Connectivity-Optimized Individualized Localization (COIL)

本项目的总体目标是开发一种连接引导的工具，通过经颅磁刺激（TMS）靶向背外侧前额皮质（DLPFC）。为了广泛的适用性，底层算法需要鲁棒地提供个性化优化目标，以实现高精度的个性化刺激。为了平衡个体精确性和稳健性，来自规范数据集和抑郁症患者数据的大规模信息将用于定义DLPFC的关键连接概况。我们将把机器学习算法应用到这些配置文件中，以识别单个主题中该区域内的最佳热点。将该算法实现为一个用户友好的软件包将产生一个有效的工具，用于经颅磁刺激治疗难治性抑郁症。

The overarching goal of this project is to develop a tool for connectivity- guided targeting the dorsolateral prefrontal cortex (DLPFC) with transcranial magnetic stimulation (TMS). For broad applicability, the underlying algorithm needs to robustly provide individually optimized targets for high-precision personalized stimulation. To balance individual precision and robustness, large-scale information from normative datasets and data from patients with depression will serve to define the critical connectivity profiles of the DLPFC. We will apply machine-learning algorithms to these profiles to identify the optimal hotspot within this region in individual subjects. Implementation of the algorithm into a user-friendly software package will yield an impactful tool for TMS therapy of treatment-resistant depression.