SepaConvNet for Localizing the Subthalamic Nucleus Using One Second Micro-electrode Recordings.

Micro-electrode recording (MER) is a powerful way of localizing target structures during neurosurgical procedures such as the implantation of deep brain stimulation electrodes, which is a common treatment for Parkinson's disease and other neurological disorders. While Micro-electrode Recording (MER) provides adjunctive information to guidance assisted by pre-operative imaging, it is not unanimously used in the operating room. The lack of standard use of MER may be in part due to its long duration, which can lead to complications during the operation, or due to high degree of expertise required for their interpretation. Over the past decade, various approaches addressing automating MER analysis for target localization have been proposed, which have mainly focused on feature engineering. While the accuracies obtained are acceptable in certain configurations, one issue with handcrafted MER features is that they do not necessarily capture more subtle differences in MER that could be detected auditorily by an expert neurophysiologist. In this paper, we propose and validate a deep learning-based pipeline for subthalamic nucleus (STN) localization with micro-electrode recordings motivated by the human auditory system. Our proposed Convolutional Neural Network (CNN), referred as SepaConvNet, shows improved accuracy over two comparative networks for locating the STN from one second MER samples.

Unsupervised Domain Adaptation With Optimal Transport in Multi-Site Segmentation of Multiple Sclerosis Lesions From MRI Data.

Automatic segmentation of Multiple Sclerosis (MS) lesions from Magnetic Resonance Imaging (MRI) images is essential for clinical assessment and treatment planning of MS. Recent years have seen an increasing use of Convolutional Neural Networks (CNNs) for this task. Although these methods provide accurate segmentation, their applicability in clinical settings remains limited due to a reproducibility issue across different image domains. MS images can have highly variable characteristics across patients, MRI scanners and imaging protocols; retraining a supervised model with data from each new domain is not a feasible solution because it requires manual annotation from expert radiologists. In this work, we explore an unsupervised solution to the problem of domain shift. We present a framework, Seg-JDOT, which adapts a deep model so that samples from a source domain and samples from a target domain sharing similar representations will be similarly segmented. We evaluated the framework on a multi-site dataset, MICCAI 2016, and showed that the adaptation toward a target site can bring remarkable improvements in a model performance over standard training.