Rule-based deep learning method for prognosis of neonatal hypoxic-ischemic encephalopathy by using susceptibility weighted image analysis.
Heatmap
Hypoxic-ischemic
SWI image
Transfer learning
Journal
Magma (New York, N.Y.)
ISSN: 1352-8661
Titre abrégé: MAGMA
Pays: Germany
ID NLM: 9310752
Informations de publication
Date de publication:
22 Jan 2024
22 Jan 2024
Historique:
received:
09
07
2023
accepted:
11
12
2023
revised:
06
12
2023
medline:
22
1
2024
pubmed:
22
1
2024
entrez:
22
1
2024
Statut:
aheadofprint
Résumé
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. 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. 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. 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.
Identifiants
pubmed: 38252196
doi: 10.1007/s10334-023-01139-2
pii: 10.1007/s10334-023-01139-2
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Informations de copyright
© 2024. The Author(s), under exclusive licence to European Society for Magnetic Resonance in Medicine and Biology (ESMRMB).
Références
Nadeem M, Murray DM, Boylan GB, Dempsey EM, Ryan CA (2011) Early blood glucose profile and neurodevelopmental outcome at two years in neonatal hypoxic-ischaemic encephalopathy. BMC Pediatr 11(1):1–6
doi: 10.1186/1471-2431-11-10
Massaro AN, Evangelou I, Fatemi A, Vezina G, Mccarter R, Glass P, Limperopoulos C (2015) White matter tract integrity and developmental outcome in newborn infants with hypoxic-ischemic encephalopathy treated with hypothermia. Dev Med Child Neurol 57(5):441–448
doi: 10.1111/dmcn.12646
pubmed: 25492527
Martinez-Biarge M, Diez-Sebastian J, Rutherford MA, Cowan FM (2010) Outcomes after central grey matter injury in term perinatal hypoxic-ischaemic encephalopathy. Early Human Dev 86(11):675–682
doi: 10.1016/j.earlhumdev.2010.08.013
Cawley P, Chakkarapani E (2020) Fifteen-minute consultation: Therapeutic hypothermia for infants with hypoxic ischaemic encephalopathy—translating jargon, prognosis and uncertainty for parents. Arch Dis Childhood Educ Pract 105(2):75–83
doi: 10.1136/archdischild-2017-314116
Halpin S, McCusker C, Fogarty L, White J, Cavalière E, Boylan G, Murray D (2022) Long-term neuropsychological and behavioral outcome of mild and moderate hypoxic ischemic encephalopathy. Early Human Dev 165:105541
doi: 10.1016/j.earlhumdev.2022.105541
Lakatos A (2021) Prognostic role of early MRI in neonatal hypoxic ischemic encephalopathy (doctoral dissertation)
Haacke EM, Mittal S, Wu Z, Neelavalli J, Cheng YC (2009) Susceptibility-weighted imaging: technical aspects and clinical applications, part 1. Am J Neuroradiol 30(1):19–30
doi: 10.3174/ajnr.A1400
pubmed: 19039041
pmcid: 3805391
Messina SA, Poretti A, Tekes A, Robertson C, Johnston MV, Huisman TA (2014) Early predictive value of susceptibility weighted imaging (SWI) in pediatric hypoxic-ischemic injury. J Neuroimaging 24(5):528–530
doi: 10.1111/jon.12043
pubmed: 24033676
LeLennartsson F, Darekar A, Maharatna K, Konn D, Allen D, Tournier JD, Broulidakis J, Vollmer B (2018) Developing a framework for studying brain networks in neonatal hypoxic-ischemic encephalopathy. In: Medical image understanding and analysis: 22nd conference, MIUA 2018, Southampton, UK, July 9–11, 2018, Proceedings 22. Springer International Publishing, pp 203–216
Ghosh N, Recker R, Shah A, Bhanu B, Ashwal S, Obenaus A (2011) Automated ischemic lesion detection in a neonatal model of hypoxic ischemic injury. J Magn Reson Imaging 33(4):772–781
doi: 10.1002/jmri.22488
pubmed: 21448940
Wu S, Mahmoodi S, Darekar A, Vollmer B, Lewis E, Liljeroth M (2017) Feature extraction and classification to diagnose hypoxic-ischemic encephalopathy patients by using susceptibility-weighted MRI images. In: Medical image understanding and analysis: 21st annual conference, MIUA 2017, Edinburgh, UK, July 11–13, 2017, Proceedings 21. Springer International Publishing, pp 527–536
Kitamura G, Kido D, Wycliffe N, Jacobson JP, Oyoyo U, Ashwal S (2011) Hypoxic-ischemic injury: utility of susceptibility-weighted imaging. Pediatr Neurol 45(4):220–224
doi: 10.1016/j.pediatrneurol.2011.06.009
pubmed: 21907881
Citraro L, Mahmoodi S, Darekar A, Vollmer B (2017) Extended three-dimensional rotation invariant local binary patterns. Image Vis Comput 62:8–18
doi: 10.1016/j.imavis.2017.03.004
Ning N, Li XJ, Gao J, Zhang YM, Han JG, Luo X, Niu G, Guo YM, Wu EX, Yang J (2013) Quantitative measurement of deep medullary venous in susceptibility weighted imaging: comparison of hypoxic ischemic and normal neonates. In: Society of Magnetic Resonance in Medicine Proceedings
Abbasi H, Bennet L, Gunn AJ, Unsworth CP (2019) 2D wavelet scalogram training of deep convolutional neural network for automatic identification of micro-scale sharp wave biomarkers in the hypoxic-ischemic EEG of preterm sheep. In: 2019 41st annual international conference of the IEEE engineering in medicine and biology society (EMBC), pp 1825–1828
Wang J, Ju R, Chen Y, Liu G, Yi Z (2020) Automated diagnosis of neonatal encephalopathy on aEEG using deep neural networks. Neurocomputing 398:95–107
doi: 10.1016/j.neucom.2020.01.057
Raurale SA, Boylan GB, Lightbody G, O’Toole JM (2020) Grading the severity of hypoxic-ischemic encephalopathy in newborn EEG using a convolutional neural network. In: 2020 42nd annual international conference of the IEEE engineering in medicine & biology society (EMBC), pp 6103–6106
Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D (2017) Grad-cam: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE international conference on computer vision, pp 618–626
Lundervold AS, Lundervold A (2019) An overview of deep learning in medical imaging focusing on MRI. Z Med Phys 29(2):102–127
doi: 10.1016/j.zemedi.2018.11.002
pubmed: 30553609
Morid MA, Borjali A, Del Fiol G (2021) A scoping review of transfer learning research on medical image analysis using ImageNet. Comput Biol Med 128:104115
doi: 10.1016/j.compbiomed.2020.104115
pubmed: 33227578
Yap MH, Pons G, Marti J, Ganau S, Sentis M, Zwiggelaar R, Marti R (2017) Automated breast ultrasound lesions detection using convolutional neural networks. IEEE J Biomed Health Inf 22(4):1218–1226
doi: 10.1109/JBHI.2017.2731873
Dar SUH, Özbey M, Çatlı AB, Çukur T (2020) A transfer-learning approach for accelerated MRI using deep neural networks. Magn Reson Med 84(2):663–685
doi: 10.1002/mrm.28148
pubmed: 31898840
Bedel HA, Sivgin I, Dalmaz O, Dar SU, Çukur T (2023) BolT: fused window transformers for fMRI time series analysis. Med Image Anal 88:102841
doi: 10.1016/j.media.2023.102841
pubmed: 37224718
Bedel HA, Çukur T (2023) DreaMR: diffusion-driven Counterfactual Explanation for Functional MRI. arXiv preprint arXiv:2307.09547
Kass M, Witkin A, Terzopoulos D (1988) Snakes: active contour models. Int J Comput Vision 1(4):321–331
doi: 10.1007/BF00133570
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778
Peng J, Kang S, Ning Z, Deng H, Shen J, Xu Y, Zhang J, Zhao W, Li X, Gong W, Huang J (2020) Residual convolutional neural network for predicting response of transarterial chemoembolization in hepatocellular carcinoma from CT imaging. Eur Radiol 30:413–424
doi: 10.1007/s00330-019-06318-1
pubmed: 31332558
Pan SJ, Yang Q (2010) A survey on transfer learning. IEEE Trans Knowl Data Eng 22(10):1345–1359
doi: 10.1109/TKDE.2009.191
Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L (2009) Imagenet: a large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition, pp 248–255
Tang Z, Mahmoodi S, Dasmahapatra S, Darekar A, Vollmer B (2020) Ridge detection and analysis of susceptibility-weighted magnetic resonance imaging in neonatal hypoxic-ischaemic encephalopathy. In: Medical Image Understanding and Analysis: 24th Annual Conference, MIUA 2020, Oxford, UK, July 15–17, 2020, Proceedings. Springer International Publishing, Cham, pp 307-318
Jain S, Salman H, Khaddaj A, Wong E, Park SM, Mądry A (2023) A data-based perspective on transfer learning. In: 2023 IEEE/CVF conference on computer vision and pattern recognition (CVPR), pp 3613–3622
Tang Z, Mahmoodi S, Darekar A, Vollmer B (2022) Hypoxic-ischaemic encephalopathy prognosis using susceptibility weighted image analysis based on histogram orientation gradient. In: proceedings of the 15th international joint conference on biomedical engineering systems and technologies—Volume 4: BIOSIGNALS, ISBN 978-989-758-552-4, ISSN 2184-4305, pp 57–62