1
|
Tang X, Guo R, Zhang C, Qian X. A causal counterfactual graph neural network for arising-from-chair abnormality detection in parkinsonians. Med Image Anal 2024; 97:103266. [PMID: 38981281 DOI: 10.1016/j.media.2024.103266] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/27/2023] [Revised: 05/21/2024] [Accepted: 07/01/2024] [Indexed: 07/11/2024]
Abstract
The arising-from-chair task assessment is a key aspect of the evaluation of movement disorders in Parkinson's disease (PD). However, common scale-based clinical assessment methods are highly subjective and dependent on the neurologist's expertise. Alternate automated methods for arising-from-chair assessment can be established based on quantitative susceptibility mapping (QSM) images with multiple-instance learning. However, performance stability for such methods can be typically undermined by the presence of irrelevant or spuriously-relevant features that mask the intrinsic causal features. Therefore, we propose a QSM-based arising-from-chair assessment method using a causal graph-neural-network framework, where counterfactual and debiasing strategies are developed and integrated into this framework for capturing causal features. Specifically, the counterfactual strategy is proposed to suppress irrelevant features caused by background noise, by producing incorrect predictions when dropping causal parts. The debiasing strategy is proposed to suppress spuriously relevant features caused by the sampling bias and it comprises a resampling guidance scheme for selecting stable instances and a causal invariance constraint for improving stability under various interferences. The results of extensive experiments demonstrated the superiority of the proposed method in detecting arising-from-chair abnormalities. Its clinical feasibility was further confirmed by the coincidence between the selected causal features and those reported in earlier medical studies. Additionally, the proposed method was extensible for another motion task of leg agility. Overall, this study provides a potential tool for automated arising-from-chair assessment in PD patients, and also introduces causal counterfactual thinking in medical image analysis. Our source code is publicly available at https://github.com/SJTUBME-QianLab/CFGNN-PDarising.
Collapse
Affiliation(s)
- Xinlu Tang
- Medical Image and Health Informatics Lab, School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai 200030, China
| | - Rui Guo
- Medical Image and Health Informatics Lab, School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai 200030, China
| | - Chencheng Zhang
- Department of Functional Neurosurgery, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200025, China
| | - Xiaohua Qian
- Medical Image and Health Informatics Lab, School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai 200030, China.
| |
Collapse
|
2
|
Shi XH, Ju L, Dong L, Zhang RH, Shao L, Yan YN, Wang YX, Fu XF, Chen YZ, Ge ZY, Wei WB. Deep Learning Models for the Screening of Cognitive Impairment Using Multimodal Fundus Images. Ophthalmol Retina 2024; 8:666-677. [PMID: 38280426 DOI: 10.1016/j.oret.2024.01.019] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/31/2023] [Revised: 01/03/2024] [Accepted: 01/19/2024] [Indexed: 01/29/2024]
Abstract
OBJECTIVE We aimed to develop a deep learning system capable of identifying subjects with cognitive impairment quickly and easily based on multimodal ocular images. DESIGN Cross sectional study. SUBJECTS Participants of Beijing Eye Study 2011 and patients attending Beijing Tongren Eye Center and Beijing Tongren Hospital Physical Examination Center. METHODS We trained and validated a deep learning algorithm to assess cognitive impairment using retrospectively collected data from the Beijing Eye Study 2011. Cognitive impairment was defined as a Mini-Mental State Examination score < 24. Based on fundus photographs and OCT images, we developed 5 models based on the following sets of images: macula-centered fundus photographs, optic disc-centered fundus photographs, fundus photographs of both fields, OCT images, and fundus photographs of both fields with OCT (multimodal). The performance of the models was evaluated and compared in an external validation data set, which was collected from patients attending Beijing Tongren Eye Center and Beijing Tongren Hospital Physical Examination Center. MAIN OUTCOME MEASURES Area under the curve (AUC). RESULTS A total of 9424 retinal photographs and 4712 OCT images were used to develop the model. The external validation sets from each center included 1180 fundus photographs and 590 OCT images. Model comparison revealed that the multimodal performed best, achieving an AUC of 0.820 in the internal validation set, 0.786 in external validation set 1, and 0.784 in external validation set 2. We evaluated the performance of the multi-model in different sexes and different age groups; there were no significant differences. The heatmap analysis showed that signals around the optic disc in fundus photographs and the retina and choroid around the macular and optic disc regions in OCT images were used by the multimodal to identify participants with cognitive impairment. CONCLUSIONS Fundus photographs and OCT can provide valuable information on cognitive function. Multimodal models provide richer information compared with single-mode models. Deep learning algorithms based on multimodal retinal images may be capable of screening cognitive impairment. This technique has potential value for broader implementation in community-based screening or clinic settings. FINANCIAL DISCLOSURE(S) Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.
Collapse
Affiliation(s)
- Xu Han Shi
- Beijing Tongren Eye Center, Beijing Key Laboratory of Intraocular Tumor Diagnosis and Treatment, Beijing Tongren Hospital, Capital Medical University, Beijing, China; Beijing Ophthalmology and Visual Sciences Key Laboratory, Beijing Tongren Hospital, Capital Medical University, Beijing, China; Medical Artificial Intelligence Research and Verification Key Laboratory of the Ministry of Industry and Information Technology, Beijing Tongren Hospital, Capital Medical University, Beijing, China
| | - Lie Ju
- Beijing Airdoc Technology Co., Ltd., Beijing, China; Augmented Intelligence and Multimodal Analytics (AIM) for Health Lab, Faculty of Information Technology, Monash University, Clayton, Australia; Faculty of Engineering, Monash University, Clayton, Australia
| | - Li Dong
- Beijing Tongren Eye Center, Beijing Key Laboratory of Intraocular Tumor Diagnosis and Treatment, Beijing Tongren Hospital, Capital Medical University, Beijing, China; Beijing Ophthalmology and Visual Sciences Key Laboratory, Beijing Tongren Hospital, Capital Medical University, Beijing, China; Medical Artificial Intelligence Research and Verification Key Laboratory of the Ministry of Industry and Information Technology, Beijing Tongren Hospital, Capital Medical University, Beijing, China
| | - Rui Heng Zhang
- Beijing Tongren Eye Center, Beijing Key Laboratory of Intraocular Tumor Diagnosis and Treatment, Beijing Tongren Hospital, Capital Medical University, Beijing, China; Beijing Ophthalmology and Visual Sciences Key Laboratory, Beijing Tongren Hospital, Capital Medical University, Beijing, China; Medical Artificial Intelligence Research and Verification Key Laboratory of the Ministry of Industry and Information Technology, Beijing Tongren Hospital, Capital Medical University, Beijing, China
| | - Lei Shao
- Beijing Tongren Eye Center, Beijing Key Laboratory of Intraocular Tumor Diagnosis and Treatment, Beijing Tongren Hospital, Capital Medical University, Beijing, China; Beijing Ophthalmology and Visual Sciences Key Laboratory, Beijing Tongren Hospital, Capital Medical University, Beijing, China; Medical Artificial Intelligence Research and Verification Key Laboratory of the Ministry of Industry and Information Technology, Beijing Tongren Hospital, Capital Medical University, Beijing, China
| | - Yan Ni Yan
- Beijing Tongren Eye Center, Beijing Key Laboratory of Intraocular Tumor Diagnosis and Treatment, Beijing Tongren Hospital, Capital Medical University, Beijing, China; Beijing Ophthalmology and Visual Sciences Key Laboratory, Beijing Tongren Hospital, Capital Medical University, Beijing, China; Medical Artificial Intelligence Research and Verification Key Laboratory of the Ministry of Industry and Information Technology, Beijing Tongren Hospital, Capital Medical University, Beijing, China
| | - Ya Xing Wang
- Beijing Ophthalmology and Visual Science Key Laboratory, Beijing Tongren Eye Center, Beijing Tongren Hospital, Beijing Institute of Ophthalmology, Capital Medical University, Beijing, China
| | - Xue Fei Fu
- Beijing Airdoc Technology Co., Ltd., Beijing, China
| | | | - Zong Yuan Ge
- Beijing Airdoc Technology Co., Ltd., Beijing, China; Augmented Intelligence and Multimodal Analytics (AIM) for Health Lab, Faculty of Information Technology, Monash University, Clayton, Australia; Faculty of Engineering, Monash University, Clayton, Australia
| | - Wen Bin Wei
- Beijing Tongren Eye Center, Beijing Key Laboratory of Intraocular Tumor Diagnosis and Treatment, Beijing Tongren Hospital, Capital Medical University, Beijing, China; Beijing Ophthalmology and Visual Sciences Key Laboratory, Beijing Tongren Hospital, Capital Medical University, Beijing, China; Medical Artificial Intelligence Research and Verification Key Laboratory of the Ministry of Industry and Information Technology, Beijing Tongren Hospital, Capital Medical University, Beijing, China.
| |
Collapse
|
3
|
Arvidsson I, Strandberg O, Palmqvist S, Stomrud E, Cullen N, Janelidze S, Tideman P, Heyden A, Åström K, Hansson O, Mattsson-Carlgren N. Comparing a pre-defined versus deep learning approach for extracting brain atrophy patterns to predict cognitive decline due to Alzheimer's disease in patients with mild cognitive symptoms. Alzheimers Res Ther 2024; 16:61. [PMID: 38504336 PMCID: PMC10949809 DOI: 10.1186/s13195-024-01428-5] [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: 11/06/2023] [Accepted: 03/10/2024] [Indexed: 03/21/2024]
Abstract
BACKGROUND Predicting future Alzheimer's disease (AD)-related cognitive decline among individuals with subjective cognitive decline (SCD) or mild cognitive impairment (MCI) is an important task for healthcare. Structural brain imaging as measured by magnetic resonance imaging (MRI) could potentially contribute when making such predictions. It is unclear if the predictive performance of MRI can be improved using entire brain images in deep learning (DL) models compared to using pre-defined brain regions. METHODS A cohort of 332 individuals with SCD/MCI were included from the Swedish BioFINDER-1 study. The goal was to predict longitudinal SCD/MCI-to-AD dementia progression and change in Mini-Mental State Examination (MMSE) over four years. Four models were evaluated using different predictors: (1) clinical data only, including demographics, cognitive tests and APOE ε4 status, (2) clinical data plus hippocampal volume, (3) clinical data plus all regional MRI gray matter volumes (N = 68) extracted using FreeSurfer software, (4) a DL model trained using multi-task learning with MRI images, Jacobian determinant images and baseline cognition as input. A double cross-validation scheme, with five test folds and for each of those ten validation folds, was used. External evaluation was performed on part of the ADNI dataset, including 108 patients. Mann-Whitney U-test was used to determine statistically significant differences in performance, with p-values less than 0.05 considered significant. RESULTS In the BioFINDER cohort, 109 patients (33%) progressed to AD dementia. The performance of the clinical data model for prediction of progression to AD dementia was area under the curve (AUC) = 0.85 and four-year cognitive decline was R2 = 0.14. The performance was improved for both outcomes when adding hippocampal volume (AUC = 0.86, R2 = 0.16). Adding FreeSurfer brain regions improved prediction of four-year cognitive decline but not progression to AD (AUC = 0.83, R2 = 0.17), while the DL model worsened the performance for both outcomes (AUC = 0.84, R2 = 0.08). A sensitivity analysis showed that the Jacobian determinant image was more informative than the MRI image, but that performance was maximized when both were included. In the external evaluation cohort from ADNI, 23 patients (21%) progressed to AD dementia. The results for predicted progression to AD dementia were similar to the results for the BioFINDER test data, while the performance for the cognitive decline was deteriorated. CONCLUSIONS The DL model did not significantly improve the prediction of clinical disease progression in AD, compared to regression models with a single pre-defined brain region.
Collapse
Affiliation(s)
- Ida Arvidsson
- Centre for Mathematical Sciences, Lund University, Lund, Sweden.
| | - Olof Strandberg
- Clinical Memory Research Unit, Department of Clinical Sciences, Malmö, Lund University, Lund, Sweden
| | - Sebastian Palmqvist
- Clinical Memory Research Unit, Department of Clinical Sciences, Malmö, Lund University, Lund, Sweden
- Memory Clinic, Skåne University Hospital, Malmö, Sweden
| | - Erik Stomrud
- Clinical Memory Research Unit, Department of Clinical Sciences, Malmö, Lund University, Lund, Sweden
- Memory Clinic, Skåne University Hospital, Malmö, Sweden
| | - Nicholas Cullen
- Clinical Memory Research Unit, Department of Clinical Sciences, Malmö, Lund University, Lund, Sweden
| | - Shorena Janelidze
- Clinical Memory Research Unit, Department of Clinical Sciences, Malmö, Lund University, Lund, Sweden
| | - Pontus Tideman
- Clinical Memory Research Unit, Department of Clinical Sciences, Malmö, Lund University, Lund, Sweden
- Memory Clinic, Skåne University Hospital, Malmö, Sweden
| | - Anders Heyden
- Centre for Mathematical Sciences, Lund University, Lund, Sweden
| | - Karl Åström
- Centre for Mathematical Sciences, Lund University, Lund, Sweden
| | - Oskar Hansson
- Clinical Memory Research Unit, Department of Clinical Sciences, Malmö, Lund University, Lund, Sweden
- Memory Clinic, Skåne University Hospital, Malmö, Sweden
| | - Niklas Mattsson-Carlgren
- Clinical Memory Research Unit, Department of Clinical Sciences, Malmö, Lund University, Lund, Sweden.
- Wallenberg Center for Molecular Medicine, Lund University, Lund, Sweden.
- Department of Neurology, Skåne University Hospital, Lund, Sweden.
| |
Collapse
|
4
|
Huang L, Li Q, Lu Y, Pan F, Cui L, Wang Y, Miao Y, Chen T, Li Y, Wu J, Chen X, Jia J, Guo Q. Consensus on rapid screening for prodromal Alzheimer's disease in China. Gen Psychiatr 2024; 37:e101310. [PMID: 38313393 PMCID: PMC10836380 DOI: 10.1136/gpsych-2023-101310] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/31/2023] [Accepted: 12/19/2023] [Indexed: 02/06/2024] Open
Abstract
Alzheimer's disease (AD) is a common cause of dementia, characterised by cerebral amyloid-β deposition, pathological tau and neurodegeneration. The prodromal stage of AD (pAD) refers to patients with mild cognitive impairment (MCI) and evidence of AD's pathology. At this stage, disease-modifying interventions should be used to prevent the progression to dementia. Given the inherent heterogeneity of MCI, more specific biomarkers are needed to elucidate the underlying AD's pathology. Although the uses of cerebrospinal fluid and positron emission tomography are widely accepted methods for detecting AD's pathology, their clinical applications are limited by their high costs and invasiveness, particularly in low-income areas in China. Therefore, to improve the early detection of Alzheimer's disease (AD) pathology through cost-effective screening methods, a panel of 45 neurologists, psychiatrists and gerontologists was invited to establish a formal consensus on the screening of pAD in China. The supportive evidence and grades of recommendations are based on a systematic literature review and focus group discussion. National meetings were held to allow participants to review, vote and provide their expert opinions to reach a consensus. A majority (two-thirds) decision was used for questions for which consensus could not be reached. Recommended screening methods are presented in this publication, including neuropsychological assessment, peripheral biomarkers and brain imaging. In addition, a general workflow for screening pAD in China is established, which will help clinicians identify individuals at high risk and determine therapeutic targets.
Collapse
Affiliation(s)
- Lin Huang
- Department of Gerontology, Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Qinjie Li
- Department of Gerontology, Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Yao Lu
- Department of Gerontology, Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Fengfeng Pan
- Department of Gerontology, Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Liang Cui
- Department of Gerontology, Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Ying Wang
- Department of Gerontology, Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Ya Miao
- Department of Gerontology, Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Tianlu Chen
- Center for Translational Medicine and Shanghai Key Laboratory of Diabetes Mellitus, Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Yatian Li
- Shanghai BestCovered, Shanghai, China
| | | | - Xiaochun Chen
- Department of Neurology, Fujian Medical University Union Hospital, Fuzhou, China
| | - Jianping Jia
- Department of Neurology, National Clinical Research Center for Geriatric Diseases, Beijing, China
| | - Qihao Guo
- Department of Gerontology, Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, China
| |
Collapse
|
5
|
Arvidsson I, Strandberg O, Palmqvist S, Stomrud E, Cullen N, Janelidze S, Tideman P, Heyden A, Åström K, Hansson O, Mattsson-Carlgren N. Comparing a pre-defined versus deep learning approach for extracting brain atrophy patterns to predict cognitive decline due to Alzheimer's disease in patients with mild cognitive symptoms. RESEARCH SQUARE 2023:rs.3.rs-3569391. [PMID: 37986841 PMCID: PMC10659533 DOI: 10.21203/rs.3.rs-3569391/v1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/22/2023]
Abstract
Background Predicting future Alzheimer's disease (AD)-related cognitive decline among individuals with subjective cognitive decline (SCD) or mild cognitive impairment (MCI) is an important task for healthcare. Structural brain imaging as measured by magnetic resonance imaging (MRI) could potentially contribute when making such predictions. It is unclear if the predictive performance of MRI can be improved using entire brain images in deep learning (DL) models compared to using pre-defined brain regions. Methods A cohort of 332 individuals with SCD/MCI were included from the Swedish BioFINDER-1 study. The goal was to predict longitudinal SCD/MCI-to-AD dementia progression and change in Mini-Mental State Examination (MMSE) over four years. Four models were evaluated using different predictors: 1) clinical data only, including demographics, cognitive tests and APOE e4 status, 2) clinical data plus hippocampal volume, 3) clinical data plus all regional MRI gray matter volumes (N=68) extracted using FreeSurfer software, 4) a DL model trained using multi-task learning with MRI images, Jacobian determinant images and baseline cognition as input. Models were developed on 80% of subjects (N=267) and tested on the remaining 20% (N=65). Mann-Whitney U-test was used to determine statistically significant differences in performance, with p-values less than 0.05 considered significant. Results In the test set, 21 patients (32.3%) progressed to AD dementia. The performance of the clinical data model for prediction of progression to AD dementia was area under the curve (AUC)=0.87 and four-year cognitive decline was R2=0.17. The performance was significantly improved for both outcomes when adding hippocampal volume (AUC=0.91, R2=0.26, p-values <0.05) or FreeSurfer brain regions (AUC=0.90, R2=0.27, p-values <0.05). Conversely, the DL model did not show any significant difference from the clinical data model (AUC=0.86, R2=0.13). A sensitivity analysis showed that the Jacobian determinant image was more informative than the MRI image, but that performance was maximized when both were included. Conclusions The DL model did not significantly improve the prediction of clinical disease progression in AD, compared to regression models with a single pre-defined brain region.
Collapse
|
6
|
Bottani S, Burgos N, Maire A, Saracino D, Ströer S, Dormont D, Colliot O. Evaluation of MRI-based machine learning approaches for computer-aided diagnosis of dementia in a clinical data warehouse. Med Image Anal 2023; 89:102903. [PMID: 37523918 DOI: 10.1016/j.media.2023.102903] [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: 03/30/2022] [Revised: 06/01/2023] [Accepted: 07/12/2023] [Indexed: 08/02/2023]
Abstract
A variety of algorithms have been proposed for computer-aided diagnosis of dementia from anatomical brain MRI. These approaches achieve high accuracy when applied to research data sets but their performance on real-life clinical routine data has not been evaluated yet. The aim of this work was to study the performance of such approaches on clinical routine data, based on a hospital data warehouse, and to compare the results to those obtained on a research data set. The clinical data set was extracted from the hospital data warehouse of the Greater Paris area, which includes 39 different hospitals. The research set was composed of data from the Alzheimer's Disease Neuroimaging Initiative data set. In the clinical set, the population of interest was identified by exploiting the diagnostic codes from the 10th revision of the International Classification of Diseases that are assigned to each patient. We studied how the imbalance of the training sets, in terms of contrast agent injection and image quality, may bias the results. We demonstrated that computer-aided diagnosis performance was strongly biased upwards (over 17 percent points of balanced accuracy) by the confounders of image quality and contrast agent injection, a phenomenon known as the Clever Hans effect or shortcut learning. When these biases were removed, the performance was very poor. In any case, the performance was considerably lower than on the research data set. Our study highlights that there are still considerable challenges for translating dementia computer-aided diagnosis systems to clinical routine.
Collapse
Affiliation(s)
- Simona Bottani
- Sorbonne Université, Institut du Cerveau - Paris Brain Institute - ICM, CNRS, Inria, Inserm, AP-HP, Hôpital de la Pitié-Salpêtrière, Paris, 75013, France
| | - Ninon Burgos
- Sorbonne Université, Institut du Cerveau - Paris Brain Institute - ICM, CNRS, Inria, Inserm, AP-HP, Hôpital de la Pitié-Salpêtrière, Paris, 75013, France
| | | | - Dario Saracino
- Sorbonne Université, Institut du Cerveau - Paris Brain Institute - ICM, CNRS, Inria, Inserm, AP-HP, Hôpital de la Pitié-Salpêtrière, Paris, 75013, France; IM2A, Reference Centre for Rare or Early-Onset Dementias, Département de Neurologie, AP-HP, Hôpital de la Pitié Salpêtrière, Paris, 75013, France
| | - Sebastian Ströer
- AP-HP, Hôpital de la Pitié Salpêtrière, Department of Neuroradiology, Paris, 75013, France
| | - Didier Dormont
- AP-HP, Hôpital de la Pitié Salpêtrière, Department of Neuroradiology, Paris, 75013, France; Sorbonne Université, Institut du Cerveau - Paris Brain Institute - ICM, CNRS, Inria, Inserm, AP-HP, Hôpital de la Pitié-Salpêtrière, DMU DIAMENT, Paris, 75013, France
| | - Olivier Colliot
- Sorbonne Université, Institut du Cerveau - Paris Brain Institute - ICM, CNRS, Inria, Inserm, AP-HP, Hôpital de la Pitié-Salpêtrière, Paris, 75013, France.
| |
Collapse
|
7
|
Xu Y, Ma L, Zhang H, Liao H. Double-attention Assisted Multi-task Learning for the Alzheimer's Disease Prediction from Mild Cognitive Impairment . ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2023; 2023:1-4. [PMID: 38083587 DOI: 10.1109/embc40787.2023.10340815] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/18/2023]
Abstract
Alzheimer's disease (AD) is a progressive neurode-generative disease. Identifying the mild cognitive impairment (MCI) subjects who will convert to AD is essential for early intervention to slow the irreversible brain damage and cognitive decline. In this paper, we propose a novel double-attention assisted multi-task framework for the MCI conversion prediction task. By introducing an auxiliary grey matter segmentation task along with an adaptive dynamic weight average strategy to balance the impact of each task. Then, a double-attention module is incorporated to leverage both the classification and the segmentation attention information to guide the network to focus more on the structural alteration regions for better discrimination of AD pathology, as well as increase the interpretability of the network. Extensive experiments on a publicly available dataset demonstrate that the proposed method significantly outperforms the approaches using the same image modality.
Collapse
|
8
|
Liu F, Wang H, Liang SN, Jin Z, Wei S, Li X. MPS-FFA: A multiplane and multiscale feature fusion attention network for Alzheimer's disease prediction with structural MRI. Comput Biol Med 2023; 157:106790. [PMID: 36958239 DOI: 10.1016/j.compbiomed.2023.106790] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/05/2022] [Revised: 02/13/2023] [Accepted: 03/11/2023] [Indexed: 03/17/2023]
Abstract
Structural magnetic resonance imaging (sMRI) is a popular technique that is widely applied in Alzheimer's disease (AD) diagnosis. However, only a few structural atrophy areas in sMRI scans are highly associated with AD. The degree of atrophy in patients' brain tissues and the distribution of lesion areas differ among patients. Therefore, a key challenge in sMRI-based AD diagnosis is identifying discriminating atrophy features. Hence, we propose a multiplane and multiscale feature-level fusion attention (MPS-FFA) model. The model has three components, (1) A feature encoder uses a multiscale feature extractor with hybrid attention layers to simultaneously capture and fuse multiple pathological features in the sagittal, coronal, and axial planes. (2) A global attention classifier combines clinical scores and two global attention layers to evaluate the feature impact scores and balance the relative contributions of different feature blocks. (3) A feature similarity discriminator minimizes the feature similarities among heterogeneous labels to enhance the ability of the network to discriminate atrophy features. The MPS-FFA model provides improved interpretability for identifying discriminating features using feature visualization. The experimental results on the baseline sMRI scans from two databases confirm the effectiveness (e.g., accuracy and generalizability) of our method in locating pathological locations. The source code is available at https://github.com/LiuFei-AHU/MPSFFA.
Collapse
Affiliation(s)
- Fei Liu
- Anhui Provincial International Joint Research Center for Advanced Technology in Medical Imaging, Anhui University, Hefei, China; School of Computer Science and Technology, Anhui University, Hefei, China
| | - Huabin Wang
- Anhui Provincial International Joint Research Center for Advanced Technology in Medical Imaging, Anhui University, Hefei, China; School of Computer Science and Technology, Anhui University, Hefei, China.
| | - Shiuan-Ni Liang
- School of Engineering, Monash University Malaysia, Kuala Lumpur, Malaysia
| | - Zhe Jin
- Anhui Provincial International Joint Research Center for Advanced Technology in Medical Imaging, Anhui University, Hefei, China
| | - Shicheng Wei
- Anhui Provincial International Joint Research Center for Advanced Technology in Medical Imaging, Anhui University, Hefei, China
| | - Xuejun Li
- Anhui Provincial International Joint Research Center for Advanced Technology in Medical Imaging, Anhui University, Hefei, China; School of Computer Science and Technology, Anhui University, Hefei, China
| | | |
Collapse
|
9
|
Nguyen HD, Clément M, Mansencal B, Coupé P. Towards better interpretable and generalizable AD detection using collective artificial intelligence. Comput Med Imaging Graph 2023; 104:102171. [PMID: 36640484 DOI: 10.1016/j.compmedimag.2022.102171] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/23/2022] [Revised: 12/24/2022] [Accepted: 12/24/2022] [Indexed: 01/03/2023]
Abstract
Alzheimer's Disease is the most common cause of dementia. Accurate diagnosis and prognosis of this disease are essential to design an appropriate treatment plan, increasing the life expectancy of the patient. Intense research has been conducted on the use of machine learning to identify Alzheimer's Disease from neuroimaging data, such as structural magnetic resonance imaging. In recent years, advances of deep learning in computer vision suggest a new research direction for this problem. Current deep learning-based approaches in this field, however, have a number of drawbacks, including the interpretability of model decisions, a lack of generalizability information and a lower performance compared to traditional machine learning techniques. In this paper, we design a two-stage framework to overcome these limitations. In the first stage, an ensemble of 125 U-Nets is used to grade the input image, producing a 3D map that reflects the disease severity at voxel-level. This map can help to localize abnormal brain areas caused by the disease. In the second stage, we model a graph per individual using the generated grading map and other information about the subject. We propose to use a graph convolutional neural network classifier for the final classification. As a result, our framework demonstrates comparative performance to the state-of-the-art methods in different datasets for both diagnosis and prognosis. We also demonstrate that the use of a large ensemble of U-Nets offers a better generalization capacity for our framework.
Collapse
Affiliation(s)
- Huy-Dung Nguyen
- Univ. Bordeaux, CNRS, Bordeaux INP, LaBRI, UMR 5800, 33400 Talence, France.
| | - Michaël Clément
- Univ. Bordeaux, CNRS, Bordeaux INP, LaBRI, UMR 5800, 33400 Talence, France
| | - Boris Mansencal
- Univ. Bordeaux, CNRS, Bordeaux INP, LaBRI, UMR 5800, 33400 Talence, France
| | - Pierrick Coupé
- Univ. Bordeaux, CNRS, Bordeaux INP, LaBRI, UMR 5800, 33400 Talence, France
| |
Collapse
|
10
|
Song X, Zhou F, Frangi AF, Cao J, Xiao X, Lei Y, Wang T, Lei B. Multicenter and Multichannel Pooling GCN for Early AD Diagnosis Based on Dual-Modality Fused Brain Network. IEEE TRANSACTIONS ON MEDICAL IMAGING 2023; 42:354-367. [PMID: 35767511 DOI: 10.1109/tmi.2022.3187141] [Citation(s) in RCA: 11] [Impact Index Per Article: 11.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/15/2023]
Abstract
For significant memory concern (SMC) and mild cognitive impairment (MCI), their classification performance is limited by confounding features, diverse imaging protocols, and limited sample size. To address the above limitations, we introduce a dual-modality fused brain connectivity network combining resting-state functional magnetic resonance imaging (fMRI) and diffusion tensor imaging (DTI), and propose three mechanisms in the current graph convolutional network (GCN) to improve classifier performance. First, we introduce a DTI-strength penalty term for constructing functional connectivity networks. Stronger structural connectivity and bigger structural strength diversity between groups provide a higher opportunity for retaining connectivity information. Second, a multi-center attention graph with each node representing a subject is proposed to consider the influence of data source, gender, acquisition equipment, and disease status of those training samples in GCN. The attention mechanism captures their different impacts on edge weights. Third, we propose a multi-channel mechanism to improve filter performance, assigning different filters to features based on feature statistics. Applying those nodes with low-quality features to perform convolution would also deteriorate filter performance. Therefore, we further propose a pooling mechanism, which introduces the disease status information of those training samples to evaluate the quality of nodes. Finally, we obtain the final classification results by inputting the multi-center attention graph into the multi-channel pooling GCN. The proposed method is tested on three datasets (i.e., an ADNI 2 dataset, an ADNI 3 dataset, and an in-house dataset). Experimental results indicate that the proposed method is effective and superior to other related algorithms, with a mean classification accuracy of 93.05% in our binary classification tasks. Our code is available at: https://github.com/Xuegang-S.
Collapse
|
11
|
Miao D, Zhou X, Wu X, Chen C, Tian L. Hippocampal morphological atrophy and distinct patterns of structural covariance network in Alzheimer's disease and mild cognitive impairment. Front Psychol 2022; 13:980954. [PMID: 36160522 PMCID: PMC9505506 DOI: 10.3389/fpsyg.2022.980954] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/29/2022] [Accepted: 07/13/2022] [Indexed: 11/13/2022] Open
Abstract
Elucidating distinct morphological atrophy patterns of Alzheimer's disease (AD) and its prodromal stage, namely, mild cognitive impairment (MCI) helps to improve early diagnosis and medical intervention of AD. On that account, we aimed to obtain distinct patterns of voxel-wise morphological atrophy and its further perturbation on structural covariance network in AD and MCI compared with healthy controls (HCs). T1-weighted anatomical images of matched AD, MCI, and HCs were included in this study. Gray matter volume was obtained using voxel-based morphometry and compared among three groups. In addition, structural covariance network of identified brain regions exhibiting morphological difference was constructed and compared between pairs of three groups. Thus, patients with AD have a reduced hippocampal volume and an increased rate of atrophy compared with MCI and HCs. MCI exhibited a decreased trend in bilateral hippocampal volume compared with HCs and the accelerated right hippocampal atrophy rate than HCs. In AD, the hippocampus further exhibited increased structural covariance connected to reward related brain regions, including the anterior cingulate cortex, the putamen, the caudate, and the insula compared with HCs. In addition, the patients with AD exhibited increased structural covariance of left hippocampus with the bilateral insula, the inferior frontal gyrus, the superior temporal gyrus, and the cerebellum than MCI. These results reveal distinct patterns of morphological atrophy in AD and MCI, providing new insights into pathology of AD.
Collapse
Affiliation(s)
- Dawei Miao
- School of Automation, Beijing University of Posts and Telecommunications, Beijing, China
| | - Xiaoguang Zhou
- School of Automation, Beijing University of Posts and Telecommunications, Beijing, China
| | - Xiaoyuan Wu
- School of Economics and Management, Minjiang University, Fuzhou, China
| | - Chengdong Chen
- School of Economics and Management, Minjiang University, Fuzhou, China
| | - Le Tian
- School of Electrical and Information Engineering, Beijing University of Civil Engineering and Architecture, Beijing, China
| |
Collapse
|
12
|
Cobbinah BM, Sorg C, Yang Q, Ternblom A, Zheng C, Han W, Che L, Shao J. Reducing variations in multi-center Alzheimer's disease classification with convolutional adversarial autoencoder. Med Image Anal 2022; 82:102585. [PMID: 36057187 DOI: 10.1016/j.media.2022.102585] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/11/2021] [Revised: 07/22/2022] [Accepted: 08/15/2022] [Indexed: 11/29/2022]
Abstract
Based on brain magnetic resonance imaging (MRI), multiple variations ranging from MRI scanners to center-specific parameter settings, imaging protocols, and brain region-of-interest (ROI) definitions pose a big challenge for multi-center Alzheimer's disease characterization and classification. Existing approaches to reduce such variations require intricate multi-step, often manual preprocessing pipelines, including skull stripping, segmentation, registration, cortical reconstruction, and ROI outlining. Such procedures are time-consuming, and more importantly, tend to be user biased. Contrasting costly and biased preprocessing pipelines, the question arises whether we can design a deep learning model to automatically reduce these variations from multiple centers for Alzheimer's disease classification? In this study, we used T1 and T2-weighted structural MRI from Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset based on three groups with 375 subjects, respectively: patients with Alzheimer's disease (AD) dementia, with mild cognitive impairment (MCI), and healthy controls (HC); to test our approach, we defined AD classification as classifying an individual's structural image to one of the three group labels. We first introduced a convolutional adversarial autoencoder (CAAE) to reduce the variations existing in multi-center raw MRI scans by automatically registering them into a common aligned space. Afterward, a convolutional residual soft attention network (CRAT) was further proposed for AD classification. Canonical classification procedures demonstrated that our model achieved classification accuracies of 91.8%, 90.05%, and 88.10% for the 2-way classification tasks using the RAW aligned MRI scans, including AD vs. HC, AD vs. MCI, and MCI vs. HC, respectively. Thus, our automated approach achieves comparable or even better classification performance by comparing it with many baselines with dedicated conventional preprocessing pipelines. Furthermore, the uncovered brain hotpots, i.e., hippocampus, amygdala, and temporal pole, are consistent with previous studies.
Collapse
Affiliation(s)
- Bernard M Cobbinah
- School of Computer Science and Engineering, University of Electronic Science and Technology of China, 611731 Chengdu, China
| | - Christian Sorg
- Department of Neuroradiology, TUM-NIC Neuroimaging Center of Technical University Munich, Germany
| | - Qinli Yang
- School of Computer Science and Engineering, University of Electronic Science and Technology of China, 611731 Chengdu, China
| | - Arvid Ternblom
- School of Computer Science and Engineering, University of Electronic Science and Technology of China, 611731 Chengdu, China
| | - Changgang Zheng
- School of Computer Science and Engineering, University of Electronic Science and Technology of China, 611731 Chengdu, China
| | - Wei Han
- School of Computer Science and Engineering, University of Electronic Science and Technology of China, 611731 Chengdu, China
| | - Liwei Che
- School of Computer Science and Engineering, University of Electronic Science and Technology of China, 611731 Chengdu, China
| | - Junming Shao
- School of Computer Science and Engineering, University of Electronic Science and Technology of China, 611731 Chengdu, China; Center for Information in BioMedicine, University of Electronic Science and Technology of China, 611731 Chengdu, China; Yangtze Delta Region Institute (Huzhou), University of Electronic Science and Technology of China, Huzhou 313001, China.
| |
Collapse
|
13
|
Diogo VS, Ferreira HA, Prata D. Early diagnosis of Alzheimer's disease using machine learning: a multi-diagnostic, generalizable approach. Alzheimers Res Ther 2022; 14:107. [PMID: 35922851 PMCID: PMC9347083 DOI: 10.1186/s13195-022-01047-y] [Citation(s) in RCA: 8] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/15/2021] [Accepted: 07/13/2022] [Indexed: 01/07/2023]
Abstract
BACKGROUND Early and accurate diagnosis of Alzheimer's disease (AD) is essential for disease management and therapeutic choices that can delay disease progression. Machine learning (ML) approaches have been extensively used in attempts to develop algorithms for reliable early diagnosis of AD, although clinical usefulness, interpretability, and generalizability of the classifiers across datasets and MRI protocols remain limited. METHODS We report a multi-diagnostic and generalizable approach for mild cognitive impairment (MCI) and AD diagnosis using structural MRI and ML. Classifiers were trained and tested using subjects from the AD Neuroimaging Initiative (ADNI) database (n = 570) and the Open Access Series of Imaging Studies (OASIS) project database (n = 531). Several classifiers are compared and combined using voting for a decision. Additionally, we report tests of generalizability across datasets and protocols (IR-SPGR and MPRAGE), the impact of using graph theory measures on diagnostic classification performance, the relative importance of different brain regions on classification for better interpretability, and an evaluation of the potential for clinical applicability of the classifier. RESULTS Our "healthy controls (HC) vs. AD" classifier trained and tested on the combination of ADNI and OASIS datasets obtained a balanced accuracy (BAC) of 90.6% and a Matthew's correlation coefficient (MCC) of 0.811. Our "HC vs. MCI vs. AD" classifier trained and tested on the ADNI dataset obtained a 62.1% BAC (33.3% being the by-chance cut-off) and 0.438 MCC. Hippocampal features were the strongest contributors to the classification decisions (approx. 25-45%), followed by temporal (approx. 13%), cingulate, and frontal regions (approx. 8-13% each), which is consistent with our current understanding of AD and its progression. Classifiers generalized well across both datasets and protocols. Finally, using graph theory measures did not improve classification performance. CONCLUSIONS In sum, we present a diagnostic tool for MCI and AD trained using baseline scans and a follow-up diagnosis regardless of progression, which is multi-diagnostic, generalizable across independent data sources and acquisition protocols, and with transparently reported performance. Rated as potentially clinically applicable, our tool may be clinically useful to inform diagnostic decisions in dementia, if successful in real-world prospective clinical trials.
Collapse
Affiliation(s)
- Vasco Sá Diogo
- Instituto de Biofísica e Engenharia Biomédica, Faculdade de Ciências da Universidade de Lisboa, 1749-016, Lisboa, Portugal.
- Iscte-Instituto Universitário de Lisboa, CIS-Iscte, Lisboa, Portugal.
| | - Hugo Alexandre Ferreira
- Instituto de Biofísica e Engenharia Biomédica, Faculdade de Ciências da Universidade de Lisboa, 1749-016, Lisboa, Portugal
| | - Diana Prata
- Instituto de Biofísica e Engenharia Biomédica, Faculdade de Ciências da Universidade de Lisboa, 1749-016, Lisboa, Portugal.
- Department of Old Age Psychiatry, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK.
| |
Collapse
|
14
|
Wan MD, Liu H, Liu XX, Zhang WW, Xiao XW, Zhang SZ, Jiang YL, Zhou H, Liao XX, Zhou YF, Tang BS, Wang JL, Guo JF, Jiao B, Shen L. Associations of multiple visual rating scales based on structural magnetic resonance imaging with disease severity and cerebrospinal fluid biomarkers in patients with Alzheimer’s disease. Front Aging Neurosci 2022; 14:906519. [PMID: 35966797 PMCID: PMC9374170 DOI: 10.3389/fnagi.2022.906519] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/28/2022] [Accepted: 07/13/2022] [Indexed: 12/11/2022] Open
Abstract
The relationships between multiple visual rating scales based on structural magnetic resonance imaging (sMRI) with disease severity and cerebrospinal fluid (CSF) biomarkers in patients with Alzheimer’s disease (AD) were ambiguous. In this study, a total of 438 patients with clinically diagnosed AD were recruited. All participants underwent brain sMRI scan, and medial temporal lobe atrophy (MTA), posterior atrophy (PA), global cerebral atrophy-frontal sub-scale (GCA-F), and Fazekas rating scores were visually evaluated. Meanwhile, disease severity was assessed by neuropsychological tests such as the Mini-Mental State Examination (MMSE), Montreal Cognitive Assessment (MoCA), and Clinical Dementia Rating (CDR). Among them, 95 patients were tested for CSF core biomarkers, including Aβ1–42, Aβ1–40, Aβ1–42/Aβ1–40, p-tau, and t-tau. As a result, the GCA-F and Fazekas scales showed positively significant correlations with onset age (r = 0.181, p < 0.001; r = 0.411, p < 0.001, respectively). Patients with late-onset AD (LOAD) showed higher GCA-F and Fazekas scores (p < 0.001, p < 0.001). With regard to the disease duration, the MTA and GCA-F were positively correlated (r = 0.137, p < 0.05; r = 0.106, p < 0.05, respectively). In terms of disease severity, a positively significant association emerged between disease severity and the MTA, PA GCA-F, and Fazekas scores (p < 0.001, p < 0.001, p < 0.001, p < 0.05, respectively). Moreover, after adjusting for age, gender, and APOE alleles, the MTA scale contributed to moderate to severe AD in statistical significance independently by multivariate logistic regression analysis (p < 0.05). The model combining visual rating scales, age, gender, and APOE alleles showed the best performance for the prediction of moderate to severe AD significantly (AUC = 0.712, sensitivity = 51.5%, specificity = 84.6%). In addition, we observed that the MTA and Fazekas scores were associated with a lower concentration of Aβ1–42 (p < 0.031, p < 0.022, respectively). In summary, we systematically analyzed the benefits of multiple visual rating scales in predicting the clinical status of AD. The visual rating scales combined with age, gender, and APOE alleles showed best performance in predicting the severity of AD. MRI biomarkers in combination with CSF biomarkers can be used in clinical practice.
Collapse
Affiliation(s)
- Mei-dan Wan
- Department of Neurology, Xiangya Hospital, Central South University, Changsha, China
| | - Hui Liu
- Department of Neurology, Xiangya Hospital, Central South University, Changsha, China
| | - Xi-xi Liu
- Department of Neurology, Xiangya Hospital, Central South University, Changsha, China
| | - Wei-wei Zhang
- Department of Radiology, Xiangya Hospital, Central South University, Changsha, China
| | - Xue-wen Xiao
- Department of Neurology, Xiangya Hospital, Central South University, Changsha, China
| | - Si-zhe Zhang
- Department of Neurology, Xiangya Hospital, Central South University, Changsha, China
| | - Ya-ling Jiang
- Department of Neurology, Xiangya Hospital, Central South University, Changsha, China
| | - Hui Zhou
- Department of Neurology, Xiangya Hospital, Central South University, Changsha, China
| | - Xin-xin Liao
- National Clinical Research Center for Geriatric Disorders, Central South University, Changsha, China
- Key Laboratory of Hunan Province in Neurodegenerative Disorders, Central South University, Changsha, China
- Department of Geriatrics, Xiangya Hospital, Central South University, Changsha, China
| | - Ya-fang Zhou
- National Clinical Research Center for Geriatric Disorders, Central South University, Changsha, China
- Key Laboratory of Hunan Province in Neurodegenerative Disorders, Central South University, Changsha, China
- Department of Geriatrics, Xiangya Hospital, Central South University, Changsha, China
| | - Bei-sha Tang
- Department of Neurology, Xiangya Hospital, Central South University, Changsha, China
- National Clinical Research Center for Geriatric Disorders, Central South University, Changsha, China
- Key Laboratory of Hunan Province in Neurodegenerative Disorders, Central South University, Changsha, China
- Engineering Research Center of Hunan Province in Cognitive Impairment Disorders, Central South University, Changsha, China
- Hunan International Scientific and Technological Cooperation Base of Neurodegenerative and Neurogenetic Diseases, Changsha, China
| | - Jun-Ling Wang
- Department of Neurology, Xiangya Hospital, Central South University, Changsha, China
- National Clinical Research Center for Geriatric Disorders, Central South University, Changsha, China
- Key Laboratory of Hunan Province in Neurodegenerative Disorders, Central South University, Changsha, China
- Engineering Research Center of Hunan Province in Cognitive Impairment Disorders, Central South University, Changsha, China
- Hunan International Scientific and Technological Cooperation Base of Neurodegenerative and Neurogenetic Diseases, Changsha, China
| | - Ji-feng Guo
- Department of Neurology, Xiangya Hospital, Central South University, Changsha, China
- National Clinical Research Center for Geriatric Disorders, Central South University, Changsha, China
- Key Laboratory of Hunan Province in Neurodegenerative Disorders, Central South University, Changsha, China
- Engineering Research Center of Hunan Province in Cognitive Impairment Disorders, Central South University, Changsha, China
- Hunan International Scientific and Technological Cooperation Base of Neurodegenerative and Neurogenetic Diseases, Changsha, China
| | - Bin Jiao
- Department of Neurology, Xiangya Hospital, Central South University, Changsha, China
- National Clinical Research Center for Geriatric Disorders, Central South University, Changsha, China
- Key Laboratory of Hunan Province in Neurodegenerative Disorders, Central South University, Changsha, China
- Engineering Research Center of Hunan Province in Cognitive Impairment Disorders, Central South University, Changsha, China
- Hunan International Scientific and Technological Cooperation Base of Neurodegenerative and Neurogenetic Diseases, Changsha, China
- Bin Jiao,
| | - Lu Shen
- Department of Neurology, Xiangya Hospital, Central South University, Changsha, China
- National Clinical Research Center for Geriatric Disorders, Central South University, Changsha, China
- Key Laboratory of Hunan Province in Neurodegenerative Disorders, Central South University, Changsha, China
- Engineering Research Center of Hunan Province in Cognitive Impairment Disorders, Central South University, Changsha, China
- Hunan International Scientific and Technological Cooperation Base of Neurodegenerative and Neurogenetic Diseases, Changsha, China
- Key Laboratory of Organ Injury, Aging and Regenerative Medicine of Hunan Province, Changsha, China
- *Correspondence: Lu Shen,
| |
Collapse
|
15
|
Tan X, Wu J, Ma X, Kang S, Yue X, Rao Y, Li Y, Huang H, Chen Y, Lyu W, Qin C, Li M, Feng Y, Liang Y, Qiu S. Convolutional Neural Networks for Classification of T2DM Cognitive Impairment Based on Whole Brain Structural Features. Front Neurosci 2022; 16:926486. [PMID: 35928014 PMCID: PMC9344913 DOI: 10.3389/fnins.2022.926486] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/22/2022] [Accepted: 06/22/2022] [Indexed: 11/18/2022] Open
Abstract
Purpose Cognitive impairment is generally found in individuals with type 2 diabetes mellitus (T2DM). Although they may not have visible symptoms of cognitive impairment in the early stages of the disorder, they are considered to be at high risk. Therefore, the classification of these patients is important for preventing the progression of cognitive impairment. Methods In this study, a convolutional neural network was used to construct a model for classifying 107 T2DM patients with and without cognitive impairment based on T1-weighted structural MRI. The Montreal cognitive assessment score served as an index of the cognitive status of the patients. Results The classifier could identify T2DM-related cognitive decline with a classification accuracy of 84.85% and achieved an area under the curve of 92.65%. Conclusions The model can help clinicians analyze and predict cognitive impairment in patients and enable early treatment.
Collapse
Affiliation(s)
- Xin Tan
- First Clinical Medical College, Guangzhou University of Chinese Medicine, Guangzhou, China
- Medical Imaging Center, First Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangzhou, China
| | - Jinjian Wu
- First Clinical Medical College, Guangzhou University of Chinese Medicine, Guangzhou, China
| | - Xiaomeng Ma
- First Clinical Medical College, Guangzhou University of Chinese Medicine, Guangzhou, China
| | - Shangyu Kang
- First Clinical Medical College, Guangzhou University of Chinese Medicine, Guangzhou, China
| | - Xiaomei Yue
- First Clinical Medical College, Guangzhou University of Chinese Medicine, Guangzhou, China
| | - Yawen Rao
- First Clinical Medical College, Guangzhou University of Chinese Medicine, Guangzhou, China
| | - Yifan Li
- First Clinical Medical College, Guangzhou University of Chinese Medicine, Guangzhou, China
| | - Haoming Huang
- Medical Imaging Center, First Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangzhou, China
| | - Yuna Chen
- Medical Imaging Center, First Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangzhou, China
| | - Wenjiao Lyu
- First Clinical Medical College, Guangzhou University of Chinese Medicine, Guangzhou, China
| | - Chunhong Qin
- Medical Imaging Center, First Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangzhou, China
| | - Mingrui Li
- First Clinical Medical College, Guangzhou University of Chinese Medicine, Guangzhou, China
| | - Yue Feng
- First Clinical Medical College, Guangzhou University of Chinese Medicine, Guangzhou, China
| | - Yi Liang
- Medical Imaging Center, First Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangzhou, China
- Yi Liang
| | - Shijun Qiu
- Medical Imaging Center, First Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangzhou, China
- *Correspondence: Shijun Qiu
| |
Collapse
|
16
|
Lim BY, Lai KW, Haiskin K, Kulathilake KASH, Ong ZC, Hum YC, Dhanalakshmi S, Wu X, Zuo X. Deep Learning Model for Prediction of Progressive Mild Cognitive Impairment to Alzheimer’s Disease Using Structural MRI. Front Aging Neurosci 2022; 14:876202. [PMID: 35721012 PMCID: PMC9201448 DOI: 10.3389/fnagi.2022.876202] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/15/2022] [Accepted: 05/11/2022] [Indexed: 01/23/2023] Open
Abstract
Alzheimer’s disease (AD) is an irreversible neurological disorder that affects the vast majority of dementia cases, leading patients to experience gradual memory loss and cognitive function decline. Despite the lack of a cure, early detection of Alzheimer’s disease permits the provision of preventive medication to slow the disease’s progression. The objective of this project is to develop a computer-aided method based on a deep learning model to distinguish Alzheimer’s disease (AD) from cognitively normal and its early stage, mild cognitive impairment (MCI), by just using structural MRI (sMRI). To attain this purpose, we proposed a multiclass classification method based on 3D T1-weight brain sMRI images from the ADNI database. Axial brain images were extracted from 3D MRI and fed into the convolutional neural network (CNN) for multiclass classification. Three separate models were tested: a CNN built from scratch, VGG-16, and ResNet-50. As a feature extractor, the VGG-16 and ResNet-50 convolutional bases trained on the ImageNet dataset were employed. To achieve classification, a new densely connected classifier was implemented on top of the convolutional bases.
Collapse
Affiliation(s)
- Bing Yan Lim
- Department of Biomedical Engineering, Faculty of Engineering, Universiti Malaya, Kuala Lumpur, Malaysia
| | - Khin Wee Lai
- Department of Biomedical Engineering, Faculty of Engineering, Universiti Malaya, Kuala Lumpur, Malaysia
- *Correspondence: Khin Wee Lai,
| | - Khairunnisa Haiskin
- Department of Biomedical Engineering, Faculty of Engineering, Universiti Malaya, Kuala Lumpur, Malaysia
| | | | - Zhi Chao Ong
- Department of Mechanical Engineering, Universiti Malaya, Kuala Lumpur, Malaysia
| | - Yan Chai Hum
- Department of Mechatronics and Biomedical Engineering, Lee Kong Chian Faculty of Engineering and Science, Universiti Tunku Abdul Rahman, Petaling Jaya, Malaysia
| | - Samiappan Dhanalakshmi
- Department of Electronics and Communication Engineering, Faculty of Engineering and Technology, College of Engineering and Technology, SRM Institute of Science and Technology, Chennai, India
| | - Xiang Wu
- School of Medical Information & Engineering, Xuzhou Medical University, Xuzhou, China
| | - Xiaowei Zuo
- Department of Psychiatry, The Affiliated Xuzhou Oriental Hospital of Xuzhou Medical University, Xuzhou, China
- Xiaowei Zuo,
| |
Collapse
|
17
|
Bi XA, Li L, Wang Z, Wang Y, Luo X, Xu L. IHGC-GAN: influence hypergraph convolutional generative adversarial network for risk prediction of late mild cognitive impairment based on imaging genetic data. Brief Bioinform 2022; 23:6554128. [PMID: 35348583 DOI: 10.1093/bib/bbac093] [Citation(s) in RCA: 8] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/18/2021] [Revised: 01/28/2022] [Accepted: 02/23/2022] [Indexed: 11/13/2022] Open
Abstract
Predicting disease progression in the initial stage to implement early intervention and treatment can effectively prevent the further deterioration of the condition. Traditional methods for medical data analysis usually fail to perform well because of their incapability for mining the correlation pattern of pathogenies. Therefore, many calculation methods have been excavated from the field of deep learning. In this study, we propose a novel method of influence hypergraph convolutional generative adversarial network (IHGC-GAN) for disease risk prediction. First, a hypergraph is constructed with genes and brain regions as nodes. Then, an influence transmission model is built to portray the associations between nodes and the transmission rule of disease information. Third, an IHGC-GAN method is constructed based on this model. This method innovatively combines the graph convolutional network (GCN) and GAN. The GCN is used as the generator in GAN to spread and update the lesion information of nodes in the brain region-gene hypergraph. Finally, the prediction accuracy of the method is improved by the mutual competition and repeated iteration between generator and discriminator. This method can not only capture the evolutionary pattern from early mild cognitive impairment (EMCI) to late MCI (LMCI) but also extract the pathogenic factors and predict the deterioration risk from EMCI to LMCI. The results on the two datasets indicate that the IHGC-GAN method has better prediction performance than the advanced methods in a variety of indicators.
Collapse
Affiliation(s)
- Xia-An Bi
- Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing, and the College of Information Science and Engineering in Hunan Normal University, Changsha 410081, P.R. China
| | - Lou Li
- Department of Computing, School of Information Science and Engineering, Hunan Normal University, Changsha, China
| | - Zizheng Wang
- Department of Computing, School of Information Science and Engineering, Hunan Normal University, Changsha, China
| | - Yu Wang
- Department of Computing, School of Information Science and Engineering, Hunan Normal University, Changsha, China
| | - Xun Luo
- Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing, and the College of Information Science and Engineering in Hunan Normal University, Changsha 410081, P.R. China
| | - Luyun Xu
- College of Business, Hunan Normal University, Changsha 410081, P.R. China
| |
Collapse
|
18
|
Ashtari-Majlan M, Seifi A, Dehshibi MM. A multi-stream convolutional neural network for classification of progressive MCI in Alzheimer's disease using structural MRI images. IEEE J Biomed Health Inform 2022; 26:3918-3926. [PMID: 35239494 DOI: 10.1109/jbhi.2022.3155705] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/07/2022]
Abstract
Early diagnosis of Alzheimers disease and its prodromal stage, also known as mild cognitive impairment (MCI), is critical since some patients with progressive MCI will develop the disease. We propose a multi-stream deep convolutional neural network fed with patch-based imaging data to classify stable MCI and progressive MCI. First, we compare MRI images of Alzheimers disease with cognitively normal subjects to identify distinct anatomical landmarks using a multivariate statistical test. These landmarks are then used to extract patches that are fed into the proposed multi-stream convolutional neural network to classify MRI images. Next, we train the architecture in a separate scenario using samples from Alzheimers disease images, which are anatomically similar to the progressive MCI ones and cognitively normal images to compensate for the lack of progressive MCI training data. Finally, we transfer the trained model weights to the proposed architecture in order to fine-tune the model using progressive MCI and stable MCI data. Experimental results on the ADNI-1 dataset indicate that our method outperforms existing methods for MCI classification, with an F1-score of 85.96%.
Collapse
|
19
|
Miao D, Zhou X, Wu X, Chen C, Tian L. Distinct profiles of functional connectivity density aberrance in Alzheimer's disease and mild cognitive impairment. Front Psychiatry 2022; 13:1079149. [PMID: 36590612 PMCID: PMC9797864 DOI: 10.3389/fpsyt.2022.1079149] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/25/2022] [Accepted: 11/23/2022] [Indexed: 12/23/2022] Open
Abstract
INTRODUCTION Investigating the neuroimaging changes from mild cognitive impairment (MCI) to Alzheimer's disease (AD) is of great significance. However, the details about the distinct functional characteristics of AD and MCI remain unknown. METHODS In this study, we investigated distinct profiles of functional connectivity density (FCD) differences between AD and MCI compared with the normal population, aiming to depict the progressive brain changes from MCI to AD. As a data-driven method, FCD measures the profiles of FC for the given voxel at different scales. Resting-state functional magnetic resonance imaging (fMRI) images were obtained from patients with AD and MCI and matched healthy controls (HCs). One-way ANCOVA was used to investigate (global, long-range, and local) FCD differences among the three groups followed by post-hoc analysis controlling age, sex, and head motion. RESULTS The three groups exhibited significant global FCD differences in the superior frontal gyrus. The post-hoc results further showed that patients with AD had a significant increase in global FCD values than those with MCI and HCs. Patients with MCI exhibited an increased trend compared with HCs. We further identified brain regions contributing to the observed global FCD differences by conducting seed-based FC analysis. We also identified that the observed global FCD differences were the additive effects of altered FC between the superior frontal gyrus and the posterior default model network. DISCUSSION These results depicted the global information communication capability impairment in AD and MCI providing a new insight into the progressive brain changes from MCI to AD.
Collapse
Affiliation(s)
- Dawei Miao
- School of Automation, Beijing University of Posts and Telecommunications, Beijing, China
| | - Xiaoguang Zhou
- School of Automation, Beijing University of Posts and Telecommunications, Beijing, China
| | - Xiaoyuan Wu
- School of Economics and Management, Minjiang University, Fuzhou, China
| | - Chengdong Chen
- School of Economics and Management, Minjiang University, Fuzhou, China
| | - Le Tian
- School of Electrical and Information Engineering, Beijing University of Civil Engineering and Architecture, Beijing, China
| |
Collapse
|
20
|
Raj A. Graph Models of Pathology Spread in Alzheimer's Disease: An Alternative to Conventional Graph Theoretic Analysis. Brain Connect 2021; 11:799-814. [PMID: 33858198 DOI: 10.1089/brain.2020.0905] [Citation(s) in RCA: 9] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/28/2023] Open
Abstract
Background: Graph theory and connectomics are new techniques for uncovering disease-induced changes in the brain's structural network. Most prior studied have focused on network statistics as biomarkers of disease. However, an emerging body of work involves exploring how the network serves as a conduit for the propagation of disease factors in the brain and has successfully mapped the functional and pathological consequences of disease propagation. In Alzheimer's disease (AD), progressive deposition of misfolded proteins amyloid and tau is well-known to follow fiber projections, under a "prion-like" trans-neuronal transmission mechanism, through which misfolded proteins cascade along neuronal pathways, giving rise to network spread. Methods: In this review, we survey the state of the art in mathematical modeling of connectome-mediated pathology spread in AD. Then we address several open questions that are amenable to mathematically precise parsimonious modeling of pathophysiological processes, extrapolated to the whole brain. We specifically identify current formal models of how misfolded proteins are produced, aggregate, and disseminate in brain circuits, and attempt to understand how this process leads to stereotyped progression in Alzheimer's and other related diseases. Conclusion: This review serves to unify current efforts in modeling of AD progression that together have the potential to explain observed phenomena and serve as a test-bed for future hypothesis generation and testing in silico. Impact statement Graph theory is a powerful new approach that is transforming the study of brain processes. There do not exist many focused reviews of the subfield of graph modeling of how Alzheimer's and other dementias propagate within the brain network, and how these processes can be mapped mathematically. By providing timely and topical review of this subfield, we fill a critical gap in the community and present a unified view that can serve as an in silico test-bed for future hypothesis generation and testing. We also point to several open and unaddressed questions and controversies that future practitioners can tackle.
Collapse
Affiliation(s)
- Ashish Raj
- Department of Radiology and Biomedical Imaging, University of California at San Francisco, San Francisco, California, USA
| |
Collapse
|
21
|
Hett K, Lyu I, Trujillo P, Lopez AM, Aumann M, Larson KE, Hedera P, Dawant B, Landman BA, Claassen DO, Oguz I. Anatomical texture patterns identify cerebellar distinctions between essential tremor and Parkinson's disease. Hum Brain Mapp 2021; 42:2322-2331. [PMID: 33755270 PMCID: PMC8090778 DOI: 10.1002/hbm.25331] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/22/2020] [Revised: 11/25/2020] [Accepted: 12/16/2020] [Indexed: 01/15/2023] Open
Abstract
Voxel-based morphometry is an established technique to study focal structural brain differences in neurologic disease. More recently, texture-based analysis methods have enabled a pattern-based assessment of group differences, at the patch level rather than at the voxel level, allowing a more sensitive localization of structural differences between patient populations. In this study, we propose a texture-based approach to identify structural differences between the cerebellum of patients with Parkinson's disease (n = 280) and essential tremor (n = 109). We analyzed anatomical differences of the cerebellum among patients using two features: T1-weighted MRI intensity, and a texture-based similarity feature. Our results show anatomical differences between groups that are localized to the inferior part of the cerebellar cortex. Both the T1-weighted intensity and texture showed differences in lobules VIII and IX, vermis VIII and IX, and middle peduncle, but the texture analysis revealed additional differences in the dentate nucleus, lobules VI and VII, vermis VI and VII. This comparison emphasizes how T1-weighted intensity and texture-based methods can provide a complementary anatomical structure analysis. While texture-based similarity shows high sensitivity for gray matter differences, T1-weighted intensity shows sensitivity for the detection of white matter differences.
Collapse
Affiliation(s)
- Kilian Hett
- Department of Electrical Engineering and Computer ScienceVanderbilt UniversityNashvilleTennesseeUSA
| | - Ilwoo Lyu
- Department of Electrical Engineering and Computer ScienceVanderbilt UniversityNashvilleTennesseeUSA
| | - Paula Trujillo
- Department of NeurologyVanderbilt University Medical CenterNashvilleTennesseeUSA
| | - Alexander M. Lopez
- Department of NeurologyVanderbilt University Medical CenterNashvilleTennesseeUSA
| | - Megan Aumann
- Department of NeurologyVanderbilt University Medical CenterNashvilleTennesseeUSA
| | - Kathleen E. Larson
- Department of Electrical Engineering and Computer ScienceVanderbilt UniversityNashvilleTennesseeUSA
| | - Peter Hedera
- Department of NeurologyVanderbilt University Medical CenterNashvilleTennesseeUSA,Department of NeurologyUniversity of LouisvilleLouisvilleKentuckyUSA
| | - Benoit Dawant
- Department of Electrical Engineering and Computer ScienceVanderbilt UniversityNashvilleTennesseeUSA
| | - Bennett A. Landman
- Department of Electrical Engineering and Computer ScienceVanderbilt UniversityNashvilleTennesseeUSA
| | - Daniel O. Claassen
- Department of NeurologyVanderbilt University Medical CenterNashvilleTennesseeUSA
| | - Ipek Oguz
- Department of Electrical Engineering and Computer ScienceVanderbilt UniversityNashvilleTennesseeUSA
| |
Collapse
|