GSGottfried Schlaug

Gottfried Schlaug

*This is an algorithmically generated author record based on publicly available information.

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


Gottfried Schlaug has a total of 62 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Case Report: Inflammatory CADASIL phenotype associated with a rare cysteine-sparing NOTCH3 variant

    by Abraham Madjidov, Mary-Alice Abbott, Katherine M. Mullen, Richard Hicks, Gottfried Schlaug

    We present a 50-year-old female who has a longstanding history of migraine with aura. She experienced one episode of partial visual field loss associated with a small acute/subacute lesion involving the cortex and subcortical white matter (showing contrast enhancement), alongside extensive white matter hyperintensities. Given these findings, CADASIL was suspected. Genetic testing identified a rare heterozygous NOTCH3 variant (c.6102dup, p.Gly2035Argfs*60), currently classified as a variant of uncertain significance. Concurrent cerebrospinal fluid analysis revealed elevated myelin basic protein, an elevated IgG index, and 4 oligoclonal bands, indicating an inflammatory process. Her visual evoked potentials showed no evidence of optic nerve or tract impairment. Approximately 9 months later, the occipital lesion evolved into encephalomalacia and gliosis without enhancement, while the extensive white matter hyperintensities remained stable. A repeat lumbar puncture 1 year later showed persistently elevated myelin basic protein and IgG index, now with 7 oligoclonal bands (some shared with serum). Currently, her neurological examination is normal. She is managed on dual antiplatelet therapy, and her migraines are effectively controlled with calcium-channel blocker prophylaxis. Notably, her mother, diagnosed with multiple sclerosis for several decades despite imaging findings suggestive of CADASIL, shares the same NOTCH3 variant. One of her two children tested negative for the variant and had normal imaging, while the other minor child has a significant history of migraines with aura. Our patient’s clinical presentation and comprehensive findings raise the possibility of an inflammatory phenotype potentially associated with the rare NOTCH3 c.6102dup variant, though causation remains unclear. Coexistence with another demyelinating central nervous system disease is possible, and further research is needed to clarify this relationship. If inflammatory variants of CADASIL exist, alternative treatments targeting inflammation may need consideration.


  • Automated Ensemble Method for Pediatric Brain Tumor Segmentation

    by Shashidhar Reddy Javaji, Advait Gosai, Sovesh Mohapatra, Gottfried Schlaug

  • An Ensemble Approach for Segmentation of Neonatal HIE Lesions

    by Chiranjeewee Prasad Koirala, Sovesh Mohapatra, Gottfried Schlaug


  • Open Access

    Automated ensemble method for pediatric brain tumor segmentation

    by Shashidhar Reddy Javaji, Sovesh Mohapatra, Advait Gosai, Gottfried Schlaug

    Brain tumors remain a critical global health challenge, necessitating advancements in diagnostic techniques and treatment methodologies. A tumor or its recurrence often needs to be identified in imaging studies and differentiated from normal brain tissue. In response to the growing need for age-specific segmentation models, particularly for pediatric patients, this study explores the deployment of deep learning techniques using magnetic resonance imaging (MRI) modalities. By introducing a novel ensemble approach using ONet and modified versions of UNet, coupled with innovative loss functions, this study achieves a precise segmentation model for the BraTS-PEDs 2023 Challenge. Data augmentation, including both single and composite transformations, ensures model robustness and accuracy across different scanning protocols. The ensemble strategy, integrating the ONet and UNet models, shows greater effectiveness in capturing specific features and modeling diverse aspects of the MRI images which result in lesion wise Dice scores of 0.52, 0.72 and 0.78 on unseen validation data and scores of 0.55, 0.70, 0.79 on final testing data for the "enhancing tumor", "tumor core" and "whole tumor" labels respectively. Visual comparisons further confirm the superiority of the ensemble method in accurate tumor region coverage. The results indicate that this advanced ensemble approach, building upon the unique strengths of individual models, offers promising prospects for enhanced diagnostic accuracy and effective treatment planning and monitoring for brain tumors in pediatric brains.


  • Open Access

    Automated Ensemble-Based Segmentation of Adult Brain Tumors: A Novel Approach Using the BraTS AFRICA Challenge Data

    by Chiranjeewee Prasad Koirala, Sovesh Mohapatra, Advait Gosai, Gottfried Schlaug

    Brain tumors, particularly glioblastoma, continue to challenge medical diagnostics and treatments globally. This paper explores the application of deep learning to multi-modality magnetic resonance imaging (MRI) data for enhanced brain tumor segmentation precision in the Sub-Saharan Africa patient population. We introduce an ensemble method that comprises eleven unique variations based on three core architectures: UNet3D, ONet3D, SphereNet3D and modified loss functions. The study emphasizes the need for both age- and population-based segmentation models, to fully account for the complexities in the brain. Our findings reveal that the ensemble approach, combining different architectures, outperforms single models, leading to improved evaluation metrics. Specifically, the results exhibit Dice scores of 0.82, 0.82, and 0.87 for enhancing tumor, tumor core, and whole tumor labels respectively. These results underline the potential of tailored deep learning techniques in precisely segmenting brain tumors and lay groundwork for future work to fine-tune models and assess performance across different brain regions.


  • Open Access

    Meta-Analysis of Transfer Learning for Segmentation of Brain Lesions

    by Sovesh Mohapatra, Advait Gosai, Anant Shinde, Aleksei Rutkovskii, Sirisha Nouduri, Gottfried Schlaug

    A major challenge in stroke research and stroke recovery predictions is the determination of a stroke lesion's extent and its impact on relevant brain systems. Manual segmentation of stroke lesions from 3D magnetic resonance (MR) imaging volumes, the current gold standard, is not only very time-consuming, but its accuracy highly depends on the operator's experience. As a result, there is a need for a fully automated segmentation method that can efficiently and objectively measure lesion extent and the impact of each lesion to predict impairment and recovery potential which might be beneficial for clinical, translational, and research settings. We have implemented and tested a fully automatic method for stroke lesion segmentation which was developed using eight different 2D-model architectures trained via transfer learning (TL) and mixed data approaches. Additionally, the final prediction was made using a novel ensemble method involving stacking and agreement window. Our novel method was evaluated in a novel in-house dataset containing 22 T1w brain MR images, which were challenging in various perspectives, but mostly because they included T1w MR images from the subacute (which typically less well defined T1 lesions) and chronic stroke phase (which typically means well defined T1-lesions). Cross-validation results indicate that our new method can efficiently and automatically segment lesions fast and with high accuracy compared to ground truth. In addition to segmentation, we provide lesion volume and weighted lesion load of relevant brain systems based on the lesions' overlap with a canonical structural motor system that stretches from the cortical motor region to the lowest end of the brain stem.

  • Open Access

    Multielectrode Network Stimulation (ME-NETS) demonstrated by concurrent tDCS and fMRI

    by David A. Ross, Anant B. Shinde, Karl D Lerud, Gottfried Schlaug

    Non-invasive transcranial direct current stimulation (tDCS) can modulate activity of targeted brain regions. Whether tDCS can reliably and repeatedly modulate intrinsic connectivity of entire brain networks is unclear. We used concurrent tDCS-MRI to investigate the effect of high dose anodal tDCS on resting state connectivity within the Arcuate Fasciculus (AF) network, which spans the temporal, parietal, and frontal lobes and is connected via a structural backbone, the Arcuate Fasciculus (AF) white matter tract. Effects of high-dose tDCS (4mA) delivered via a single electrode placed over one of the AF nodes (single electrode stimulation, SE-S) was compared to the same dose split between multiple electrodes placed over AF-network nodes (multielectrode network stimulation, ME-NETS). While both SE-S and ME-NETS significantly modulated connectivity between AF network nodes (increasing connectivity during stimulation epochs), ME-NETS had a significantly larger and more reliable effect than SE-S. Moreover, comparison with a control network, the Inferior Longitudinal Fasciculus (ILF) network suggested that the effect of ME-NETS on connectivity was specific to the targeted AF-network. This finding was further supported by the results of a seed-to-voxel analysis wherein we found ME-NETS primarily modulated connectivity between AF-network nodes. Finally, an exploratory analysis looking at dynamic connectivity using sliding window correlation found strong and immediate modulation of connectivity during three stimulation epochs within the same imaging session.

  • Open Access

    SAM vs BET: A Comparative Study for Brain Extraction and Segmentation of Magnetic Resonance Images using Deep Learning

    by Sovesh Mohapatra, Advait Gosai, Gottfried Schlaug

    Brain extraction is a critical preprocessing step in various neuroimaging studies, particularly enabling accurate separation of brain from non-brain tissue and segmentation of relevant within-brain tissue compartments and structures using Magnetic Resonance Imaging (MRI) data. FSL's Brain Extraction Tool (BET), although considered the current gold standard for automatic brain extraction, presents limitations and can lead to errors such as over-extraction in brains with lesions affecting the outer parts of the brain, inaccurate differentiation between brain tissue and surrounding meninges, and susceptibility to image quality issues. Recent advances in computer vision research have led to the development of the Segment Anything Model (SAM) by Meta AI, which has demonstrated remarkable potential in zero-shot segmentation of objects in real-world scenarios. In the current paper, we present a comparative analysis of brain extraction techniques comparing SAM with a widely used and current gold standard technique called BET on a variety of brain scans with varying image qualities, MR sequences, and brain lesions affecting different brain regions. We find that SAM outperforms BET based on average Dice coefficient, IoU and accuracy metrics, particularly in cases where image quality is compromised by signal inhomogeneities, non-isotropic voxel resolutions, or the presence of brain lesions that are located near (or involve) the outer regions of the brain and the meninges. In addition, SAM has also unsurpassed segmentation properties allowing a fine grain separation of different issue compartments and different brain structures. These results suggest that SAM has the potential to emerge as a more accurate, robust and versatile tool for a broad range of brain extraction and segmentation applications.


  • Open Access

    Identifying the engagement of a brain network during a targeted tDCS-fMRI experiment using a machine learning approach

    by Anant Shinde, Sovesh Mohapatra, Gottfried Schlaug

    Transcranial direct current stimulation (tDCS) can noninvasively modulate behavior, cognition, and physiologic brain functions depending on polarity and dose of stimulation as well as montage of electrodes. Concurrent tDCS-fMRI presents a novel way to explore the parameter space of non-invasive brain stimulation and to inform the experimenter as well as the participant if a targeted brain region or a network of spatially separate brain regions has been engaged and modulated. We compared a multi-electrode (ME) with a single electrode (SE) montage and both active conditions with a no-stimulation (NS) control condition to assess the engagement of a brain network and the ability of different electrode montages to modulate network activity. The multi-electrode montage targeted nodal regions of the right Arcuate Fasciculus Network (AFN) with anodal electrodes placed over the skull position of the posterior superior temporal/middle temporal gyrus (STG/MTG), supramarginal gyrus (SMG), posterior inferior frontal gyrus (IFG) and a return cathodal electrode over the left supraorbital region. In comparison, the single electrode montage used only one anodal electrode over a nodal brain region of the AFN, but varied the location between STG/MTG, SMG, and posterior IFG for different participants. Whole-brain rs-fMRI was obtained approximately every three seconds. The tDCS-stimulator was turned on at 3 minutes after the scanning started. A 4D rs-fMRI data set was converted to dynamic functional connectivity (DFC) matrices using a set of ROI pairs belonging to the AFN as well as other unrelated brain networks. In this study, we evaluated the performance of five algorithms to classify the DFC matrices from the three conditions (ME, SE, NS) into three different categories. The highest accuracy of 0.92 was obtained for the classification of the ME condition using the K Nearest Neighbor (KNN) algorithm. In other words, applying the classification algorithm allowed us to identify the engagement of the AFN and the ME condition was the best montage to achieve such an engagement. The top 5 ROI pairs that made a major contribution to the classification of participant’s rs-fMRI data were identified using model performance parameters; ROI pairs were mainly located within the right AFN. This proof-of-concept study using a classification algorithm approach can be expanded to create a near real-time feedback system at a participant level to detect the engagement and modulation of a brain network that spans multiple brain lobes.


  • Effects of melodic intonation therapy in patients with chronic nonfluent aphasia

    by Sarah Marchina, Andrea Norton, Gottfried Schlaug

    Patients with large left‐hemisphere lesions and post‐stroke aphasia often remain nonfluent. Melodic intonation therapy (MIT) may be an effective alternative to traditional speech therapy for facilitating recovery of fluency in those patients. In an open‐label, proof‐of‐concept study, 14 subjects with nonfluent aphasia with large left‐hemisphere lesions (171 ± 76 cc) underwent two speech/language assessments before, one at the midpoint, and two after the end of 75 sessions (1.5 h/session) of MIT. Functional MR imaging was done before and after therapy asking subjects to vocalize the same set of 10 bi‐syllabic words. We found significant improvements in speech output after a period of intensive MIT (75 sessions for a total of 112.5 h) compared to two pre‐therapy assessments. Therapy‐induced gains were maintained 4 weeks post‐treatment. Imaging changes were seen in a right‐hemisphere network that included the posterior superior temporal and inferior frontal gyri, inferior pre‐ and postcentral gyri, pre‐supplementary motor area, and supramarginal gyrus. Functional changes in the posterior right inferior frontal gyri significantly correlated with changes in a measure of fluency. Intense training of intonation‐supported auditory‐motor coupling and engaging feedforward/feedback control regions in the unaffected hemisphere improves speech‐motor functions in subjects with nonfluent aphasia and large left‐hemisphere lesions.