A 3D Deep Residual Convolutional Neural Network for Differential Diagnosis of Parkinsonian Syndromes on 18F-FDG PET Images

Zhao Y, Wu P, Wang J, Li H, Navab N, Yakushev I, Weber W, Schwaiger M, Huang SC, Cumming P, Rominger A, Zuo C, Shi K (2019)

Publication Type: Conference contribution

Publication year: 2019

Journal

Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society IEEE Engineering in Medicine and Biology Society

Publisher: Institute of Electrical and Electronics Engineers Inc.

Pages Range: 3531-3534

Conference Proceedings Title: Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS

Event location: Berlin, DEU

ISBN: 9781538613115

DOI: 10.1109/EMBC.2019.8856747

Abstract

Idiopathic Parkinsons disease and atypical parkinsonian syndromes have similar symptoms at early disease stages, which makes the early differential diagnosis difficult. Positron emission tomography with 18F-FDG shows the ability to assess early neuronal dysfunction of neurodegenerative diseases and is well established for clinical use. In the past decades, machine learning methods have been widely used for the differential diagnosis of parkinsonism based on metabolic patterns. Unlike these conventional machine learning methods relying on hand-crafted features, the deep convolutional neural networks, which have achieved significant success in medical applications recently, have the advantage of learning salient feature representations automatically and effectively. This advantage may offer more appropriate invisible features extracted from data for the enhancement of the diagnosis accuracy. Therefore, this paper develops a 3D deep convolutional neural network on 18F-FDG PET images for the automated early diagnosis. Furthermore, we depicted in saliency maps the decision mechanism of the deep learning method to assist the physiological interpretation of deep learning performance. The proposed method was evaluated on a dataset with 920 patients. In addition to improving the accuracy in the differential diagnosis of parkinsonism compared to state-of-the-art approaches, the deep learning methods also discovered saliency features in a number of critical regions (e.g., midbrain), which are widely accepted as characteristic pathological regions for movement disorders but were ignored in the conventional analysis of FDG PET images.

Involved external institutions

Technische Universität München (TUM) DE Germany (DE) Fudan University / 复旦大学 CN China (CN) University of California Los Angeles (UCLA) US United States (USA) (US) Universität Bern CH Switzerland (CH)

How to cite

APA:

Zhao, Y., Wu, P., Wang, J., Li, H., Navab, N., Yakushev, I.,... Shi, K. (2019). A 3D Deep Residual Convolutional Neural Network for Differential Diagnosis of Parkinsonian Syndromes on 18F-FDG PET Images. In Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS (pp. 3531-3534). Berlin, DEU: Institute of Electrical and Electronics Engineers Inc..

MLA:

Zhao, Yu, et al. "A 3D Deep Residual Convolutional Neural Network for Differential Diagnosis of Parkinsonian Syndromes on 18F-FDG PET Images." Proceedings of the 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019, Berlin, DEU Institute of Electrical and Electronics Engineers Inc., 2019. 3531-3534.

BibTeX: Download