Abstract
Resting-state functional MRI (RS-fMRI) enables the mapping of function within the brain and is emerging as an efficient tool for the presurgical evaluation of eloquent cortex. Models capable of reliable and precise mapping of resting-state networks (RSNs) with a reduced scanning time would lead to improved patient comfort while reducing the cost per scan. The aims of the present study were to develop a deep 3D convolutional neural network (3DCNN) capable of voxel-wise mapping of language (LAN) and motor (MOT) RSNs with minimal quantities of RS-fMRI data. Imaging data were gathered from multiple ongoing studies at Washington University School of Medicine and other thoroughly characterized, publicly available data sets. All study participants (n = 2252 healthy adults) were cognitively screened and completed structural neuroimaging and RS-fMRI. Random permutations of RS-fMRI regions of interest were used to train a 3DCNN. After training, model inferences were compared using varying amounts of RS-fMRI data from the control data set as well as 5 patients with glioblastoma multiforme. The trained model achieved 96% out-of-sample validation accuracy on data encompassing a large age range collected on multiple scanner types and varying sequence parameters. Testing on out-of-sample control data showed 97.9% similarity between results generated using either 50 or 200 RS-fMRI time points, corresponding to approximately 2.5 and 10 minutes, respectively (96.9% LAN, 96.3% MOT true-positive rate). In evaluating data from patients with brain tumors, the 3DCNN was able to accurately map LAN and MOT networks despite structural and functional alterations. Functional maps produced by the 3DCNN can inform surgical planning in patients with brain tumors in a time-efficient manner. The authors present a highly efficient method for presurgical functional mapping and thus improved functional preservation in patients with brain tumors.
Overview
- The study aimed to develop a deep 3D convolutional neural network (3DCNN) capable of voxel-wise mapping of language (LAN) and motor (MOT) resting-state networks (RSNs) with minimal quantities of resting-state functional MRI (RS-fMRI) data. The study used imaging data from multiple ongoing studies at Washington University School of Medicine and other thoroughly characterized, publicly available data sets. All study participants were cognitively screened and completed structural neuroimaging and RS-fMRI. Random permutations of RS-fMRI regions of interest were used to train a 3DCNN. After training, model inferences were compared using varying amounts of RS-fMRI data from the control data set as well as 5 patients with glioblastoma multiforme. The trained model achieved 96% out-of-sample validation accuracy on data encompassing a large age range collected on multiple scanner types and varying sequence parameters. Testing on out-of-sample control data showed 97.9% similarity between results generated using either 50 or 200 RS-fMRI time points, corresponding to approximately 2.5 and 10 minutes, respectively (96.9% LAN, 96.3% MOT true-positive rate). The study's primary objective was to develop a highly efficient method for presurgical functional mapping and thus improved functional preservation in patients with brain tumors.
Comparative Analysis & Findings
- The study compared the outcomes observed under different experimental conditions or interventions detailed in the study. The trained 3DCNN achieved 96% out-of-sample validation accuracy on data encompassing a large age range collected on multiple scanner types and varying sequence parameters. Testing on out-of-sample control data showed 97.9% similarity between results generated using either 50 or 200 RS-fMRI time points, corresponding to approximately 2.5 and 10 minutes, respectively (96.9% LAN, 96.3% MOT true-positive rate). The study identified significant differences or similarities in the results between these conditions. The trained model was able to accurately map LAN and MOT networks despite structural and functional alterations in patients with brain tumors. The key findings of the study were that the 3DCNN achieved high accuracy in mapping LAN and MOT networks with minimal quantities of RS-fMRI data and that it can inform surgical planning in patients with brain tumors in a time-efficient manner.
Implications and Future Directions
- The study's findings have significant implications for the field of research or clinical practice. The highly efficient method for presurgical functional mapping developed in the study can improve functional preservation in patients with brain tumors. The study identified limitations that need to be addressed in future research, such as the need for more data to validate the model's performance in different populations and the need to evaluate the model's performance in other types of brain tumors. Possible future research directions that could build on the results of the study, explore unresolved questions, or utilize novel approaches include developing models for other RSNs, evaluating the model's performance in other populations, and exploring the use of the model in clinical decision-making.