Georgios Kapsas
Georgios Kapsas has a total of 332 co-authors. Here are the top co-authors by number of shared publications:
- Marion Smits
Department of Radiology and Nuclear Medicine Erasmus MC, University Medical Center Rotterdam Rotterdam The Netherlands
4 shared publications - Martin J. van Den Bent
The Brain Tumor Center, Erasmus MC Cancer Institute, Rotterdam, the Netherlands
4 shared publications - Pim French
Erasmus MC, Rotterdam, Netherlands
4 shared publications - Stefan Klein
Department of Radiology and Nuclear Medicine, Erasmus MC, Rotterdam, The Netherlands
4 shared publications Fatih Incekara
Department of Radiology and Nuclear Medicine, Erasmus MC University Medical Centre Rotterdam, Rotterdam, Netherlands
3 shared publications- Renske Gahrmann
Department of Radiology and Nuclear Medicine, Erasmus MC University Medical Centre Rotterdam, Rotterdam, Netherlands
3 shared publications
Latest Publications
- Open Access
- 31 October 2025
- Published by The Korean Movement Disorder Society in Journal of Movement Disorders
- Vol. 18 (4) , 289-303
MRI-Guided Focused Ultrasound in Parkinson’s Disease and Essential Tremor: Incisionless but Invasive. A Narrative Review
Magnetic resonance-guided focused ultrasound (MRgFUS) is an emerging and promising technology for treating movement disorders, such as essential tremors and tremor-dominant Parkinson’s disease. MRgFUS utilizes advanced ultrasound transducer emitters to condense sound waves at a precisely defined point. This technology can target various brain areas, such as the pallidothalamic tract, thalamus, and pallidum, to ameliorate some of the symptoms of Parkinson’s disease and other movement disorders, such as dystonic and action-induced tremors. We review the current status of preclinical and clinical trials on the clinical use, treatment outcomes, and indications of MRgFUS.
- 31 October 2025
- Published by The Korean Movement Disorder Society in Journal of Movement Disorders
- Vol. 18 (4) , 289-303
Open AccessMRI-Guided Focused Ultrasound in Parkinson’s Disease and Essential Tremor: Incisionless but Invasive. A Narrative Review
Magnetic resonance-guided focused ultrasound (MRgFUS) is an emerging and promising technology for treating movement disorders, such as essential tremors and tremor-dominant Parkinson’s disease. MRgFUS utilizes advanced ultrasound transducer emitters to condense sound waves at a precisely defined point. This technology can target various brain areas, such as the pallidothalamic tract, thalamus, and pallidum, to ameliorate some of the symptoms of Parkinson’s disease and other movement disorders, such as dystonic and action-induced tremors. We review the current status of preclinical and clinical trials on the clinical use, treatment outcomes, and indications of MRgFUS.
- Open Access
- 26 January 2023
- Published by Springer Nature in Nature Communications
- Vol. 14 (1) , 1-2
Author Correction: Federated learning enables big data for rare cancer boundary detection
- 26 January 2023
- Published by Springer Nature in Nature Communications
- Vol. 14 (1) , 1-2
Open AccessAuthor Correction: Federated learning enables big data for rare cancer boundary detection
- Top Cited PapersOpen Access
- 5 December 2022
- Published by Springer Nature in Nature Communications
- Vol. 13 (1) , 1-17
Federated learning enables big data for rare cancer boundary detection
Although machine learning (ML) has shown promise across disciplines, out-of-sample generalizability is concerning. This is currently addressed by sharing multi-site data, but such centralization is challenging/infeasible to scale due to various limitations. Federated ML (FL) provides an alternative paradigm for accurate and generalizable ML, by only sharing numerical model updates. Here we present the largest FL study to-date, involving data from 71 sites across 6 continents, to generate an automatic tumor boundary detector for the rare disease of glioblastoma, reporting the largest such dataset in the literature (n = 6, 314). We demonstrate a 33% delineation improvement for the surgically targetable tumor, and 23% for the complete tumor extent, over a publicly trained model. We anticipate our study to: 1) enable more healthcare studies informed by large diverse data, ensuring meaningful results for rare diseases and underrepresented populations, 2) facilitate further analyses for glioblastoma by releasing our consensus model, and 3) demonstrate the FL effectiveness at such scale and task-complexity as a paradigm shift for multi-site collaborations, alleviating the need for data-sharing.
- 5 December 2022
- Published by Springer Nature in Nature Communications
- Vol. 13 (1) , 1-17
Top Cited PapersOpen AccessFederated learning enables big data for rare cancer boundary detection
Although machine learning (ML) has shown promise across disciplines, out-of-sample generalizability is concerning. This is currently addressed by sharing multi-site data, but such centralization is challenging/infeasible to scale due to various limitations. Federated ML (FL) provides an alternative paradigm for accurate and generalizable ML, by only sharing numerical model updates. Here we present the largest FL study to-date, involving data from 71 sites across 6 continents, to generate an automatic tumor boundary detector for the rare disease of glioblastoma, reporting the largest such dataset in the literature (n = 6, 314). We demonstrate a 33% delineation improvement for the surgically targetable tumor, and 23% for the complete tumor extent, over a publicly trained model. We anticipate our study to: 1) enable more healthcare studies informed by large diverse data, ensuring meaningful results for rare diseases and underrepresented populations, 2) facilitate further analyses for glioblastoma by releasing our consensus model, and 3) demonstrate the FL effectiveness at such scale and task-complexity as a paradigm shift for multi-site collaborations, alleviating the need for data-sharing.
- Top Cited PapersOpen Access
- 5 July 2022
- Published by Oxford University Press (OUP) in Neuro-Oncology
- Vol. 25 (2) , 279-289
Combined molecular subtyping, grading, and segmentation of glioma using multi-task deep learning
Background: Accurate characterization of glioma is crucial for clinical decision making. A delineation of the tumor is also desirable in the initial decision stages but is time-consuming. Previously, deep learning methods have been developed that can either non-invasively predict the genetic or histological features of glioma, or that can automatically delineate the tumor, but not both tasks at the same time. Here, we present our method that can predict the molecular subtype and grade, while simultaneously providing a delineation of the tumor. Methods: We developed a single multi-task convolutional neural network that uses the full 3D, structural, preoperative MRI scans to predict the IDH mutation status, the 1p/19q co-deletion status, and the grade of a tumor, while simultaneously segmenting the tumor. We trained our method using a patient cohort containing 1508 glioma patients from 16 institutes. We tested our method on an independent dataset of 240 patients from 13 different institutes. Results: In the independent test set, we achieved an IDH-AUC of 0.90, an 1p/19q co-deletion AUC of 0.85, and a grade AUC of 0.81 (grade II/III/IV). For the tumor delineation, we achieved a mean whole tumor Dice score of 0.84. Conclusions: We developed a method that non-invasively predicts multiple, clinically relevant features of glioma. Evaluation in an independent dataset shows that the method achieves a high performance and that it generalizes well to the broader clinical population. This first-of-its-kind method opens the door to more generalizable, instead of hyper-specialized, AI methods.
- 5 July 2022
- Published by Oxford University Press (OUP) in Neuro-Oncology
- Vol. 25 (2) , 279-289
Top Cited PapersOpen AccessCombined molecular subtyping, grading, and segmentation of glioma using multi-task deep learning
Background: Accurate characterization of glioma is crucial for clinical decision making. A delineation of the tumor is also desirable in the initial decision stages but is time-consuming. Previously, deep learning methods have been developed that can either non-invasively predict the genetic or histological features of glioma, or that can automatically delineate the tumor, but not both tasks at the same time. Here, we present our method that can predict the molecular subtype and grade, while simultaneously providing a delineation of the tumor. Methods: We developed a single multi-task convolutional neural network that uses the full 3D, structural, preoperative MRI scans to predict the IDH mutation status, the 1p/19q co-deletion status, and the grade of a tumor, while simultaneously segmenting the tumor. We trained our method using a patient cohort containing 1508 glioma patients from 16 institutes. We tested our method on an independent dataset of 240 patients from 13 different institutes. Results: In the independent test set, we achieved an IDH-AUC of 0.90, an 1p/19q co-deletion AUC of 0.85, and a grade AUC of 0.81 (grade II/III/IV). For the tumor delineation, we achieved a mean whole tumor Dice score of 0.84. Conclusions: We developed a method that non-invasively predicts multiple, clinically relevant features of glioma. Evaluation in an independent dataset shows that the method achieves a high performance and that it generalizes well to the broader clinical population. This first-of-its-kind method opens the door to more generalizable, instead of hyper-specialized, AI methods.
- Open Access
- 13 December 2019
- Published by American Association for Cancer Research (AACR) in Clinical Cancer Research
- Vol. 25 (24) , 7455-7462
Predicting the 1p/19q Codeletion Status of Presumed Low-Grade Glioma with an Externally Validated Machine Learning Algorithm
Purpose: Patients with 1p/19q codeleted low-grade glioma (LGG) have longer overall survival and better treatment response than patients with 1p/19q intact tumors. Therefore, it is relevant to know the 1p/19q status. To investigate whether the 1p/19q status can be assessed prior to tumor resection, we developed a machine learning algorithm to predict the 1p/19q status of presumed LGG based on preoperative MRI. Experimental Design: Preoperative brain MR images from 284 patients who had undergone biopsy or resection of presumed LGG were used to train a support vector machine algorithm. The algorithm was trained on the basis of features extracted from post-contrast T1-weighted and T2-weighted MR images and on patients' age and sex. The performance of the algorithm compared with tissue diagnosis was assessed on an external validation dataset of MR images from 129 patients with LGG from The Cancer Imaging Archive (TCIA). Four clinical experts also predicted the 1p/19q status of the TCIA MR images. Results: The algorithm achieved an AUC of 0.72 in the external validation dataset. The algorithm had a higher predictive performance than the average of the neurosurgeons (AUC 0.52) but lower than that of the neuroradiologists (AUC of 0.81). There was a wide variability between clinical experts (AUC 0.45–0.83). Conclusions: Our results suggest that our algorithm can noninvasively predict the 1p/19q status of presumed LGG with a performance that on average outperformed the oncological neurosurgeons. Evaluation on an independent dataset indicates that our algorithm is robust and generalizable.
- 13 December 2019
- Published by American Association for Cancer Research (AACR) in Clinical Cancer Research
- Vol. 25 (24) , 7455-7462
Open AccessPredicting the 1p/19q Codeletion Status of Presumed Low-Grade Glioma with an Externally Validated Machine Learning Algorithm
Purpose: Patients with 1p/19q codeleted low-grade glioma (LGG) have longer overall survival and better treatment response than patients with 1p/19q intact tumors. Therefore, it is relevant to know the 1p/19q status. To investigate whether the 1p/19q status can be assessed prior to tumor resection, we developed a machine learning algorithm to predict the 1p/19q status of presumed LGG based on preoperative MRI. Experimental Design: Preoperative brain MR images from 284 patients who had undergone biopsy or resection of presumed LGG were used to train a support vector machine algorithm. The algorithm was trained on the basis of features extracted from post-contrast T1-weighted and T2-weighted MR images and on patients' age and sex. The performance of the algorithm compared with tissue diagnosis was assessed on an external validation dataset of MR images from 129 patients with LGG from The Cancer Imaging Archive (TCIA). Four clinical experts also predicted the 1p/19q status of the TCIA MR images. Results: The algorithm achieved an AUC of 0.72 in the external validation dataset. The algorithm had a higher predictive performance than the average of the neurosurgeons (AUC 0.52) but lower than that of the neuroradiologists (AUC of 0.81). There was a wide variability between clinical experts (AUC 0.45–0.83). Conclusions: Our results suggest that our algorithm can noninvasively predict the 1p/19q status of presumed LGG with a performance that on average outperformed the oncological neurosurgeons. Evaluation on an independent dataset indicates that our algorithm is robust and generalizable.
- Open Access
- 25 May 2018
- Published by Galenos Yayinevi in Turkish Journal of Hematology
- Vol. 35 (2) , 147-149
Successful Treatment of Chronic Lymphocytic Leukemia Multifocal Central Nervous System Involvement with Ibrutinib
- 25 May 2018
- Published by Galenos Yayinevi in Turkish Journal of Hematology
- Vol. 35 (2) , 147-149
Open AccessSuccessful Treatment of Chronic Lymphocytic Leukemia Multifocal Central Nervous System Involvement with Ibrutinib