Simon Lysdahlgaard
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Simon Lysdahlgaard has a total of 41 co-authors. Here are the top co-authors by number of shared publications:
- Martin Weber Kusk
Department of Radiology and Nuclear Medicine, University Hospital of Southern Denmark, Esbjerg, Denmark
9 shared publications - Janni Jensen
Department of Radiology, Odense University Hospital, Odense, Denmark
4 shared publications - Malene Roland Vils Pedersen
Department of Radiology, University Hospital of Southern Denmark, 7100 Vejle, Denmark
4 shared publications - Ronald Antulov
Department of Radiology, Clinical Hospital Center Rijeka, Rijeka, Croatia
4 shared publications - Søren Hess
Department of Clinical Research, University of Southern Denmark
4 shared publications - Oke Gerke
Department of Nuclear Medicine (O.G.), Odense University Hospital, Denmark
3 shared publications
Latest Publications
- 1 December 2026
- Published by Wolters Kluwer Health in Neurology Open Access
- Vol. 2 (4)
Time of Stroke Onset and the Efficacy of Remote Ischemic Conditioning
- 1 December 2026
- Published by Wolters Kluwer Health in Neurology Open Access
- Vol. 2 (4)
Time of Stroke Onset and the Efficacy of Remote Ischemic Conditioning
- Open Access
- 1 July 2026
- Published by Wolters Kluwer Health in Stroke: Vascular and Interventional Neurology
- Vol. 6 (4)
Remote Ischemic Conditioning on Infarct Growth in Patients With Acute Ischemic Stroke: Subgroup Analysis From the RESIST Trial
BACKGROUND: Remote ischemic conditioning (RIC) is a promising cerebroprotective strategy, but its effects on early infarct dynamics are unclear. We assessed whether RIC reduces acute-to-24-hour infarct growth on magnetic resonance imaging in this predefined RESIST substudy (Remote Ischemic Conditioning in Patients With Acute Stroke). METHODS: We included consecutive patients with acute ischemic stroke from a single RESIST center where acute and 24-hour magnetic resonance imaging were acquired. Infarcts were automatically segmented on diffusion-weighted images using a combined deep learning algorithm. For the primary analysis, brain infarct volume (mL) was analyzed using a linear mixed-effects model with group (RIC versus sham), scan time (baseline/24 hours), their interaction (group×scan), age, and prehospital stroke severity as predictors. Secondary analyses comprised stratified subgroup analyses by age, sex, smoking, diabetes, hypertension, arterial fibrillation, previous acute ischemic stroke, National Institutes of Health Stroke Scale scores, reperfusion treatment, and change from baseline. RESULTS: Of 384 screened patients with acute ischemic stroke, 346 were analyzed (RIC=162; sham=184) with similar baseline characteristics (age, 71 [interquartile range, 62–80] versus 73 [interquartile range, 64–78] years; female 34% versus 36%). Median infarct growth was similar (RIC, 0.45 [interquartile range, −0.54 to 2.86] versus sham, 0.40 mL [interquartile range, −0.50 to 4.74]). The mean infarct growth from acute to 24-hour magnetic resonance imaging was comparable between the RIC group (6.19 [range, −44.94 to 277.01] mL) and the sham group (5.80 [range, −66.18 to 182.13] mL). No significant differences in infarct growth were found between groups, and subgroup analyses likewise showed no significant differences across National Institutes of Health Stroke Scale score or reperfusion categories. CONCLUSIONS: In this RESIST substudy, combined prehospital and early in-hospital RIC was not associated with differences in early diffusion-weighted imaging–based infarct growth compared with sham.
- 1 July 2026
- Published by Wolters Kluwer Health in Stroke: Vascular and Interventional Neurology
- Vol. 6 (4)
Open AccessRemote Ischemic Conditioning on Infarct Growth in Patients With Acute Ischemic Stroke: Subgroup Analysis From the RESIST Trial
BACKGROUND: Remote ischemic conditioning (RIC) is a promising cerebroprotective strategy, but its effects on early infarct dynamics are unclear. We assessed whether RIC reduces acute-to-24-hour infarct growth on magnetic resonance imaging in this predefined RESIST substudy (Remote Ischemic Conditioning in Patients With Acute Stroke). METHODS: We included consecutive patients with acute ischemic stroke from a single RESIST center where acute and 24-hour magnetic resonance imaging were acquired. Infarcts were automatically segmented on diffusion-weighted images using a combined deep learning algorithm. For the primary analysis, brain infarct volume (mL) was analyzed using a linear mixed-effects model with group (RIC versus sham), scan time (baseline/24 hours), their interaction (group×scan), age, and prehospital stroke severity as predictors. Secondary analyses comprised stratified subgroup analyses by age, sex, smoking, diabetes, hypertension, arterial fibrillation, previous acute ischemic stroke, National Institutes of Health Stroke Scale scores, reperfusion treatment, and change from baseline. RESULTS: Of 384 screened patients with acute ischemic stroke, 346 were analyzed (RIC=162; sham=184) with similar baseline characteristics (age, 71 [interquartile range, 62–80] versus 73 [interquartile range, 64–78] years; female 34% versus 36%). Median infarct growth was similar (RIC, 0.45 [interquartile range, −0.54 to 2.86] versus sham, 0.40 mL [interquartile range, −0.50 to 4.74]). The mean infarct growth from acute to 24-hour magnetic resonance imaging was comparable between the RIC group (6.19 [range, −44.94 to 277.01] mL) and the sham group (5.80 [range, −66.18 to 182.13] mL). No significant differences in infarct growth were found between groups, and subgroup analyses likewise showed no significant differences across National Institutes of Health Stroke Scale score or reperfusion categories. CONCLUSIONS: In this RESIST substudy, combined prehospital and early in-hospital RIC was not associated with differences in early diffusion-weighted imaging–based infarct growth compared with sham.
- Open Access
- 4 June 2026
- Published by Elsevier in Radiography
- Vol. 32 (5) , 103459
Quality assessment of radiographs through AI-driven feedback: A randomized comparative study on radiographer response in lateral knee radiographs
- 4 June 2026
- Published by Elsevier in Radiography
- Vol. 32 (5) , 103459
Open AccessQuality assessment of radiographs through AI-driven feedback: A randomized comparative study on radiographer response in lateral knee radiographs
- Open Access
- 21 February 2026
- Published by Elsevier in Radiography
- Vol. 32 (3) , 103359
External validation of a pre-trained hybrid convolutional neural network in radiographers agreement of positioning in lateral knee radiographs
- 21 February 2026
- Published by Elsevier in Radiography
- Vol. 32 (3) , 103359
Open AccessExternal validation of a pre-trained hybrid convolutional neural network in radiographers agreement of positioning in lateral knee radiographs
- Open Access
- 16 January 2026
- Published by MDPI AG in Diagnostics
- Vol. 16 (2) , 282
Real-World Integration of an Automated Tool for Intracranial Hemorrhage Detection in an Unselected Cohort of Emergency Department Patients—An External Validation Study
Background/Objectives: Intracranial hemorrhage (ICH) is a life-threatening condition that can be rapidly detected by non-contrast head computed tomography (NCCT). RAPID ICH is a deep learning (DL) tool for automatic ICH identification using NCCT. Our aim was to assess the real-world performance of RAPID ICH compared to that of a first-year radiology resident on consecutively acquired NCCTs from patients referred from the Emergency Department. Methods: This single-center retrospective cohort study included NCCTs acquired on the same CT scanner over three months. Exclusion criteria were motion or metallic artifacts that substantially degraded the NCCT quality and incomplete NCCTs. Two senior neuroradiologists conducted ground-truth labeling of the NCCTs regarding ICH presence in a binary manner. The first-year radiology resident assessed NCCTs for ICH presence and was blinded to the ground-truth labeling. Sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were computed for the RAPID ICH identifications and for the first-year radiology resident’s ICH identifications. Results: After applying exclusion criteria, 844 NCCTs remained. Ground-truth labeling found ICH in 63 NCCTs. RAPID ICH showed 87.3% sensitivity, 74% specificity, 21.3% PPV, and 98.6% NPV, while the first-year radiology resident achieved 95.2% sensitivity, 90.8% specificity, 45.5% PPV, and 99.6% NPV. There were 8 false-negative and 203 false-positive RAPID ICH identifications. Conclusions: RAPID ICH’s sensitivity and specificity were lower than in prior studies performed using RAPID ICH, and there was a high number of false-positive RAPID ICH identifications, limiting the generalizability of the assessed version of this DL tool. Testing DL tools by comparing them with radiologists of varying experience can provide valuable insights into their performance.
- 16 January 2026
- Published by MDPI AG in Diagnostics
- Vol. 16 (2) , 282
Open AccessReal-World Integration of an Automated Tool for Intracranial Hemorrhage Detection in an Unselected Cohort of Emergency Department Patients—An External Validation Study
Background/Objectives: Intracranial hemorrhage (ICH) is a life-threatening condition that can be rapidly detected by non-contrast head computed tomography (NCCT). RAPID ICH is a deep learning (DL) tool for automatic ICH identification using NCCT. Our aim was to assess the real-world performance of RAPID ICH compared to that of a first-year radiology resident on consecutively acquired NCCTs from patients referred from the Emergency Department. Methods: This single-center retrospective cohort study included NCCTs acquired on the same CT scanner over three months. Exclusion criteria were motion or metallic artifacts that substantially degraded the NCCT quality and incomplete NCCTs. Two senior neuroradiologists conducted ground-truth labeling of the NCCTs regarding ICH presence in a binary manner. The first-year radiology resident assessed NCCTs for ICH presence and was blinded to the ground-truth labeling. Sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were computed for the RAPID ICH identifications and for the first-year radiology resident’s ICH identifications. Results: After applying exclusion criteria, 844 NCCTs remained. Ground-truth labeling found ICH in 63 NCCTs. RAPID ICH showed 87.3% sensitivity, 74% specificity, 21.3% PPV, and 98.6% NPV, while the first-year radiology resident achieved 95.2% sensitivity, 90.8% specificity, 45.5% PPV, and 99.6% NPV. There were 8 false-negative and 203 false-positive RAPID ICH identifications. Conclusions: RAPID ICH’s sensitivity and specificity were lower than in prior studies performed using RAPID ICH, and there was a high number of false-positive RAPID ICH identifications, limiting the generalizability of the assessed version of this DL tool. Testing DL tools by comparing them with radiologists of varying experience can provide valuable insights into their performance.
- 15 January 2026
- Published by Springer Nature
- p. 191-210
AI Applications in Ultrasound Imaging
- 9 September 2024
- Published by Elsevier in Journal of Medical Imaging and Radiation Sciences
- Vol. 55 (4) , 101736
Artificial intelligence and advanced MRI techniques: A comprehensive analysis of diffuse gliomas
- 9 September 2024
- Published by Elsevier in Journal of Medical Imaging and Radiation Sciences
- Vol. 55 (4) , 101736
Artificial intelligence and advanced MRI techniques: A comprehensive analysis of diffuse gliomas
- Open Access
- 27 June 2024
- Published by Elsevier in Radiography
- Vol. 30 (5) , 1427-1433
Radiomics evaluation for the early detection of Alzheimer's dementia using T1-weighted MRI
- 27 June 2024
- Published by Elsevier in Radiography
- Vol. 30 (5) , 1427-1433
Open AccessRadiomics evaluation for the early detection of Alzheimer's dementia using T1-weighted MRI
- Open Access
- 22 May 2024
- Published by Elsevier in Radiography
- Vol. 30 (4) , 1106-1115
A Nordic survey on artificial intelligence in the radiography profession – Is the profession ready for a culture change?
- 22 May 2024
- Published by Elsevier in Radiography
- Vol. 30 (4) , 1106-1115
Open AccessA Nordic survey on artificial intelligence in the radiography profession – Is the profession ready for a culture change?
- Open Access
- 9 March 2024
- Published by Elsevier in Radiography
- Vol. 30 (3) , 776-783
Nordic radiographers’ and students’ perspectives on artificial intelligence – A cross-sectional online survey
- 9 March 2024
- Published by Elsevier in Radiography
- Vol. 30 (3) , 776-783
Open AccessNordic radiographers’ and students’ perspectives on artificial intelligence – A cross-sectional online survey