Towards a Pseudo-Labeling Workflow for Celltype-Classification from Explanted Brain Slice Recordings

Current Directions in Biomedical Engineering, vol. 12, pp. 231–234

Abstract

Abstract This paper proposes an unsupervised workflow to pseudo-label extracellular spikes from human brain slice MEA recordings into two putative cell types: pyramidal cells and interneurons. Here, the raw data from the data acquisition system is used and processed. The pipeline for preprocessing includes bandpass filtering, threshold-based spike detection, frame alignment and normalization. In the ML workflow, dimensionality reduction (PCA, t-SNE, UMAP), clustering (GMM, k-means). To achieve an online system, template matching and OSort under varying curation strictness is also considered. All pipelines are evaluated by different cluster quality with within-cluster Pearson correlation, Silhouette score, and Calinski-Harabasz index. Applying stricter curation improves separation at some cost to inclusivity.

Authors 5

1. Cora Jostock

   University of Duisburg-Essen

   Affiliation as printed

   University of Duisburg-Essen, Intelligent Embedded Systems Lab, Duisburg , Germany

2. Jonas Ort Aachen Department of Neurosurgery

   RWTH Aachen University

   Affiliation as printed

   RWTH University Hospital, Department of Neurosurgery, Aachen , Germany

3. Henner Koch Aachen Department of Epileptology

   RWTH Aachen University

   Affiliation as printed

   RWTH University Hospital, Department of Epileptology, Aachen , Germany

4. Gregor Schiele

   University of Duisburg-Essen

   Affiliation as printed

   University of Duisburg-Essen, Intelligent Embedded Systems Lab, Duisburg , Germany

5. Andreas Erbslöh

   University of Duisburg-Essen

   Affiliation as printed

   University of Duisburg-Essen, Intelligent Embedded Systems Lab, Duisburg , Germany