A deep learning model for a priori estimation of spatiotemporal regions for neuroimaging guided non-invasive brain stimulation

Rahul, Fnu; Dutta, Anirban; Subedi, Aseem; Makled, Basiel; Norfleet, Jack; Intes, Xavier; De, Survanu

doi:10.1016/j.brs.2021.10.323

Cited by 6 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In conclusion, the current study showed that topography-preserving CNN approach can substantially improve (>98%) EEG topography-based classification of FLS suturing with intracorporeal knot tying when compared to microstate based CSP analysis (~90%) in addition to providing insights into the salient brain areas that differentiate experts from novices. This is crucial since those salient brain areas may be facilitated with neuroimaging guided non-invasive brain stimulation (Rahul et al, 2021), (Walia, Kumar, et al, 2021) to improve FLS task performance and show causality. In the future, FGANet (Kwak et al, 2022) approach to online fNIRS-EEG fusion may be relevant in driving closed-loop adaptive FLS simulators in virtual reality such that task difficulty can be individualized according to the brain-based metrics of skill level to avoid mental stress response that can also be monitored with neuroimaging (Sikka et al, 2020).…”

Section: Discussionmentioning

confidence: 99%

EEG topography preserving convolutional neural network approach to assess skill levels during laparoscopic surgical training

Manabe

Rahul

et al. 2023

Preprint

View full text Add to dashboard Cite

The study objective was classification of skill level based on the topographical features of the electroencephalogram(EEG) during the most complex Fundamentals of Laparoscopic Surgery(FLS) task. We developed a novel microstate-based Common Spatial Pattern (CSP) analysis with linear discriminant analysis(LDA) classification that was compared with topography-preserving convolutional neural network(CNN) based approach to distinguish experts versus novices based on EEG. Ten expert surgeons and thirteen novice medical residents were recruited at the University at Buffalo. After informed consent, the subjects performed three trials of laparoscopic suturing and knot tying with rest periods in-between. 32-channel EEG during task performance was used to analyze spatial patterns of brain activity in 8 expert surgeons (2 dropouts due to data quality) and 13 novice medical residents. Besides conventional CSP analysis, microstate analysis was applied for preprocessing before CSP analysis for improved classification using LDA with 10-fold cross-validation. Also, a topography-preserving 3D CNN model (ESNet) was applied that considered both spatial and temporal information for the classification. Here, 5-fold cross-validation was repeated 10 times, and the results of each iteration of the testing data set were evaluated using indices, Accuracy, F1 score, Mathews Correlation Coefficient (MCC), sensitivity, and Specificity. Microstate-based CSP analysis found that while novices had primarily the frontal cortex involved for a maximum of spatial pattern vectors, experts had the hotspot of the spatial pattern vectors over the frontal and parietal cortices where the discriminating parietal brain region was supported by the Gradient-weighted Class Activation Mapping (Grad-CAM) of our 3D CNN-based model. Here, LDA with 10-fold cross-validation achieved more than 90% classification accuracy with microstate-based CSP, while conventional regularized CSP could reach around 80% classification accuracy. Then, 3D CNN provided the highest sensitivity of 99.30%, the highest specificity of 99.70%, the highest F1 score of 98.51%, and the highest MCC of 97.56%. Microstate-based CSP analysis improved the LDA classification (~90%) of experts versus novices based on EEG topography during a complex FLS task; however, combining the spatial and temporal information in the EEG topography preserving 3D CNN model significantly improved the classifier accuracy (>98%) in addition to providing mechanistic insights based on Grad-CAM analysis.

show abstract

Section: Discussionmentioning

confidence: 99%

EEG topography preserving convolutional neural network approach to assess skill levels during laparoscopic surgical training

Manabe

Rahul

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…However, in the last few years, various eXplainable AI (XAI) tools such as class activation maps, 106 Grad-CAMS, 107 and saliency maps 108 have been proposed to impart understandability and comprehensibility. 109 Such tools can, for instance, provide visual map(s) that highlight the main data features leveraged for the model decision. Such a map can then correlate the extracted features with known neurophysiology, specific application characteristics (for instance, hand switching during surgery), and/or correlate with other biomarkers, such as videos, gaze measurements, and motion tracking devices.…”

Section: Discussion and Future Outlookmentioning

confidence: 99%

“…In other words, the extracted high-level features from the data inputs that lead to high task performances during training and validation are not accessible and hence, cannot be interpreted. However, in the last few years, various eXplainable AI (XAI) tools such as class activation maps, 106 Grad-CAMS, 107 and saliency maps 108 have been proposed to impart understandability and comprehensibility 109 . Such tools can, for instance, provide visual map(s) that highlight the main data features leveraged for the model decision.…”

Section: Discussion and Future Outlookmentioning

confidence: 99%

Deep learning in fNIRS: a review

Eastmond

Subedi

et al. 2022

Neurophoton.

Self Cite

View full text Add to dashboard Cite

Significance: Optical neuroimaging has become a well-established clinical and research tool to monitor cortical activations in the human brain. It is notable that outcomes of functional nearinfrared spectroscopy (fNIRS) studies depend heavily on the data processing pipeline and classification model employed. Recently, deep learning (DL) methodologies have demonstrated fast and accurate performances in data processing and classification tasks across many biomedical fields.Aim: We aim to review the emerging DL applications in fNIRS studies.Approach: We first introduce some of the commonly used DL techniques. Then, the review summarizes current DL work in some of the most active areas of this field, including braincomputer interface, neuro-impairment diagnosis, and neuroscience discovery.Results: Of the 63 papers considered in this review, 32 report a comparative study of DL techniques to traditional machine learning techniques where 26 have been shown outperforming the latter in terms of the classification accuracy. In addition, eight studies also utilize DL to reduce the amount of preprocessing typically done with fNIRS data or increase the amount of data via data augmentation. Conclusions:The application of DL techniques to fNIRS studies has shown to mitigate many of the hurdles present in fNIRS studies such as lengthy data preprocessing or small sample sizes while achieving comparable or improved classification accuracy.

show abstract

“…Here, a distinction is necessary between sensory prediction error [69], which is postulated to be important at the initial perceptual-cognitive stage of skill learning [70], and task error which is postulated to be important in the later stages for strategy learning [9] to achieve expert performance. Then, the CNN with Grad-CAM approach provided insights into the main brain areas that differentiated experts from novices, which may be facilitated with neuroimaging-guided non-invasive brain stimulation- [58,71]. For example, noninvasive cerebellar stimulation may facilitate sensory prediction error and/or non-invasive frontal stimulation may facilitate task error feedback to improve FLS task performance and demonstrate brain-behaviour causality [72].…”

Section: Conclusion and Future Researchmentioning

confidence: 99%

Distinguishing Laparoscopic Surgery Experts from Novices Using EEG Topographic Features

Manabe,

Rahul,

et al. 2023

Brain Sciences

View full text Add to dashboard Cite

The study aimed to differentiate experts from novices in laparoscopic surgery tasks using electroencephalogram (EEG) topographic features. A microstate-based common spatial pattern (CSP) analysis with linear discriminant analysis (LDA) was compared to a topography-preserving convolutional neural network (CNN) approach. Expert surgeons (N = 10) and novice medical residents (N = 13) performed laparoscopic suturing tasks, and EEG data from 8 experts and 13 novices were analysed. Microstate-based CSP with LDA revealed distinct spatial patterns in the frontal and parietal cortices for experts, while novices showed frontal cortex involvement. The 3D CNN model (ESNet) demonstrated a superior classification performance (accuracy > 98%, sensitivity 99.30%, specificity 99.70%, F1 score 98.51%, MCC 97.56%) compared to the microstate based CSP analysis with LDA (accuracy ~90%). Combining spatial and temporal information in the 3D CNN model enhanced classifier accuracy and highlighted the importance of the parietal–temporal–occipital association region in differentiating experts and novices.

show abstract

A deep learning model for a priori estimation of spatiotemporal regions for neuroimaging guided non-invasive brain stimulation

Cited by 6 publications

References 0 publications

EEG topography preserving convolutional neural network approach to assess skill levels during laparoscopic surgical training

EEG topography preserving convolutional neural network approach to assess skill levels during laparoscopic surgical training

Deep learning in fNIRS: a review

Distinguishing Laparoscopic Surgery Experts from Novices Using EEG Topographic Features

Contact Info

Product

Resources

About