Title: Automated Eloquent Cortex Localization in Brain Tumor Patients Using Multi-task Graph Neural Networks
Abstract: Localizing the eloquent cortex is a crucial part of presurgical planning. While invasive mapping is the gold standard, there is increasing interest in using noninvasive fMRI to shorten and improve the process. However, many surgical patients cannot adequately perform task-based fMRI protocols. Resting-state fMRI has emerged as an alternative modality, but automated eloquent cortex localization remains an open challenge. In this paper, we develop a novel deep learning architecture to simultaneously identify language and primary motor cortex from rs-fMRI connectivity. Our approach uses the representational power of convolutional neural networks alongside the generalization power of multi-task learning to find a shared representation between the eloquent subnetworks. We validate our method on data from the publicly available Human Connectome Project and on a brain tumor dataset acquired at the Johns Hopkins Hospital. We compare our method against feature-based machine learning approaches and a fully-connected deep learning model that does not account for the shared network organization of the data. Our model achieves significantly better performance than competing baselines. We also assess the generalizability and robustness of our method. Our results clearly demonstrate the advantages of our graph convolution architecture combined with multi-task learning and highlight the promise of using rs-fMRI as a presurgical mapping tool.
You do not have permission to view this content.
Congrats to Danielle and Yu-Chung!
Danielle’s Paper: Cross-Site Epileptic Seizure Detection Using Convolutional Neural Networks
Yu-Chung’s Paper: Predicting Acute Kidney Injury via Interpretable Ensemble Learning and Attention Weighted Convoutional–Recurrent Neural Networks
Congrats Niharika and Ravi!
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
The paper will be featured in a special oral session of the Image Processing conference. Congrats, Sayan!
Title: G-MIND: An End-to-End Multimodal Imaging-Genetics Framework for Biomarker Identification and Disease Classification
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.