Hanne Sorger

Dr. Hanne Sorger

orcid

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
9 February 2017 in PLOS ONE
Verified
Journal Article
Open access
PDF file
HSHanne Sorger
Hanne Sorger
EHErlend Fagertun Hofstad
Erlend Fagertun Hofstad
TATore Amundsen
Tore Amundsen
TLThomas Langø
Thomas Langø
JBJanne Beate Lervik Bakeng
Janne Beate Lervik Bakeng
HLHåkon Olav Leira
Håkon Olav Leira
Endobronchial ultrasound transbronchial needle aspiration (EBUS-TBNA) is the endoscopic method of choice for confirming lung cancer metastasis to mediastinal lymph nodes. Precision is crucial for correct staging and clinical decision-making. Navigation and multimodal imaging can potentially improve EBUS-TBNA efficiency. To demonstrate the feasibility of a multimodal image guiding system using electromagnetic navigation for ultrasound bronchoschopy in humans. Four patients referred for lung cancer diagnosis and staging with EBUS-TBNA were enrolled in the study. Target lymph nodes were predefined from the preoperative computed tomography (CT) images. A prototype convex probe ultrasound bronchoscope with an attached sensor for position tracking was used for EBUS-TBNA. Electromagnetic tracking of the ultrasound bronchoscope and ultrasound images allowed fusion of preoperative CT and intraoperative ultrasound in the navigation software. Navigated EBUS-TBNA was used to guide target lymph node localization and sampling. Navigation system accuracy was calculated, measured by the deviation between lymph node position in ultrasound and CT in three planes. Procedure time, diagnostic yield and adverse events were recorded. Preoperative CT and real-time ultrasound images were successfully fused and displayed in the navigation software during the procedures. Overall navigation accuracy (11 measurements) was 10.0 ± 3.8 mm, maximum 17.6 mm, minimum 4.5 mm. An adequate sample was obtained in 6/6 (100%) of targeted lymph nodes. No adverse events were registered. Electromagnetic navigated EBUS-TBNA was feasible, safe and easy in this human pilot study. The clinical usefulness was clearly demonstrated. Fusion of real-time ultrasound, preoperative CT and electromagnetic navigational bronchoscopy provided a controlled guiding to level of target, intraoperative overview and procedure documentation.

6 August 2024 in Journal of Imaging
Verified
Journal Article
Open access
PDF file
ØEØyvind Ervik
Øyvind Ervik
ITIngrid Elisabeth Tveten
Ingrid Elisabeth Tveten
EHErlend Fagertun Hofstad
Erlend Fagertun Hofstad
TLThomas Lango
Thomas Lango
HLHåkon Olav Leira
Håkon Olav Leira
HSHanne Sorger
Hanne Sorger
Endobronchial ultrasound (EBUS) is used in the minimally invasive sampling of thoracic lymph nodes. In lung cancer staging, the accurate assessment of mediastinal structures is essential but challenged by variations in anatomy, image quality, and operator-dependent image interpretation. This study aimed to automatically detect and segment mediastinal lymph nodes and blood vessels employing a novel U-Net architecture-based approach in EBUS images. A total of 1161 EBUS images from 40 patients were annotated. For training and validation, 882 images from 30 patients and 145 images from 5 patients were utilized. A separate set of 134 images was reserved for testing. For lymph node and blood vessel segmentation, the mean ± standard deviation (SD) values of the Dice similarity coefficient were 0.71 ± 0.35 and 0.76 ± 0.38, those of the precision were 0.69 ± 0.36 and 0.82 ± 0.22, those of the sensitivity were 0.71 ± 0.38 and 0.80 ± 0.25, those of the specificity were 0.98 ± 0.02 and 0.99 ± 0.01, and those of the F1 score were 0.85 ± 0.16 and 0.81 ± 0.21, respectively. The average processing and segmentation run-time per image was 55 ± 1 ms (mean ± SD). The new U-Net architecture-based approach (EBUS-AI) could automatically detect and segment mediastinal lymph nodes and blood vessels in EBUS images. The method performed well and was feasible and fast, enabling real-time automatic labeling.

5 January 2025 in Journal of Imaging
Verified
Journal Article
Open access
PDF file
ØEØyvind Ervik
Øyvind Ervik
MRMia Rødde
Mia Rødde
EHErlend Fagertun Hofstad
Erlend Fagertun Hofstad
ITIngrid Elisabeth Tveten
Ingrid Elisabeth Tveten
TLThomas Lango
Thomas Lango
HSHanne Sorger
Hanne Sorger
Endobronchial ultrasound-guided transbronchial needle aspiration (EBUS-TBNA) is a cornerstone in minimally invasive thoracic lymph node sampling. In lung cancer staging, precise assessment of lymph node position is crucial for clinical decision-making. This study aimed to demonstrate a new deep learning method to classify thoracic lymph nodes based on their anatomical location using EBUS images. Bronchoscopists labeled lymph node stations in real-time according to the Mountain Dressler nomenclature. EBUS images were then used to train and test a deep neural network (DNN) model, with intraoperative labels as ground truth. In total, 28,134 EBUS images were acquired from 56 patients. The model achieved an overall classification accuracy of 59.5 ± 5.2%. The highest precision, sensitivity, and F1 score were observed in station 4L, 77.6 ± 13.1%, 77.6 ± 15.4%, and 77.6 ± 15.4%, respectively. The lowest precision, sensitivity, and F1 score were observed in station 10L. The average processing and prediction time for a sequence of ten images was 0.65 ± 0.04 s, demonstrating the feasibility of real-time applications. In conclusion, the new DNN-based model could be used to classify lymph node stations from EBUS images. The method performance was promising with a potential for clinical use.

21 March 2025 in Respiratory Medicine
Verified
Journal Article
Open access
ALA.G. Lunde
A.G. Lunde
AHA.H. Henriksen
A.H. Henriksen
HSHanne Sorger
Hanne Sorger
TNT. Naustdal
T. Naustdal
TNT.I. Lund Nilsen
T.I. Lund Nilsen
SRS. Romundstad
S. Romundstad
The incidence and prevalence of sarcoidosis vary globally, with the highest estimates in Scandinavia. Since there are no recent data from Norway, we aimed to investigate the prevalence, incidence and mortality of sarcoidosis over three decades among participants in the population-based HUNT Study. The study population included participants in the first three surveys of the HUNT Study (HUNT1,1984-86; HUNT2,1995-97 and HUNT3, 2006-08). We identified 365 participants with sarcoidosis. Approximately 10 % of sarcoidosis patients were identified by x-ray screening in HUNT1, the remaining by linkage to hospital records. We randomly selected four age, sex and survey-matched participants without sarcoidosis for each of the 310 participants with incident sarcoidosis and followed these from diagnosis until death or end of follow-up in 2023. We used Cox regression to estimate adjusted hazard ratios (HRs) with 95 % confidence intervals (CIs) of death from all-causes. From 1984 to 2018, annual prevalence increased from 0.54 (95 % CI 0.41, 0.72) to 1.34 (95 % CI 1.08, 1.64) percent, while incidence rate increased from 12.1 (95 % CI 9.5, 14.7) to 18.7 (95 % CI 13.4, 24.0) per 100 000/year. The largest increase was seen in non-Lofgren syndrome (nLS). People with nLS had more than twice the mortality compared to people without sarcoidosis (HR 2.4; 95 % CI, 1.9, 3.1). There was no clear association between Lofgren syndrome and overall mortality. Sarcoidosis prevalence and incidence appeared to increase, particularly for nLS. Mechanisms leading to increased mortality in nLS needs to be further addressed.

20 May 2025 in Journal of Imaging
Verified
Journal Article
Open access
PDF file
SOSoroush Oskouei
Soroush Oskouei
MVMarit Valla
Marit Valla
APAndré Pedersen
André Pedersen
ESErik Smistad
Erik Smistad
VDVibeke Grotnes Dale
Vibeke Grotnes Dale
HSHanne Sorger
Hanne Sorger
The increased workload in pathology laboratories today means automated tools such as artificial intelligence models can be useful, helping pathologists with their tasks. In this paper, we propose a segmentation model (DRU-Net) that can provide a delineation of human non-small cell lung carcinomas and an augmentation method that can improve classification results. The proposed model is a fused combination of truncated pre-trained DenseNet201 and ResNet101V2 as a patch-wise classifier, followed by a lightweight U-Net as a refinement model. Two datasets (Norwegian Lung Cancer Biobank and Haukeland University Lung Cancer cohort) were used to develop the model. The DRU-Net model achieved an average of 0.91 Dice similarity coefficient. The proposed spatial augmentation method (multi-lens distortion) improved the Dice similarity coefficient from 0.88 to 0.91. Our findings show that selecting image patches that specifically include regions of interest leads to better results for the patch-wise classifier compared to other sampling methods. A qualitative analysis by pathology experts showed that the DRU-Net model was generally successful in tumor detection. Results in the test set showed some areas of false-positive and false-negative segmentation in the periphery, particularly in tumors with inflammatory and reactive changes. In summary, the presented DRU-Net model demonstrated the best performance on the segmentation task, and the proposed augmentation technique proved to improve the results.

10 February 2026 in Bioengineering
Verified
Journal Article
Open access
PDF file
ØEØyvind Ervik
Øyvind Ervik
MRMia Rødde
Mia Rødde
EHErlend Fagertun Hofstad
Erlend Fagertun Hofstad
TLThomas Lango
Thomas Lango
HLHåkon Olav Leira
Håkon Olav Leira
HSHanne Sorger
Hanne Sorger
Accurate localization of thoracic lymph nodes during endobronchial ultrasound (EBUS) is crucial for lung cancer staging, treatment planning, and prognostication. Artificial intelligence (AI) has the potential to support this process. Deep learning (DL) models often lack transparency but can benefit from explainable AI (XAI) tools like Gradient-weighted Class Activation Mapping (Grad-CAM). However, no prior study has quantitatively assessed whether model attention in EBUS imaging corresponds to relevant anatomy. This study developed a convolutional neural network (CNN) to classify thoracic lymph node stations and evaluated the anatomical relevance of Grad-CAM activations using a structured annotation framework. Applied on 35,527 labeled EBUS images, the CNN achieved 63.1% accuracy, with the highest F1-score in stations 4L, 4R, and 10R. Three expert bronchoscopists independently annotated Grad-CAM maps from 3131 test images. Activations predominantly aligned with lymph nodes and/or blood vessels, yielding an accuracy of 65.9% and an F1-score of 58.4%, with moderate interobserver agreement. These findings indicate that DL can aid lymph node station classification and that XAI offers meaningful insight into model behavior. The proposed framework may enhance anatomical orientation and operator training during EBUS, although further optimization and multicenter validation are required.