Our Paper on Neuropsychiatric Disease Classification Accepted to MedIA!

Title: Neuropsychiatric Disease Classification Using Functional Connectomics – Results of the Connectomics in NeuroImaging Transfer Learning Challenge

Authors: M.D. Schirmer, A. Venkataraman, I. Rekik, M. Kim, S. Mostofsky, M.B. Nebel, K. Rosch, K. Seymour, D. Crocetti, H. Irzan, M. Hutel, S. Ourselin, N. Marlow, A. Melbourne, E. Levchenko, S. Zhou, M. Kunda, H. Lu, N.C. Dvornek, J. Zhuang, G. Pinto, S. Samal, J.L. Bernal-Rusiel, R. Pienaar, A. Wern Chung

Our paper on Deep Learning for Seizure Detection is Accepted to Biomedical Signal Processing and Control

Title: Automated Inter-Patient Seizure Detection Using Multichannel Convolutional and Recurrent Neural Networks

Abstract: We present an end-to-end deep learning model that can automatically detect epileptic seizures in multichannel electroencephalography (EEG) recordings. Our model combines a Convolutional Neural Network (CNN) and a Bidirectional Long Short-Term Memory (BLSTM) network to eciently mine information from the EEG data using a small number of trainable parameters. Specifically, the CNN learns a latent encoding for each one second window of raw multichannel EEG data. In conjunction, the BLSTM learns the temporal evolution of seizure presentations given the CNN encodings. The combination of these architectures allows our model to capture both the short time scale EEG features indicative of seizure activity as well as the long term correlations in seizure presentations. Unlike most prior work in seizure detection, we mimic an in-patient monitoring setting through a leave-one-patient-out cross validation procedure, attaining an average seizure detection sensitivity of 0.91 across all patients. This strategy verifies that our model can generalize to new patients. We demonstrate that our CNN-BLSTM outperforms both conventional feature extraction methods and state-of-the-art deep learning approaches that rely on larger and more complex network architectures.