A Multi-scale Spatial and Temporal Attention Network on Dynamic Connectivity to Localize the Eloquent Cortex in Brain Tumor Patients

Nandakumar, Naresh; Manzoor, Komal; Agarwal, Shruti; Pillai, Jay J.; Gujar, Sachin K.; Sair, Haris I.; Venkataraman, Archana

doi:10.1007/978-3-030-78191-0_19

Cited by 4 publications

(3 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, acquiring and integrating this data into DeepEZ remains a crucial direction of future work. Finally, we emphasize that our deep learning framework can be adapted to other applications, such as preoperative mapping of the eloquent cortex [ 54 ]–[ 56 ].…”

Section: Discussionmentioning

confidence: 99%

“…Since the GCN layers are designed to operate upon a whole-brain connectivity matrix, traditional data augmentation techniques would not solve our class imbalance problem. Following the work of [ 55 ], [ 56 ], we train our model with a modified Risk-Sensitive Cross-Entropy loss function [ 74 ], which is designed to handle a class membership imbalance. Formally, let δ i be the risk associated with class i .…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

DeepEZ: A Graph Convolutional Network for Automated Epileptogenic Zone Localization From Resting-State fMRI Connectivity

Nandakumar

Hsu

Ahmed

et al. 2023

IEEE Trans. Biomed. Eng.

Self Cite

View full text Add to dashboard Cite

Objective: Epileptogenic zone (EZ) localization is a crucial step during diagnostic work up and therapeutic planning in medication refractory epilepsy. In this paper, we present the first deep learning approach to localize the EZ based on resting-state fMRI (rs-fMRI) data. Methods: Our network, called DeepEZ , uses a cascade of graph convolutions that emphasize signal propagation along expected anatomical pathways. We also integrate domain-specific information, such as an asymmetry term on the predicted EZ and a learned subject-specific bias to mitigate environmental confounds. Results: We validate DeepEZ on rs-fMRI collected from 14 patients with focal epilepsy at the University of Wisconsin Madison. Using cross validation, we demonstrate that DeepEZ achieves consistently high EZ localization performance (Accuracy: 0.88 ± 0.03; AUC: 0.73 ± 0.03) that far outstripped any of the baseline methods. This performance is notable given the variability in EZ locations and scanner type across the cohort. Conclusion: Our results highlight the promise of using DeepEZ as an accurate and noninvasive therapeutic planning tool for medication refractory epilepsy. Significance: While prior work in EZ localization focused on identifying localized aberrant signatures, there is growing evidence that epileptic seizures affect inter-regional connectivity in the brain. DeepEZ allows clinicians to harness this information from noninvasive imaging that can easily be integrated into the existing clinical workflow.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

DeepEZ: A Graph Convolutional Network for Automated Epileptogenic Zone Localization From Resting-State fMRI Connectivity

Nandakumar

Hsu

Ahmed

et al. 2023

IEEE Trans. Biomed. Eng.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Branch attention [33] formulates an attention mask across different branches, which can then be used to identify the salient branches [15]. Temporal attention [34] adjusts an attention mask over the temporal dimension, which can then be harnessed to distinguish vital frames of the input data. By employing this attention mechanism, the model is enabled to concentrate on the most salient temporal segments while disregarding irrelevant ones.…”

Section: Attention-based Deep Learning For Brain Tumors Diagnosismentioning

confidence: 99%

Attention-based Deep Learning Approaches in Brain Tumor Image Analysis: A Mini Review

Saraei,

Liu

2023

Front Health Inform

View full text Add to dashboard Cite

Introduction: Accurate diagnosis is crucial for brain tumors, given their low survival rates and high treatment costs. However, traditional methods relying on manual interpretation of medical images are time-consuming and prone to errors. Attention-based deep learning, utilizing deep neural networks to selectively focus on relevant features, offers a promising solution.Material and Methods: This paper presents an overview of recent advancements in attention-based deep learning for brain tumor image analysis. While the reviewed models have demonstrated respectable performance across different datasets, they have yet to achieve state-of-the-art results.Results: Advanced techniques, including super-resolution image reconstruction, multi-swin-transformer blocks, and spatial group-wise enhanced attention blocks, have shown improved segmentation network performance. Integration of graph attention, swin-transformer, and gradient awareness minimization with positional attention convolution blocks, self-attention blocks, and intermittent fully connected layers has considerably enhanced the efficiency of classification networks.Conclusion: While attention-based deep learning has shown improvements in performance, challenges persist. These challenges include the requirement for large datasets, resource limitations, accurate segmentation of irregularly shaped tumors, and high computational demands. Future studies should address these challenges to further enhance the efficiency of brain tumor diagnoses in real-world settings.

show abstract

A Lesion-Aware Edge-Based Graph Neural Network for Predicting Language Ability in Patients with Post-stroke Aphasia

Chen,

Varkanitsa,

Ishwar

et al. 2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

A Multi-scale Spatial and Temporal Attention Network on Dynamic Connectivity to Localize the Eloquent Cortex in Brain Tumor Patients

Cited by 4 publications

References 25 publications

DeepEZ: A Graph Convolutional Network for Automated Epileptogenic Zone Localization From Resting-State fMRI Connectivity

DeepEZ: A Graph Convolutional Network for Automated Epileptogenic Zone Localization From Resting-State fMRI Connectivity

Attention-based Deep Learning Approaches in Brain Tumor Image Analysis: A Mini Review

A Lesion-Aware Edge-Based Graph Neural Network for Predicting Language Ability in Patients with Post-stroke Aphasia

Contact Info

Product

Resources

About