Eun-Gyoung Yi

Transcranial temporal interference (TI) stimulation offers non-invasive modulation of deep brain regions with limited neocortical activation. Achieving focal TI stimulation requires individualized optimization of the stimulation parameters, including electrode configurations and injection currents. However, conventional exhaustive search (ES) approach is computationally expensive, hindering the clinical applicability of subject-specific parameter optimization. We propose a target-specific restricted exhaustive search (RES) strategy that substantially reduces the computational burden while preserving reliability of ES-based optimization. ES was conducted to identify the optimal two-pair TI stimulation parameters for three deep brain targets (the nucleus accumbens, hippocampal head, and caudate body) using 40 individual finite element head models. Target-specific restricted candidate electrode subsets were constructed based on the electrode selection patterns observed across multiple subjects. RES was then performed by constraining the search space only for these selected subsets. A 4-fold cross-validation approach was employed to quantify the average changes in the objective function and computational time, which were then compared with those of the conventional ES approach. A parametric analysis was also conducted to identify the size of the minimal subset that maintained a robust performance for each target. RES maintained an optimization accuracy comparable to that of conventional ES across all three targets, while reducing the computation time approximately 30- to 100-fold, enabling optimization within minutes or seconds. Specifically, targeting the nucleus accumbens allowed for the most extensive search space reduction without compromising stimulation efficacy. This is the first study to identify target-specific electrode selection patterns across individuals to optimize TI stimulation. The RES strategy leverages these patterns to preserve the deterministic nature of ES while reducing the optimization time from hours to minutes, thereby facilitating the clinical application of personalized TI stimulation.

The advancement of artificial intelligence (AI) tools utilizing electroencephalography (EEG) for diagnosing major depressive disorder (MDD) has shown significant progress. However, the practical implementation of these tools is often impeded by the large amount of EEG data required for training AI models and the lack of explanations for the MDD diagnoses. This study aims to develop an interpretable deep‐learning‐based computer‐aided diagnostic system for diagnosing male MDD patients using explainable AI (XAI) algorithms. The CAD system was designed to facilitate the diagnostic process by using a reduced number of EEG channels and data length while enhancing understanding of the neurophysiological characteristics of male MDD. Resting‐state EEG data were collected from 40 male MDD patients (20–63 years) and 41 gender‐matched healthy controls (HCs, 19–61 years). A shallow convolutional neural network (CNN; Shallow ConvNet) model was utilized to distinguish between MDD patients and HCs. Relevance scores were extracted by the layer‐wise relevance propagation (LRP) method, integrated with the Shallow ConvNet, to interpret the outcomes of the deep‐learning‐based CAD system. Additionally, changes in diagnostic performance were assessed by progressively reducing the number of channels using an LRP‐based channel selection method, as well as EEG data length. Our XAI‐based CAD system showed a high diagnostic performance of 100% when using the whole 62 channels with 180‐s EEG data. A relatively high diagnostic performance over 90% was retained with only five channels with 60‐s EEG data. Neurophysiologically meaningful brain areas, such as fronto‐central, centro‐parietal, and occipital areas, also revealed significant differences in relevance scores extracted by the LRP‐method between the two groups. This study successfully developed a high performance and practical XAI‐based CAD system for male MDD patients. Our developed CAD system not only achieves high diagnostic accuracy but also provides meaningful neurophysiological biomarkers for male MDD patients.