Yong Xia
Yong Xia has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Dagan Feng
Biomedical and Multimedia Information Technology Research Group, School of Computer Science, The University of Sydney, Sydney, NSW, Australia
1 shared publication David Dagan Feng
Biomedical and Multimedia Information Technology (BMIT) Research Group
1 shared publication- Jiyong Wang
Department of Anesthesiology, The First Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangzhou, China
1 shared publication Lingfeng Wen
Biomedical and Multimedia Information Technology (BMIT) Research Group
1 shared publication- Michael Fulham
University of Sydney
1 shared publication - Shen Lu
Biomedical and Multimedia Information Technology (BMIT) Research Group, School of Information Technologies, University of Sydney, NSW 2006, Australia
1 shared publication
Latest Publications
- Open Access
- 1 January 2014
- Published by Wiley in BioMed Research International
- Vol. 2014, 1-8
Automated Identification of Dementia Using FDG-PET Imaging
Parametric FDG-PET images offer the potential for automated identification of the different dementia syndromes. However, various existing image features and classifiers have their limitations in characterizing and differentiating the patterns of this disease. We reported a hybrid feature extraction, selection, and classification approach, namely, the GA-MKL algorithm, for separating patients with suspected Alzheimer’s disease and frontotemporal dementia from normal controls. In this approach, we extracted three groups of features to describe the average level, spatial variation, and asymmetry of glucose metabolic rates in 116 cortical volumes. An optimal combination of features, that is, capable of classifying dementia cases was identified by a genetic algorithm- (GA-) based method. The condition of each FDG-PET study was predicted by applying the selected features to a multikernel learning (MKL) machine, in which the weighting parameter of each kernel function can be automatically estimated. We compared our approach to two state-of-the-art dementia identification algorithms on a set of 129 clinical cases and improved the performance in separating the dementia types, achieving accuracy of 94.62%. There is a very good agreement between the proposed automated technique and the diagnosis made by clinicians.
- 1 January 2014
- Published by Wiley in BioMed Research International
- Vol. 2014, 1-8
Open AccessAutomated Identification of Dementia Using FDG-PET Imaging
Parametric FDG-PET images offer the potential for automated identification of the different dementia syndromes. However, various existing image features and classifiers have their limitations in characterizing and differentiating the patterns of this disease. We reported a hybrid feature extraction, selection, and classification approach, namely, the GA-MKL algorithm, for separating patients with suspected Alzheimer’s disease and frontotemporal dementia from normal controls. In this approach, we extracted three groups of features to describe the average level, spatial variation, and asymmetry of glucose metabolic rates in 116 cortical volumes. An optimal combination of features, that is, capable of classifying dementia cases was identified by a genetic algorithm- (GA-) based method. The condition of each FDG-PET study was predicted by applying the selected features to a multikernel learning (MKL) machine, in which the weighting parameter of each kernel function can be automatically estimated. We compared our approach to two state-of-the-art dementia identification algorithms on a set of 129 clinical cases and improved the performance in separating the dementia types, achieving accuracy of 94.62%. There is a very good agreement between the proposed automated technique and the diagnosis made by clinicians.
- 1 December 2010
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 44, 63-68
Automated Detection of the Occurrence and Changes of Hot-Spots in Intro-subject FDG-PET Images from Combined PET-CT Scanners
Dual-modality PET-CT imaging has been prevalently used as an essential diagnostic tool for monitoring treatment response in malignant disease patients. However, evaluation of treatment outcomes in serial scans by visual inspecting multiple PET-CT volumes is time consuming and laborious. In this paper, we propose an automated algorithm to detect the occurrence and changes of hot-spots in intro-subject FDG-PET images from combined PET-CT scanners. In this algorithm, multiple CT images of the same subject are aligned by using an affine transformation, and the estimated transformation is then used to align the corresponding PET images into the same coordinate system. Hot-spots are identified using thresholding and region growing with parameters determined specifically for different body parts. The changes of the detected hot-spots over time are analysed and presented. Our results in 19 clinical PET-CT studies demonstrate that the proposed algorithm has a good performance.
- 1 December 2010
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 44, 63-68
Automated Detection of the Occurrence and Changes of Hot-Spots in Intro-subject FDG-PET Images from Combined PET-CT Scanners
Dual-modality PET-CT imaging has been prevalently used as an essential diagnostic tool for monitoring treatment response in malignant disease patients. However, evaluation of treatment outcomes in serial scans by visual inspecting multiple PET-CT volumes is time consuming and laborious. In this paper, we propose an automated algorithm to detect the occurrence and changes of hot-spots in intro-subject FDG-PET images from combined PET-CT scanners. In this algorithm, multiple CT images of the same subject are aligned by using an affine transformation, and the estimated transformation is then used to align the corresponding PET images into the same coordinate system. Hot-spots are identified using thresholding and region growing with parameters determined specifically for different body parts. The changes of the detected hot-spots over time are analysed and presented. Our results in 19 clinical PET-CT studies demonstrate that the proposed algorithm has a good performance.