Laurens Raes

Laurens Raes

Auto-generated profile, based on publicly available information

Laurens Raes

Department of Nuclear Medicine, Vrije Universiteit Brussel (VUB), Universitair Ziekenhuis Brussel (UZ Brussel), Brussels, Belgium

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
6 June 2025 in EJNMMI Physics
Verified
Journal Article
Open access
PDF file
SSSelene De Sutter
Selene De Sutter
IDIne Dirks
Ine Dirks
LRLaurens Raes
Laurens Raes
WGWietse Geens
Wietse Geens
HEHendrik Everaert
Hendrik Everaert
JVJef Vandemeulebroucke
Jef Vandemeulebroucke
Positron emission tomography (PET) with a [18F]fluoroethyl)-L-tyrosine ([18F]FET) tracer is of growing importance in the management of glioblastoma for the estimation of tumor extent and extraction of diagnostic and prognostic parameters. Robust and accurate glioblastoma segmentation methods are essential to maximize the benefits of this imaging modality. Given the importance of setting the foreground threshold during manual tumor delineation, this study investigates the added value of incorporating such prior knowledge to guide the automated segmentation and improve performance. Two segmentation networks were trained based on the nnU-Net guidelines: one with the [18F]FET PET image as sole input, and one with an additional input channel for the threshold map. For the latter, we investigate the benefit of manually obtained thresholds and explore automated prediction and generation of such maps. A fully automated pipeline was constructed by selecting the best performing threshold prediction approach and cascading this with the tumor segmentation model. The proposed two-channel network shows increased performance with guidance of threshold maps originating from the same reader whose ground-truth tumor label the prediction is compared to (DSC = 0.901). When threshold maps were generated by a different reader, performance reverted to levels comparable to the one-channel network and inter-reader variability. The proposed full pipeline achieves results on par with current state of the art (DSC = 0.807). Incorporating a threshold map can significantly improve tumor segmentation performance when it aligns well with the ground-truth label. However, the current inability to reliably reproduce these maps—both manually and automatically—or the ground-truth tumor labels, restricts the achievable accuracy for automated glioblastoma segmentation on [18F]FET PET, highlighting the need for more consistent definitions of such ground-truth delineations.

2 January 2026
Verified
Book Chapter
Closed access
PDF file
SSSelene De Sutter
Selene De Sutter
IDIne Dirks
Ine Dirks
LRLaurens Raes
Laurens Raes
WGWietse Geens
Wietse Geens
HEHendrik Everaert
Hendrik Everaert
JVJef Vandemeulebroucke
Jef Vandemeulebroucke

15 February 2022 in Cancer Research
Verified
Journal Article
Open access
OGOdrade Gondry
Odrade Gondry
CXCatarina Xavier
Catarina Xavier
WWWim Waelput
Wim Waelput
ODOmar Al Dabssi
Omar Al Dabssi
MVMarian Vanhoeij
Marian Vanhoeij
MKMarleen Keyaerts
Marleen Keyaerts
Background: Human epidermal growth factor receptor 2 (HER2) status is an important predictive biomarker in breast cancer (BC). Tumor heterogeneity has been described, with changes in HER2 expression levels between lesions and over the disease course. HER2 expression is assessed on tissue biopsies, at primary diagnosis and in metastatic lesions. A whole-body imaging technique such as PET/CT could help understand expression levels in different lesions. A 68Ga-labeled single domain antibody (sdAb) targeting the HER2 receptor has been developed and proven safe (Keyaerts et al., 2016). Imaging is performed at 90 min post-injection (pi). We report results of a phase II trial to assess the repeatability of the technique in 20 patients and the correlation of tracer uptake with HER2 tissue expression of the lesions present at the time of imaging. Methods: Twenty patients (pts) with a locally advanced or metastatic BC with at least one lesion of minimum 12 mm were included. Pts were injected intravenously with a typical protein mass of 100 µg and a radioactive dose ranging from 98-168 MBq 68GaNOTA-anti-HER2 sdAb. PET/CT images were obtained at 90 min pi. A second tracer injection followed by PET/CT was done with a maximal interval of 8 days. To assess repeatability, up to 5 lesions per pt were selected, with no more than 2 in a single organ. Peak Standard Uptake Values (SUVpeak) of the lesions were measured on both scans and compared with a t-test and Bland-Altman Plots. Images were compared to other available medical or imaging data and interpreted considering the subject’s disease course. Serum and plasma samples were collected before injection and between 60 and 365 days pi and stored for future detection of anti-drug antibodies (ADA) and liquid biopsies analysis for the presence of HER2 amplification. Tissue samples were assessed by central labs using mass spectrometry, immunohistochemistry and in fluorescence situ hybridization. Results: Twenty women with BC (6 HER2+, 14 HER2-) with a mean age of 58.6 y (37-81) were included. Three pts were scanned only once (2 due to withdrawal of consent, 1 due to covid pandemic). Repeatability of the technique was visually scored as excellent. For quantification, 50 lesions were compared on both scans in 17 pts without significant differences between the two measurements (p=0.40). The repeatability coefficient (RC) was 38.2%. The mean absolute percentage difference (MAPD) was 13.6%, comparable to repeat values reported for 18F-FDG. In 3 out of 6 HER2-positive (HER2+) patients, lesions showed high uptake, even better visible than using 18F-FDG in 2 of them. In 2 HER2+ subjects with a negative scan, lesions were confirmed to be true negatives: one patient did not relapse from BC but had tuberculosis; the other was confirmed to have a radiopneumonitis after radiotherapy and no relapse. In 1 HER2+ patient, the uptake was unexpectedly low. However, the HER2 status was also not reconfirmed in the metastatic setting for this subject. In 1 HER2-negative patient, the tumor HER2 status was changed from negative to positive based on a subsequent image-guided biopsy performed in this study. High tracer uptake was also seen in many of the patients presenting with HER2-low BC (IHC 1+ or 2+), indicating the potential of the tracer to detect low-level HER2 expression. Additional correlation to centrally performed tissue and blood analysis is ongoing. Conclusion: 68GaNOTA-Anti-HER2 PET/CT shows high uptake in HER2-expressing BC lesions but also in HER2-low lesions. The technique shows good repeatability and, in some cases, even better sensitivity than 18F-FDG PET/CT. Specificity was confirmed in relapse-free lesions such as tuberculosis and radiopneumonitis. Its sensitivity makes it a promising technique to assess HER2+ and HER2-low lesions in BC patients. Citation Format: Odrade Gondry, Catarina Xavier, Wim Waelput, Omar Al Dabssi, Marian Vanhoeij, Sandrine Aspeslagh, Sofie Joris, Christel Fontaine, Guy Verfaillie, Jacques De Grève, Katrien Glorieus, Ine Luyten, Frederik Vandenbroucke, Sophie Bourgeois, Laurens Raes, Sheeno Thyparambil, Nick Devoogdt, Ilse Vaneycken, Julie Cousaert, Vicky Caveliers, Hendrik Everaert, Tony Lahoutte, Marleen Keyaerts. Assessment of repeatability and uptake quantification of 68GaNOTA-anti-HER2 sdAb PET/CT in patients with locally advanced or metastatic breast cancer [abstract]. In: Proceedings of the 2021 San Antonio Breast Cancer Symposium; 2021 Dec 7-10; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2022;82(4 Suppl):Abstract nr P3-02-05.

9 April 2026 in ESMO Open
Verified
Journal Article
Open access
IDiris dirven
iris dirven
BCBertels Cleo
Bertels Cleo
YMY. Moreels
Y. Moreels
JKJ.I. Kessels
J.I. Kessels
NVNathalie Vanlaer
Nathalie Vanlaer
BNBart Neyns
Bart Neyns
Most patients with advanced melanoma progress despite standard-of-care treatments. Regorafenib (REGO), an oral multikinase inhibitor with RAF-dimer activity, demonstrated clinical activity in melanoma in retrospective case series and preclinical efficacy in overcoming resistance to BRAF/MEK inhibitors (BRAF/MEKi). This study prospectively evaluated REGO in heavily pretreated advanced melanoma patients. This single-center, phase II clinical trial (RegoMel, NCT05370807) assessed the objective response rate (ORR) upon continuous REGO dosing (40-120 mg daily) in 16 patients with advanced pretreated melanoma, regardless of the melanoma driver mutation. In BRAFV600-mutant patients, BRAF/MEKi addition was permitted upon progression on REGO monotherapy. Based on early efficacy signs, a KIT-mutant expansion cohort was also recruited and analyzed. Secondary endpoints included progression-free survival (PFS), overall survival (OS), and safety. There was one complete (BRAFV600-mutant) and five partial responses [KIT- (n = 3), BRAFV600-mutant (n = 2); ORR 37.5%; disease control rate (DCR) 56%]. Median duration of response was 37.4 weeks with median PFS (mPFS) and mOS of 12.1 weeks and 75.8 weeks, respectively. In the KIT-mutant expansion cohort (N = 9), ORR and DCR were 78% and 100%, respectively, and mPFS 43.4 weeks; mOS was not reached. Six BRAFV600-mutant patients received REGO + BRAF/MEKi at first progression (ORR 33%, DCR 83%, mPFS 20.4 weeks, mOS 62.1 weeks). Grade 3 treatment-related adverse events (TRAEs) occurred in 59% of patients on REGO monotherapy and 50% on REGO + BRAF/MEKi. The most common TRAEs were hand-foot-skin reaction, hypertension, and diarrhea. All TRAEs were reversible. This phase II clinical trial met its primary endpoint, demonstrating clinically meaningful antitumor activity and manageable toxicity with continuous daily REGO in advanced pretreated melanoma. The unprecedented high response rates in KIT-mutant melanoma and encouraging activity in BRAFV600-mutant patients receiving REGO + BRAF/MEKi support further investigation of REGO-based regimens in these subpopulations of melanoma patients.