Gina Fürtjes
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Gina Fürtjes has a total of 45 co-authors. Here are the top co-authors by number of shared publications:
- Roland Goldbrunner
Department of Neurosurgery, University of Cologne , Cologne
22 shared publications - Abdulkader Al-Shugri
Institute for Neuropathology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Cologne, Germany. 6
21 shared publications - Adrian Ion-Margineanu
Invenio Imaging, Santa Clara, California
21 shared publications - Anna-Katharina Meissner
Dept. of General Neurosurgery, Center for Neurosurgery, Faculty of Medicine and University Hospital Cologne, University of Cologne, Cologne, Germany
21 shared publications - Daniel Ruess
University of Cologne
21 shared publications - David Reinecke
Department of General Neurosurgery, Center for Neurosurgery, Faculty of Medicine and University Hospital Cologne, University of Cologne, Cologne, Germany
21 shared publications
Latest Publications
- Open Access
- 12 January 2026
- Published by Oxford University Press (OUP) in Neuro-Oncology Advances
- Vol. 8 (1)
Performance of intraoperative artificial intelligence-assisted label-free stimulated Raman histology in recurrent brain tumors
Background: Therapy-induced tissue alterations complicate intraoperative diagnosis of recurrent central nervous system (CNS) tumors. We evaluated stimulated Raman histology (SRH) combined with convolutional neural networks (CNNs) for rapid tumor detection and classification. Methods: In this bicentric observational study, fresh tissue from patients undergoing resection or stereotactic biopsy for suspected recurrent CNS tumors was imaged with fiber-laser-based SRH. CNN1 performed binary tumor/non-tumor prediction and CNN2 histotype classification. CNN1 was evaluated against blinded neuropathologist SRH consensus and CNN2 against the final integrated histopathological diagnosis. Results: Of 382 acquired SRH images, 262 images from 143 patients were included. CNN1 achieved an AUC of 0.975 (95% CI, 0.95-1.00) for tumor detection. An exploratory cohort-derived tumor probability threshold of ≥59 increased specificity from 70.7% to 92.0% while maintaining 95.2% sensitivity and identifying 71.4% of radiation necrosis samples. Among 212 images in treatment subgroup analysis, CNN1 accuracy did not differ significantly across prior-treatment groups (overall 90.1%; P = .080). CNN2 accuracy declined from 61.8% after surgery alone to 39.0% after surgery, radiotherapy, and medical treatment (χ2 = 6.04, P = .049). Multimodal therapy was independently associated with lower odds of correct CNN2 prediction (adjusted OR, 0.10 [95% CI, 0.02-0.39]; P = .001 and 0.04 [95% CI, 0.01-0.20]; P < .001). 120/382 images (31.4%) were of insufficient diagnostic quality; application of the quality control threshold would have rejected 84/120 (70.0%). Conclusions: CNN1 maintained high tumor/non-tumor discrimination across treatment subgroups when image quality was sufficient, whereas CNN2 entity-classification performance declined with increasing treatment intensity. Reliable SRH-based diagnosis in recurrent tumors requires validated image-quality control measures and model adaptation to recurrent disease.
- 12 January 2026
- Published by Oxford University Press (OUP) in Neuro-Oncology Advances
- Vol. 8 (1)
Open AccessPerformance of intraoperative artificial intelligence-assisted label-free stimulated Raman histology in recurrent brain tumors
Background: Therapy-induced tissue alterations complicate intraoperative diagnosis of recurrent central nervous system (CNS) tumors. We evaluated stimulated Raman histology (SRH) combined with convolutional neural networks (CNNs) for rapid tumor detection and classification. Methods: In this bicentric observational study, fresh tissue from patients undergoing resection or stereotactic biopsy for suspected recurrent CNS tumors was imaged with fiber-laser-based SRH. CNN1 performed binary tumor/non-tumor prediction and CNN2 histotype classification. CNN1 was evaluated against blinded neuropathologist SRH consensus and CNN2 against the final integrated histopathological diagnosis. Results: Of 382 acquired SRH images, 262 images from 143 patients were included. CNN1 achieved an AUC of 0.975 (95% CI, 0.95-1.00) for tumor detection. An exploratory cohort-derived tumor probability threshold of ≥59 increased specificity from 70.7% to 92.0% while maintaining 95.2% sensitivity and identifying 71.4% of radiation necrosis samples. Among 212 images in treatment subgroup analysis, CNN1 accuracy did not differ significantly across prior-treatment groups (overall 90.1%; P = .080). CNN2 accuracy declined from 61.8% after surgery alone to 39.0% after surgery, radiotherapy, and medical treatment (χ2 = 6.04, P = .049). Multimodal therapy was independently associated with lower odds of correct CNN2 prediction (adjusted OR, 0.10 [95% CI, 0.02-0.39]; P = .001 and 0.04 [95% CI, 0.01-0.20]; P < .001). 120/382 images (31.4%) were of insufficient diagnostic quality; application of the quality control threshold would have rejected 84/120 (70.0%). Conclusions: CNN1 maintained high tumor/non-tumor discrimination across treatment subgroups when image quality was sufficient, whereas CNN2 entity-classification performance declined with increasing treatment intensity. Reliable SRH-based diagnosis in recurrent tumors requires validated image-quality control measures and model adaptation to recurrent disease.
- Open Access
- 3 September 2024
- Published by American Association for Cancer Research (AACR)
Supplementary Figure S2 from Streamlined Intraoperative Brain Tumor Classification and Molecular Subtyping in Stereotactic Biopsies Using Stimulated Raman Histology and Deep Learning
Supplementary Figure S2. Illustration of two SRH images with different signal-to-noise ratios due to ambient temperature and autofocus variability.
- 3 September 2024
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Figure S2 from Streamlined Intraoperative Brain Tumor Classification and Molecular Subtyping in Stereotactic Biopsies Using Stimulated Raman Histology and Deep Learning
Supplementary Figure S2. Illustration of two SRH images with different signal-to-noise ratios due to ambient temperature and autofocus variability.
- Open Access
- 3 September 2024
- Published by American Association for Cancer Research (AACR)
Data from Streamlined Intraoperative Brain Tumor Classification and Molecular Subtyping in Stereotactic Biopsies Using Stimulated Raman Histology and Deep Learning
Purpose:Recent artificial intelligence algorithms aided intraoperative decision-making via stimulated Raman histology (SRH) during craniotomy. This study assesses deep learning algorithms for rapid intraoperative diagnosis from SRH images in small stereotactic-guided brain biopsies. It defines a minimum tissue sample size threshold to ensure diagnostic accuracy.Experimental Design:A prospective single-center study examined 121 SRH images from 84 patients with unclear intracranial lesions undergoing stereotactic brain biopsy. Unprocessed, label-free samples were imaged using a portable fiber laser Raman scattering microscope. Three deep learning models were tested to (i) identify tumorous/nontumorous tissue as qualitative biopsy control; (ii) subclassify into high-grade glioma (central nervous system World Health Organization grade 4), diffuse low-grade glioma (central nervous system World Health Organization grades 2–3), metastases, lymphoma, or gliosis; and (iii) molecularly subtype IDH and 1p/19q statuses of adult-type diffuse gliomas. Model predictions were evaluated against frozen section analysis and final neuropathologic diagnoses.Results:The first model identified tumorous/nontumorous tissue with 91.7% accuracy. Sample size on slides impacted accuracy in brain tumor subclassification (81.6%, κ = 0.72 frozen section; 73.9%, κ = 0.61 second model), with SRH images being smaller than hematoxylin and eosin images (4.1 ± 2.5 mm2 vs. 16.7 ± 8.2 mm2, P < 0.001). SRH images with more than 140 high-quality patches and a mean squeezed sample of 5.26 mm2 yielded 89.5% accuracy in subclassification and 93.9% in molecular subtyping of adult-type diffuse gliomas.Conclusions:Artificial intelligence–based SRH image analysis is non-inferior to frozen section analysis in detecting and subclassifying brain tumors during small stereotactic-guided biopsies once a critical squeezed sample size is reached. Beyond frozen section analysis, it enables valid molecular glioma subtyping, allowing faster treatment decisions in the future; however, refinement is needed for long-term application.
- 3 September 2024
- Published by American Association for Cancer Research (AACR)
Open AccessData from Streamlined Intraoperative Brain Tumor Classification and Molecular Subtyping in Stereotactic Biopsies Using Stimulated Raman Histology and Deep Learning
Purpose:Recent artificial intelligence algorithms aided intraoperative decision-making via stimulated Raman histology (SRH) during craniotomy. This study assesses deep learning algorithms for rapid intraoperative diagnosis from SRH images in small stereotactic-guided brain biopsies. It defines a minimum tissue sample size threshold to ensure diagnostic accuracy.Experimental Design:A prospective single-center study examined 121 SRH images from 84 patients with unclear intracranial lesions undergoing stereotactic brain biopsy. Unprocessed, label-free samples were imaged using a portable fiber laser Raman scattering microscope. Three deep learning models were tested to (i) identify tumorous/nontumorous tissue as qualitative biopsy control; (ii) subclassify into high-grade glioma (central nervous system World Health Organization grade 4), diffuse low-grade glioma (central nervous system World Health Organization grades 2–3), metastases, lymphoma, or gliosis; and (iii) molecularly subtype IDH and 1p/19q statuses of adult-type diffuse gliomas. Model predictions were evaluated against frozen section analysis and final neuropathologic diagnoses.Results:The first model identified tumorous/nontumorous tissue with 91.7% accuracy. Sample size on slides impacted accuracy in brain tumor subclassification (81.6%, κ = 0.72 frozen section; 73.9%, κ = 0.61 second model), with SRH images being smaller than hematoxylin and eosin images (4.1 ± 2.5 mm2 vs. 16.7 ± 8.2 mm2, P < 0.001). SRH images with more than 140 high-quality patches and a mean squeezed sample of 5.26 mm2 yielded 89.5% accuracy in subclassification and 93.9% in molecular subtyping of adult-type diffuse gliomas.Conclusions:Artificial intelligence–based SRH image analysis is non-inferior to frozen section analysis in detecting and subclassifying brain tumors during small stereotactic-guided biopsies once a critical squeezed sample size is reached. Beyond frozen section analysis, it enables valid molecular glioma subtyping, allowing faster treatment decisions in the future; however, refinement is needed for long-term application.
- Open Access
- 3 September 2024
- Published by American Association for Cancer Research (AACR)
Supplementary Table S6 from Streamlined Intraoperative Brain Tumor Classification and Molecular Subtyping in Stereotactic Biopsies Using Stimulated Raman Histology and Deep Learning
Supplementary Table S6. The second model was used to predict the class of each acquired entity from small biopsy tissue samples. These predictions were compared to the frozen section diagnosis after tumor radiotherapy. The level of accuracy depended on the final diagnosis and the predefined model label assignment to the respective subclasses.
- 3 September 2024
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Table S6 from Streamlined Intraoperative Brain Tumor Classification and Molecular Subtyping in Stereotactic Biopsies Using Stimulated Raman Histology and Deep Learning
Supplementary Table S6. The second model was used to predict the class of each acquired entity from small biopsy tissue samples. These predictions were compared to the frozen section diagnosis after tumor radiotherapy. The level of accuracy depended on the final diagnosis and the predefined model label assignment to the respective subclasses.
- Open Access
- 3 September 2024
- Published by American Association for Cancer Research (AACR)
Supplementary Table S2 from Streamlined Intraoperative Brain Tumor Classification and Molecular Subtyping in Stereotactic Biopsies Using Stimulated Raman Histology and Deep Learning
Supplementary Table S2. The first model illustrates each collected entity with corresponding class predictions (CP). It classifies small biopsy tissue samples as tumorous or non-tumorous tissue; accuracy depends on the final diagnosis (FD).
- 3 September 2024
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Table S2 from Streamlined Intraoperative Brain Tumor Classification and Molecular Subtyping in Stereotactic Biopsies Using Stimulated Raman Histology and Deep Learning
Supplementary Table S2. The first model illustrates each collected entity with corresponding class predictions (CP). It classifies small biopsy tissue samples as tumorous or non-tumorous tissue; accuracy depends on the final diagnosis (FD).
- Open Access
- 3 September 2024
- Published by American Association for Cancer Research (AACR)
Supplementary Table S6 from Streamlined Intraoperative Brain Tumor Classification and Molecular Subtyping in Stereotactic Biopsies Using Stimulated Raman Histology and Deep Learning
Supplementary Table S6. The second model was used to predict the class of each acquired entity from small biopsy tissue samples. These predictions were compared to the frozen section diagnosis after tumor radiotherapy. The level of accuracy depended on the final diagnosis and the predefined model label assignment to the respective subclasses.
- 3 September 2024
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Table S6 from Streamlined Intraoperative Brain Tumor Classification and Molecular Subtyping in Stereotactic Biopsies Using Stimulated Raman Histology and Deep Learning
Supplementary Table S6. The second model was used to predict the class of each acquired entity from small biopsy tissue samples. These predictions were compared to the frozen section diagnosis after tumor radiotherapy. The level of accuracy depended on the final diagnosis and the predefined model label assignment to the respective subclasses.
- Open Access
- 3 September 2024
- Published by American Association for Cancer Research (AACR)
Supplementary Table S7 from Streamlined Intraoperative Brain Tumor Classification and Molecular Subtyping in Stereotactic Biopsies Using Stimulated Raman Histology and Deep Learning
Supplementary Table S7. Illustration of each deep-learning model’s best prediction performance on SRH images with ≥130 high-quality patches (first model) and >140 high-quality patches (second and third model) after stepwise metric performance evaluation. The second model was used to predict the class of each acquired entity from small biopsy tissue samples. The level of accuracy depended on the final integrated diagnosis and the predefined model label assignment to the respective subclasses.
- 3 September 2024
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Table S7 from Streamlined Intraoperative Brain Tumor Classification and Molecular Subtyping in Stereotactic Biopsies Using Stimulated Raman Histology and Deep Learning
Supplementary Table S7. Illustration of each deep-learning model’s best prediction performance on SRH images with ≥130 high-quality patches (first model) and >140 high-quality patches (second and third model) after stepwise metric performance evaluation. The second model was used to predict the class of each acquired entity from small biopsy tissue samples. The level of accuracy depended on the final integrated diagnosis and the predefined model label assignment to the respective subclasses.
- Open Access
- 3 September 2024
- Published by American Association for Cancer Research (AACR)
Supplementary Table S1 from Streamlined Intraoperative Brain Tumor Classification and Molecular Subtyping in Stereotactic Biopsies Using Stimulated Raman Histology and Deep Learning
Supplementary Table S1. Description of the SRH-based diagnostic accuracy of the first model in case of neuropathological diagnosed non-tumorous tissue from open resection procedures since the stereotactic-guided biopsy dataset contained only a few cases due to IRB protocol restrictions and the common non-invasive diagnostic differentiation by means of 18F-FET-PET CT/MRI to distinguish between tumorous and non-tumorous tissue, e.g., in recurrent tumor cases. Non-tumorous tissue samples of the brain summarized here were obtained non- or purposely from surrounding white or gray matter adjacent to the tumor during open tumor en bloc resections. After resection, these tissue parts were extracted from the whole tissue sample for further analysis. Further cases comprised space-occupying suspected tumorous lesions or post-radiotherapy lesions (e.g., pseudoprogression or radiogenic necrosis) due to immense edematous effect. The final FFPE-based diagnosis revealed non-tumorous tissue.
- 3 September 2024
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Table S1 from Streamlined Intraoperative Brain Tumor Classification and Molecular Subtyping in Stereotactic Biopsies Using Stimulated Raman Histology and Deep Learning
Supplementary Table S1. Description of the SRH-based diagnostic accuracy of the first model in case of neuropathological diagnosed non-tumorous tissue from open resection procedures since the stereotactic-guided biopsy dataset contained only a few cases due to IRB protocol restrictions and the common non-invasive diagnostic differentiation by means of 18F-FET-PET CT/MRI to distinguish between tumorous and non-tumorous tissue, e.g., in recurrent tumor cases. Non-tumorous tissue samples of the brain summarized here were obtained non- or purposely from surrounding white or gray matter adjacent to the tumor during open tumor en bloc resections. After resection, these tissue parts were extracted from the whole tissue sample for further analysis. Further cases comprised space-occupying suspected tumorous lesions or post-radiotherapy lesions (e.g., pseudoprogression or radiogenic necrosis) due to immense edematous effect. The final FFPE-based diagnosis revealed non-tumorous tissue.
- Open Access
- 3 September 2024
- Published by American Association for Cancer Research (AACR)
Supplementary Figure S1 from Streamlined Intraoperative Brain Tumor Classification and Molecular Subtyping in Stereotactic Biopsies Using Stimulated Raman Histology and Deep Learning
Supplementary Figure S1. Illustration of unprocessed sample processing and corresponding field of view (FOV) size selection.
- 3 September 2024
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Figure S1 from Streamlined Intraoperative Brain Tumor Classification and Molecular Subtyping in Stereotactic Biopsies Using Stimulated Raman Histology and Deep Learning
Supplementary Figure S1. Illustration of unprocessed sample processing and corresponding field of view (FOV) size selection.
- Open Access
- 3 September 2024
- Published by American Association for Cancer Research (AACR)
Supplementary Table S3 from Streamlined Intraoperative Brain Tumor Classification and Molecular Subtyping in Stereotactic Biopsies Using Stimulated Raman Histology and Deep Learning
Supplementary Table S3. The second model was tested on small biopsy tissue samples to classify each acquired entity into subclasses, e.g., pilocytic astrocytoma, diffuse low-grade glioma, high-grade glioma, lymphoma, metastases, and gliosis. The corresponding class predictions are compared to the final neuropathological diagnosis.
- 3 September 2024
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Table S3 from Streamlined Intraoperative Brain Tumor Classification and Molecular Subtyping in Stereotactic Biopsies Using Stimulated Raman Histology and Deep Learning
Supplementary Table S3. The second model was tested on small biopsy tissue samples to classify each acquired entity into subclasses, e.g., pilocytic astrocytoma, diffuse low-grade glioma, high-grade glioma, lymphoma, metastases, and gliosis. The corresponding class predictions are compared to the final neuropathological diagnosis.