistad, Erik; Østvik, Andreas; Salte, Ivar Mjåland; Leclerc, Sarah; Bernard, Olivier; Løvstakken, Lasse (Journal article; Peer reviewed, 2018)
      Cardiac ultrasound measurements such as left ventricular volume, ejection fraction (EF) and mitral annular plane systolic excursion (MAPSE) are time consuming and highly observer dependent. In this work, we investigate if ...
    • High Performance Neural Network Inference, Streaming, and Visualization of Medical Images Using FAST 

      Smistad, Erik; Østvik, Andreas; Pedersen, Andrè (Journal article; Peer reviewed, 2019)
      Deep convolutional neural networks have quickly become the standard for medical image analysis. Although there are many frameworks focusing on training neural networks, there are few that focus on high performance inference ...
    • Myocardial Function Imaging in Echocardiography Using Deep Learning 

      Østvik, Andreas; Salte, Ivar Mjåland; Smistad, Erik; Nguyen, Thuy Mi; Melichova, Daniela; Brunvand, Harald; Haugaa, Kristina; Edvardsen, Thor; Grenne, Bjørnar; Løvstakken, Lasse (Journal article; Peer reviewed, 2021)
      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 ...
    • Real-Time Automatic Ejection Fraction and Foreshortening Detection Using Deep Learning 

      Smistad, Erik; Salte, Ivar Mjåland; Østvik, Andreas; Melichova, Daniela; Nguyen, Thuy Mi; Haugaa, Kristina; Brunvand, Harald; Edvardsen, Thor; Leclerc, Sarah; Bernard, Olivier; Grenne, Bjørnar; Løvstakken, Lasse (Peer reviewed; Journal article, 2020)
      Volume and ejection fraction (EF) measurements of the left ventricle (LV) in 2-D echocardiography are associated with a high uncertainty not only due to interobserver variability of the manual measurement, but also due to ...
    • Real-time Standard View Classification in Transthoracic Echocardiography using Convolutional Neural Networks 

      Østvik, Andreas; Smistad, Erik; Aase, Svein Arne; Haugen, Bjørn Olav; Løvstakken, Lasse (Journal article; Peer reviewed, 2018)
      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, ...
    • Real-time temporal adaptation of dynamic movement primitives for moving targets 

      Østvik, Andreas; Grøtli, Esten Ingar; Vagia, Marialena; Gravdahl, Jan Tommy (Chapter, 2021)
    • Reinforcement learning for robotic soft-body interaction 

      Jakobsen, Herman Kolstad (Master thesis, 2021)
      Innen klinisk medisin ansees det som utfordrende å benytte autonome robotsystemer. Håndtering av bevegelige objekter og myke materialer, samt variasjon mellom pasienter, har vist seg å være en hindring for robotassisterte ...
    • Robot Control in Image-Guided Intervention 

      Østvik, Andreas (Master thesis, 2016)
      Introducing autonomous robot systems in clinical medicine is deemed extremely challenging due to the complex scene involved and variations between patients. The majority of commercialized systems are controlled directly ...
    • Ultrasound speckle reduction using generative adversial networks 

      Dietrichson, Fabian Sødal; Smistad, Erik; Østvik, Andreas; Løvstakken, Lasse (Journal article; Peer reviewed, 2018)
      Generative adversial networks (GANs) have shown its ability to create realistic and accurate image-to-image transformation. The goal of this work was to investigate whether deep convolutional GANs can learn to perform ...