1
|
Tang Z, Mahmoodi S, Meng D, Darekar A, Vollmer B. Rule-based deep learning method for prognosis of neonatal hypoxic-ischemic encephalopathy by using susceptibility weighted image analysis. MAGMA (NEW YORK, N.Y.) 2024; 37:227-239. [PMID: 38252196 DOI: 10.1007/s10334-023-01139-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/09/2023] [Revised: 12/06/2023] [Accepted: 12/11/2023] [Indexed: 01/23/2024]
Abstract
OBJECTIVE Susceptibility weighted imaging (SWI) of neonatal hypoxic-ischemic brain injury can provide assistance in the prognosis of neonatal hypoxic-ischemic encephalopathy (HIE). We propose a convolutional neural network model to classify SWI images with HIE. MATERIALS AND METHODS Due to the lack of a large dataset, transfer learning method with fine-tuning a pre-trained ResNet 50 is introduced. We randomly select 11 datasets from patients with normal neurology outcomes (n = 31) and patients with abnormal neurology outcomes (n = 11) at 24 months of age to avoid bias in classification due to any imbalance in the data. RESULTS We develop a rule-based system to improve the classification performance, with an accuracy of 0.93 ± 0.09. We also compute heatmaps produced by the Grad-CAM technique to analyze which areas of SWI images contributed more to the classification patients with abnormal neurology outcome. CONCLUSION Such regions that are important in the classification accuracy can interpret the relationship between the brain regions affected by hypoxic-ischemic and neurodevelopmental outcomes of infants with HIE at the age of 2 years.
Collapse
Affiliation(s)
- Zhen Tang
- School of Computer Science and Technology, AnHui University of Technology, Maxiang Street, Maanshan, 243032, Anhui, China.
| | - Sasan Mahmoodi
- School of Electronics and Computer Science, University of Southampton, Southampton, SO17 1BJ, UK
| | - Di Meng
- School of Computer Science and Technology, AnHui University of Technology, Maxiang Street, Maanshan, 243032, Anhui, China
| | - Angela Darekar
- Department of Medical Physics, University Hospital Southampton NHS Foundation Trust, Southampton, SO16 6YD, UK
| | - Brigitte Vollmer
- Clinical Neurosciences and Clinical and Experimental Sciences, Faculty of Medicine, University of Southampton, Southampton, SO17 1BJ, UK
| |
Collapse
|
2
|
O'Toole JM, Mathieson SR, Raurale SA, Magarelli F, Marnane WP, Lightbody G, Boylan GB. Neonatal EEG graded for severity of background abnormalities in hypoxic-ischaemic encephalopathy. Sci Data 2023; 10:129. [PMID: 36899033 PMCID: PMC10006081 DOI: 10.1038/s41597-023-02002-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/07/2022] [Accepted: 02/03/2023] [Indexed: 03/12/2023] Open
Abstract
This report describes a set of neonatal electroencephalogram (EEG) recordings graded according to the severity of abnormalities in the background pattern. The dataset consists of 169 hours of multichannel EEG from 53 neonates recorded in a neonatal intensive care unit. All neonates received a diagnosis of hypoxic-ischaemic encephalopathy (HIE), the most common cause of brain injury in full term infants. For each neonate, multiple 1-hour epochs of good quality EEG were selected and then graded for background abnormalities. The grading system assesses EEG attributes such as amplitude, continuity, sleep-wake cycling, symmetry and synchrony, and abnormal waveforms. Background severity was then categorised into 4 grades: normal or mildly abnormal EEG, moderately abnormal EEG, majorly abnormal EEG, and inactive EEG. The data can be used as a reference set of multi-channel EEG for neonates with HIE, for EEG training purposes, or for developing and evaluating automated grading algorithms.
Collapse
Affiliation(s)
- John M O'Toole
- INFANT Research Centre, University College Cork, Cork, Ireland.
- Department of Paediatrics and Child Health, University College Cork, Cork, Ireland.
| | - Sean R Mathieson
- INFANT Research Centre, University College Cork, Cork, Ireland
- Department of Paediatrics and Child Health, University College Cork, Cork, Ireland
| | - Sumit A Raurale
- INFANT Research Centre, University College Cork, Cork, Ireland
- Department of Paediatrics and Child Health, University College Cork, Cork, Ireland
| | - Fabio Magarelli
- INFANT Research Centre, University College Cork, Cork, Ireland
- Department of Paediatrics and Child Health, University College Cork, Cork, Ireland
| | - William P Marnane
- INFANT Research Centre, University College Cork, Cork, Ireland
- Department of Electronic and Electrical Engineering, University College Cork, Cork, Ireland
| | - Gordon Lightbody
- INFANT Research Centre, University College Cork, Cork, Ireland
- Department of Electronic and Electrical Engineering, University College Cork, Cork, Ireland
| | - Geraldine B Boylan
- INFANT Research Centre, University College Cork, Cork, Ireland
- Department of Paediatrics and Child Health, University College Cork, Cork, Ireland
| |
Collapse
|
3
|
Montazeri S, Pinchefsky E, Tse I, Marchi V, Kohonen J, Kauppila M, Airaksinen M, Tapani K, Nevalainen P, Hahn C, Tam EWY, Stevenson NJ, Vanhatalo S. Building an Open Source Classifier for the Neonatal EEG Background: A Systematic Feature-Based Approach From Expert Scoring to Clinical Visualization. Front Hum Neurosci 2021; 15:675154. [PMID: 34135744 PMCID: PMC8200402 DOI: 10.3389/fnhum.2021.675154] [Citation(s) in RCA: 7] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/03/2021] [Accepted: 04/30/2021] [Indexed: 11/13/2022] Open
Abstract
Neonatal brain monitoring in the neonatal intensive care units (NICU) requires a continuous review of the spontaneous cortical activity, i.e., the electroencephalograph (EEG) background activity. This needs development of bedside methods for an automated assessment of the EEG background activity. In this paper, we present development of the key components of a neonatal EEG background classifier, starting from the visual background scoring to classifier design, and finally to possible bedside visualization of the classifier results. A dataset with 13,200 5-minute EEG epochs (8-16 channels) from 27 infants with birth asphyxia was used for classifier training after scoring by two independent experts. We tested three classifier designs based on 98 computational features, and their performance was assessed with respect to scoring system, pre- and post-processing of labels and outputs, choice of channels, and visualization in monitor displays. The optimal solution achieved an overall classification accuracy of 97% with a range across subjects of 81-100%. We identified a set of 23 features that make the classifier highly robust to the choice of channels and missing data due to artefact rejection. Our results showed that an automated bedside classifier of EEG background is achievable, and we publish the full classifier algorithm to allow further clinical replication and validation studies.
Collapse
Affiliation(s)
- Saeed Montazeri
- BABA Center, Pediatric Research Centre, Department of Clinical Neurophysiology, Children’s Hospital and HUS Diagnostic Center, Helsinki University Hospital and University of Helsinki, Helsinki, Finland
| | - Elana Pinchefsky
- Division of Neurology, Department of Paediatrics, Sainte-Justine University Hospital Centre, University of Montreal, Montreal, QC, Canada
| | - Ilse Tse
- BABA Center, Pediatric Research Centre, Department of Clinical Neurophysiology, Children’s Hospital and HUS Diagnostic Center, Helsinki University Hospital and University of Helsinki, Helsinki, Finland
| | - Viviana Marchi
- BABA Center, Pediatric Research Centre, Department of Clinical Neurophysiology, Children’s Hospital and HUS Diagnostic Center, Helsinki University Hospital and University of Helsinki, Helsinki, Finland
- Department of Developmental Neuroscience, Stella Maris Scientific Institute, IRCCS Fondazione Stella Maris Foundation, Pisa, Italy
| | - Jukka Kohonen
- Department of Computer Science, Aalto University, Espoo, Finland
| | - Minna Kauppila
- BABA Center, Pediatric Research Centre, Department of Clinical Neurophysiology, Children’s Hospital and HUS Diagnostic Center, Helsinki University Hospital and University of Helsinki, Helsinki, Finland
| | - Manu Airaksinen
- BABA Center, Pediatric Research Centre, Department of Clinical Neurophysiology, Children’s Hospital and HUS Diagnostic Center, Helsinki University Hospital and University of Helsinki, Helsinki, Finland
- Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland
| | - Karoliina Tapani
- BABA Center, Pediatric Research Centre, Department of Clinical Neurophysiology, Children’s Hospital and HUS Diagnostic Center, Helsinki University Hospital and University of Helsinki, Helsinki, Finland
| | - Päivi Nevalainen
- BABA Center, Pediatric Research Centre, Department of Clinical Neurophysiology, Children’s Hospital and HUS Diagnostic Center, Helsinki University Hospital and University of Helsinki, Helsinki, Finland
| | - Cecil Hahn
- Department of Paediatrics (Neurology), The Hospital for Sick Children and University of Toronto, Toronto, ON, Canada
| | - Emily W. Y. Tam
- Department of Paediatrics (Neurology), The Hospital for Sick Children and University of Toronto, Toronto, ON, Canada
| | - Nathan J. Stevenson
- Brain Modelling Group, QIMR Berghofer Medical Research Institute, Brisbane, QLD, Australia
| | - Sampsa Vanhatalo
- BABA Center, Pediatric Research Centre, Department of Clinical Neurophysiology, Children’s Hospital and HUS Diagnostic Center, Helsinki University Hospital and University of Helsinki, Helsinki, Finland
- Neuroscience Center, Helsinki Institute of Life Science, University of Helsinki, Helsinki, Finland
| |
Collapse
|
4
|
Raurale SA, Boylan GB, Mathieson S, Marnane WP, Lightbody G, O'Toole JM. Grading hypoxic-ischemic encephalopathy in neonatal EEG with convolutional neural networks and quadratic time-frequency distributions. J Neural Eng 2021; 18. [PMID: 33618337 PMCID: PMC8208632 DOI: 10.1088/1741-2552/abe8ae] [Citation(s) in RCA: 13] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/12/2020] [Accepted: 02/22/2021] [Indexed: 12/12/2022]
Abstract
OBJECTIVE To develop an automated system to classify the severity of hypoxic-ischaemic encephalopathy injury (HIE) in neonates from the background electroencephalogram (EEG). METHOD By combining a quadratic time{frequency distribution (TFD) with a convolutional neural network, we develop a system that classifies 4 EEG grades of HIE. The network learns directly from the two- dimensional TFD through 3 independent layers with convolution in the time, frequency, and time{frequency directions. Computationally efficient algorithms make it feasible to transform each 5 minute epoch to the time-frequency domain by controlling for oversampling to reduce both computation and computer memory. The system is developed on EEG recordings from 54 neonates. Then the system is validated on a large unseen dataset of 338 hours of EEG recordings from 91 neonates obtained across multiple international centres. RESULTS The proposed EEG HIE-grading system achieves a leave-one-subject-out testing accuracy of 88.9% and kappa of 0.84 on the development dataset. Accuracy for the large unseen test dataset is 69.5% (95% confidence interval, CI: 65.3 to 73.6%) and kappa of 0.54, which is a significant (P < 0.001) improvement over a state-of-the-art feature-based method with an accuracy of 56.8% (95% CI: 51.4 to 61.7%) and kappa of 0.39. Performance of the proposed system was unaffected when the number of channels in testing was reduced from 8 to 2|accuracy for large validation dataset remained at 69.5% (95% CI: 65.5 to 74.0%). SIGNIFICANCE The proposed system outperforms the state-of-the-art machine learning algorithms for EEG grade classification on a large multi-centre unseen dataset, indicating the potential to assist clinical decision making for neonates with HIE.
Collapse
Affiliation(s)
- Sumit Arun Raurale
- Pediatrics and child health, INFANT Centre, University College Cork, Cork, Cork, T12 DC4A, IRELAND
| | - Geraldine B Boylan
- Department of Paediatrics and Child Health, University College Cork, University College Cork,, Cork, IRELAND
| | - Sean Mathieson
- Podiatric and Child Health, INFANT Centre, University College Cork, Wilton, Cork, T12 DC4A, IRELAND
| | - W P Marnane
- Department of Electrical Engineering and Microelectronics, University College Cork, College Road, Cork, T12 DC4A, IRELAND
| | - Gordon Lightbody
- Department of Electrical Engineering and Microelectronics, University College Cork, College Road, Cork, T12 DC4A, IRELAND
| | - John M O'Toole
- Irish Centre for Fetal and Neonatal Translational Research, Dept. ofPaediatrics and Child Health, University College Cork National University of Ireland, Western Gateway Building, Western Road, Cork, IRELAND
| |
Collapse
|