Search Results for author: Kjersti Engan

Found 12 papers, 5 papers with code

Self-supervised learning of a tailored Convolutional Auto Encoder for histopathological prostate grading

no code implementations21 Mar 2023 Zahra Tabatabaei, Adrian colomer, Kjersti Engan, Javier Oliver, Valery Naranjo

In particular, a tailored Convolutional Auto Encoder (CAE) is trained to reconstruct 128x128x3 patches of prostate cancer Whole Slide Images (WSIs) as a pretext task.

Self-Supervised Learning whole slide images

Activity Recognition From Newborn Resuscitation Videos

no code implementations14 Mar 2023 Øyvind Meinich-Bache, Simon Lennart Austnes, Kjersti Engan, Ivar Austvoll, Trygve Eftestøl, Helge Myklebust, Simeon Kusulla, Hussein Kidanto, Hege Ersdal

An important step is to generate timelines of relevant resuscitation activities, including ventilation, stimulation, suction, etc., during the resuscitation episodes.

Activity Recognition object-detection +1

Object Detection During Newborn Resuscitation Activities

no code implementations14 Mar 2023 Øyvind Meinich-Bache, Kjersti Engan, Ivar Austvoll, Trygve Eftestøl, Helge Myklebust, Ladislaus Blacy Yarrot, Hussein Kidanto, Hege Ersdal

Significance: This is the first step in a thorough analysis of newborn resuscitation episodes, which could provide important insight about the importance and effect of different newborn resuscitation activities

object-detection Object Detection

Active Learning Based Domain Adaptation for Tissue Segmentation of Histopathological Images

no code implementations9 Mar 2023 Saul Fuster, Farbod Khoraminia, Trygve Eftestøl, Tahlita C. M. Zuiverloon, Kjersti Engan

Accurate segmentation of tissue in histopathological images can be very beneficial for defining regions of interest (ROI) for streamline of diagnostic and prognostic tasks.

Active Learning Domain Adaptation

Self-Supervised Few-Shot Learning for Ischemic Stroke Lesion Segmentation

1 code implementation2 Mar 2023 Luca Tomasetti, Stine Hansen, Mahdieh Khanmohammadi, Kjersti Engan, Liv Jorunn Høllesli, Kathinka Dæhli Kurz, Michael Kampffmeyer

Precise ischemic lesion segmentation plays an essential role in improving diagnosis and treatment planning for ischemic stroke, one of the prevalent diseases with the highest mortality rate.

Few-Shot Learning Ischemic Stroke Lesion Segmentation +1

Multi-input segmentation of damaged brain in acute ischemic stroke patients using slow fusion with skip connection

1 code implementation18 Mar 2022 Luca Tomasetti, Mahdieh Khanmohammadi, Kjersti Engan, Liv Jorunn Høllesli, Kathinka Dæhli Kurz

We propose an automatic method based on a neural network using a set of parametric maps to segment the two ischemic regions (core and penumbra) in patients affected by acute ischemic stroke.

Nested Multiple Instance Learning with Attention Mechanisms

1 code implementation1 Nov 2021 Saul Fuster, Trygve Eftestøl, Kjersti Engan

Strongly supervised learning requires detailed knowledge of truth labels at instance levels, and in many machine learning applications this is a major drawback.

Multiple Instance Learning Time Series Analysis +1

CNN Based Segmentation of Infarcted Regions in Acute Cerebral Stroke Patients From Computed Tomography Perfusion Imaging

1 code implementation7 Apr 2021 Luca Tomasetti, Kjersti Engan, Mahdieh Khanmohammadi, Kathinka Dæhli Kurz

However, there is no consensus in terms of which thresholds to use, or how to combine the information from the parametric maps, and the presented methods all have limitations in terms of both accuracy and reproducibility.

Cannot find the paper you are looking for? You can Submit a new open access paper.