Multimodal Neuroimaging Feature Learning for Multiclass Diagnosis of Alzheimer's Disease
Open accessThe DOI matches its Crossref record; 69 of the 76 references it cites were found in a registry or an index.
Abstract
The accurate diagnosis of Alzheimer's disease (AD) is essential for patient care and will be increasingly important as disease modifying agents become available, early in the course of the disease. Although studies have applied machine learning methods for the computer-aided diagnosis of AD, a bottleneck in the diagnostic performance was shown in previous methods, due to the lacking of efficient strategies for representing neuroimaging biomarkers. In this study, we designed a novel diagnostic framework with deep learning architecture to aid the diagnosis of AD. This framework uses a zero-masking strategy for data fusion to extract complementary information from multiple data modalities. Compared to the previous state-of-the-art workflows, our method is capable of fusing multimodal neuroimaging features in one setting and has the potential to require less labeled data. A performance gain was achieved in both binary classification and multiclass classification of AD. The advantages and limitations of the proposed framework are discussed.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
LIBSVM: A library for support vector machines
Chang, C.-C., & Lin, C.-J. (2011) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/1961189.1961199 · Cited by 40,918 · cited 2×
“The SVM-based experiments were performed using LIBSVM [58].”
MethodMcKhann, G., Drachman, D., Folstein, M., Katzman, R., Price, D., & Stadlan, E. M. (1984) · Neurology · doi:10.1212/wnl.34.7.939 · Cited by 27,915
Regularization and Variable Selection Via the Elastic Net
Zou, H., & Hastie, T. (2005) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.1467-9868.2005.00503.x · Cited by 20,957
Reducing the dimensionality of data with neural networks
Hinton, G. E., & Salakhutdinov, R. R. (2006) · Science · doi:10.1126/science.1127647 · Cited by 20,928
A fast learning algorithm for deep belief nets
Hinton, G. E., Osindero, S., & Teh, Y.-W. (2006) · Neural Computation · doi:10.1162/neco.2006.18.7.1527 · Cited by 16,336
Representation Learning: A Review and New Perspectives
Bengio, Y., Courville, A., & Vincent, P. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.50 · Cited by 13,001 · cited 1×
“Deep learning architectures extract high-level features progressively via several layers of feature representations [37].”
BackgroundJenkinson, M., Bannister, P., Brady, M., & Smith, S. (2002) · NeuroImage · doi:10.1006/nimg.2002.1132 · Cited by 11,888 · cited 1×
“The PET images were aligned to the corresponding MR image using FSL FLIRT [49].”
MethodLearning Deep Architectures for AI
Bengio, Y. (2009) · Foundations and Trends® in Machine Learning · doi:10.1561/2200000006 · Cited by 9,239 · cited 1×
“The features extracted by the unsupervised network are fed to an output layer with softmax regression [55].”
Method3D Slicer as an image computing platform for the Quantitative Imaging Network
Fedorov, A., Beichel, R., Kalpathy-Cramer, J., Finet, J., Fillion-Robin, J.-C., Pujol, S., Bauer, C., Jennings, D., Fennessy, F., Sonka, M., et al. (2012) · Magnetic Resonance Imaging · doi:10.1016/j.mri.2012.05.001 · Cited by 9,023
Self-citation(2012) · Cited by 8,009
Research works printed but not linked: 4
- liu, 2014, High-level feature based PET image retrieval with deep learning architecture, J Nucl Med, 55, 2018
- liu, 2013, Sparse auto-encoded hypo-metabolism patterns in Alzheimer's disease and mild cognitive impairment, J Nucl Med, 54, 1807
- liu, 0, Multifold Bayesian kernelization in Alzheimers diagnosis, Proc Int Conf Med Image Comput Comput -Assisted Intervention, 303
- zou, 0, Unsupervised learning of visual invariance with temporal coherence, Proc NIPS Workshop on Deep Learning and Unsupervised Feature Learning
Cited by
Items 101–200 of 639
Automatic Alzheimer’s Disease Recognition from MRI Data Using Deep Learning Method
Luo, S., Li, X., & Li, J. (2017) · Journal of Applied Mathematics and Physics · doi:10.4236/jamp.2017.59159 · Cited by 87
“[6] presented a multimodal neuroimaging feature extraction pipeline for multiclass AD diagnosis.”
BackgroundOdusami, M., Maskeliūnas, R., Damaševičius, R., & Misra, S. (2023) · Cognitive Neurodynamics · doi:10.1007/s11571-023-09993-5 · Cited by 114
Abraham, B., & Nair, P. (. ). M. S. (2018) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2018.08.006 · Cited by 84
Mahim, S. M., Ali, M. S., Hasan, M. O., Nafi, A. A. N., Sadat, A. K. M., Hasan, S. A., Shareef, B., Ahsan, M. M., Islam, M. K., Miah, M. S., et al. (2024) · IEEE Access · doi:10.1109/access.2024.3351809 · Cited by 102
Autism Spectrum Disorder Detection with Machine Learning Methods
Erkan, U., & Thanh, D. N. H. (2019) · Current Psychiatry Research and Reviews · doi:10.2174/2666082215666191111121115 · Cited by 134
Artificial Intelligence in Clinical Neuroscience: Methodological and Ethical Challenges
Ienca, M., & Ignatiadis, K. (2020) · AJOB Neuroscience · doi:10.1080/21507740.2020.1740352 · Cited by 106
“One example is the use of ANNs to predict the conversion from Mild Cognitive Impairment (MCI) to AD (Liu et al. 2015; Vieira et al. 2017).”
MethodSharma, S., & Mandal, P. K. (2022) · ACM Computing Surveys · doi:10.1145/3492865 · Cited by 106
“The accuracy of the proposed model for binary classification is 91.40% and 82.10% for AD vs. HC and MCI vs. HC, respectively, whereas the accuracy for multi-classification (AD vs.MCI vs. HC) is not much significant at 53.79% [104].”
MethodInfluentialLin, W.-M., Gao, Q., Yuan, J., Chen, Z., Feng, C., Chen, W., Du, M., & Tong, T. (2020) · Frontiers in Aging Neuroscience · doi:10.3389/fnagi.2020.00077 · Cited by 88
Pei, X., Zuo, K., Li, Y., & Pang, Z. (2023) · International Journal of Computational Intelligence Systems · doi:10.1007/s44196-023-00225-6 · Cited by 77
“deep-learning methods for solving medical processes, such as different fusion models for physical medical image segmentation [6], brain tumor segmentation [24], multi-organ detection [56], anatomical education [57], multiple diagnoses of Alzheimer's disease [58], the prognosis of rectal cancer [59], breast mass detect…”
Classification of Alzheimer’s Disease Using Deep Convolutional Spiking Neural Network
Turkson, R. E., Qu, H., Mawuli, C. B., & Eghan, M. J. (2021) · Neural Processing Letters · doi:10.1007/s11063-021-10514-w · Cited by 85
“Detecting the early stages and the full spectrum of AD progression is essential in order to enable patients to control the risk factors, for example, isolated systolic hypertension before irreversible brain damage develops [7].”
Deep learning in neuroimaging data analysis: Applications, challenges, and solutions
Avberšek, L. K., & Repovš, G. (2022) · Frontiers in Neuroimaging · doi:10.3389/fnimg.2022.981642 · Cited by 100
Alzheimer’s disease diagnosis via multimodal feature fusion
Tu, Y., Lin, S., Qiao, J., Zhuang, Y., & Zhang, P. (2022) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2022.105901 · Cited by 84
Alzheimer’s Disease Diagnosis Using Machine Learning: A Survey
Dara, O. A., López-Guede, J. M., Raheem, H. I., Rahebi, J., Zulueta, E., & Fernández‐Gámiz, U. (2023) · Applied Sciences · doi:10.3390/app13148298 · Cited by 81
“[116] SVM 92.48 [117] Fisher 96.32 [118] SVM with genetic algorithm 96.80 [118] SVM with image processing 93.30 [119] Multi-modal neuroimaging 91.40 [120] Image processing and weight extraction operations 95 [123] Stochastic random forest 93 [124] PCA with SVM 95 [129,131,132] CNN with various…”
InfluentialA deep learning pipeline to classify different stages of Alzheimer's disease from fMRI data
Kazemi, Y., & Houghten, S. K. (2018) · IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB) · doi:10.1109/cibcb.2018.8404980 · Cited by 82
“The availability of this data from the ADNI project will give us the opportunity to use the previous multi modal methods [34] [37] [36] [72] [73] [59] [60] with the assistance of SVM techniques to improve the accuracy of classification in this problem.”
BackgroundMethodNagasato, D., Tabuchi, H., Ohsugi, H., Masumoto, H., Enno, H., Ishitobi, N., Sonobe, T., Kameoka, M., Niki, M., Hayashi, K., et al. (2018) · Journal of Ophthalmology · doi:10.1155/2018/1875431 · Cited by 73
Deep Multi-Modal Discriminative and Interpretability Network for Alzheimer’s Disease Diagnosis
Zhu, Q., Xu, B., Huang, J., Wang, H., Xu, R., Shao, W., & Zhang, D. (2022) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2022.3230750 · Cited by 76
“For accuracy, we compare the performance of LMKD with the first layer weight (FLW) [12] and DMDR, under different conditions of single modality and multi-modality.”
BackgroundMethodInfluentialDeep-Learning-Based Diagnosis and Prognosis of Alzheimer’s Disease: A Comprehensive Review
Sharma, R., Goel, T., Tanveer, M., Lin, C., & Murugan, R. (2023) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2023.3254209 · Cited by 88
“[120] uses the ADNI database with a novel idea of a zero-masking strategy for data fusion and proposes a model of fusing multimodal data and pretrained stacked AE as a DL algorithm.”
MethodIterative sparse and deep learning for accurate diagnosis of Alzheimer’s disease
Chen, Y., & Xia, Y. (2021) · Pattern Recognition · doi:10.1016/j.patcog.2021.107944 · Cited by 80
Alzheimer's disease classification based on combination of multi-model convolutional networks
Li, F., Cheng, D., & Liu, M. (2017) · IEEE International Conference on Imaging Systems and Techniques (IST) · doi:10.1109/ist.2017.8261566 · Cited by 71
“[5] designed a novel diagnostic framework with deep learning architecture to aid the diagnosis of AD by using a zero-masking strategy for data fusion to extract complementary information from multiple data modalities.”
BackgroundRaju, M., Gopi, V. P., Anitha, V. S., & Wahid, K. A. (2020) · Physical and Engineering Sciences in Medicine · doi:10.1007/s13246-020-00924-w · Cited by 70
Initiative, T. A. D. N., Wu, C., Guo, S., Hong, Y., Xiao, B., Wu, Y., & Zhang, Q. (2018) · Quantitative Imaging in Medicine and Surgery · doi:10.21037/qims.2018.10.17 · Cited by 68
“A multimodal neuroimaging feature learning and fusion method (24) was employed for classification and showed a 91.4% accuracy for NC-AD, an 82.1% accuracy for NC-MCI, and a 53.79% accuracy for AD/cMCI/sMCI/NC.”
MethodInfluentialNagasawa, T., Tabuchi, H., Masumoto, H., Enno, H., Niki, M., Ohara, Z., Yoshizumi, Y., Ohsugi, H., & Mitamura, Y. (2019) · International Ophthalmology · doi:10.1007/s10792-019-01074-z · Cited by 76
Ismail, W. N., P., F. R. P., & Ali, M. A. S. (2023) · Mathematics · doi:10.3390/math11040957 · Cited by 73
Convolutional Neural Network-based MR Image Analysis for Alzheimer’s Disease Classification
Choi, B.-K., Madusanka, N., Choi, H., So, J.-H., Kim, C., Park, H., Bhattacharjee, S., & Prakash, D. (2019) · Current Medical Imaging Formerly Current Medical Imaging Reviews · doi:10.2174/1573405615666191021123854 · Cited by 73
Yoo, Y., Tang, L. Y. W., Li, D. K. B., Metz, L., Kolind, S., Traboulsee, A. L., & Tam, R. C. (2019) · Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization · doi:10.1080/21681163.2017.1356750 · Cited by 67
“Forexample, deep learning of neuroimaging data has been used to perform various tasks such as the classification between mild cognitive impairment and Alzheimer’s disease (e.g. Suk et al. 2014; Liu et al. 2015) and to model pathological variability in MS (Brosch et al. 2014).”
MethodTufail, A. B., Anwar, N., Othman, M. T. B., Ullah, I., Khan, R. A., Ma, Y., Adhikari, D., Rehman, A. U., Shafiq, M., & Hamam, H. (2022) · Sensors · doi:10.3390/s22124609 · Cited by 70
“It is distinguished by the continuous degeneration of nerve cells, formation of neurofibrillary tangles as well as of amyloid plaques [2].”
BackgroundA transfer learning approach for multiclass classification of Alzheimer's disease using MRI images
Khan, R., Akbar, S., Mehmood, A., Shahid, F., Munir, K., Ilyas, N., Asif, M., & Zheng, Z. (2023) · Frontiers in Neuroscience · doi:10.3389/fnins.2022.1050777 · Cited by 86
“A multimodal learning-based network (Liu et al., 2014) based on PET, and MRI images, a multi-modal stack-net (Shi et al.”
BackgroundMethodInfluentialFang, X., Liu, Z., & Xu, M. (2019) · IET Image Processing · doi:10.1049/iet-ipr.2019.0617 · Cited by 74
Tagaris, A., Kollias, D., Stafylopatis, A., Tagaris, G. L., & Kollias, S. (2018) · International Journal of Artificial Intelligence Tools · doi:10.1142/s0218213018500112 · Cited by 100
Model Based on Deep Feature Extraction for Diagnosis of Alzheimer’s Disease
Silva, I. R. R., Silva, G. D. S. L. E., de Souza, R. G., dos Santos, W. P., & Fagundes, R. (2019) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2019.8852138 · Cited by 70
“(2015) [18] ADNI Stacked Autoencoders (MRI+PET) Softmax 0.”
BackgroundJabason, E., Ahmad, M. O., & Swamy, M. N. S. (2019) · IEEE International Midwest Symposium on Circuits and Systems (MWSCAS) · doi:10.1109/mwscas.2019.8884939 · Cited by 73
“Liu et al [10] MRI+PET 53.”
AD-NET: Age-adjust neural network for improved MCI to AD conversion prediction
Gao, F., Yoon, H., Xu, Y., Goradia, D., Luo, J., Wu, T., & Su, Y. (2020) · NeuroImage: Clinical · doi:10.1016/j.nicl.2020.102290 · Cited by 64
Promises and pitfalls of deep neural networks in neuroimaging-based psychiatric research
Eitel, F., Schulz, M.-A., Seiler, M., Walter, H., & Ritter, K. (2021) · Experimental Neurology · doi:10.1016/j.expneurol.2021.113608 · Cited by 79
Wang, Z., Zhu, X., Adeli, E., Zhu, Y., Nie, F., Munsell, B. C., & Guorong Wu, A. (2017) · Medical Image Analysis · doi:10.1016/j.media.2017.05.003 · Cited by 68
Thung, K.-H., Yap, P.-T., & Shen, D. (2017) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-67558-9_19 · Cited by 63
“Though some models are applicable to incomplete data, almost all of them are based on data synthesis/imputation [5,6], which may not work well for large amount of missing data [7].”
MethodHierarchical Feature Extraction for Early Alzheimer’s Disease Diagnosis
Yue, L., Gong, X., Li, J., Ji, H., Li, M., & Nandi, A. K. (2019) · IEEE Access · doi:10.1109/access.2019.2926288 · Cited by 70
“All the images were preprocessed by GradWarp and B1 Correction with pro_ADNI_script [14], then processed by ADNI pipeline with nonparametric non-uniform intensity normalization (N3) algorithm for a correction of intensity inhomogeneity [10], [14].”
MethodDTI based Alzheimer’s disease classification with rank modulated fusion of CNNs and random forest
De, A., & Chowdhury, A. S. (2020) · Expert Systems with Applications · doi:10.1016/j.eswa.2020.114338 · Cited by 74
Neuroimaging modality fusion in Alzheimer’s classification using convolutional neural networks
Punjabi, A., Martersteck, A., Wang, Y., Parrish, T. B., Katsaggelos, A. K., & Initiative, A. T. A. D. N. (2019) · PLoS ONE · doi:10.1371/journal.pone.0225759 · Cited by 74
“In [20], features from MRI and FDG PET images were extracted using a stacked autoencoder which were then classified with softmax regression.”
MethodSarraf, S., DeSouza, D. D., Anderson, J. A. E., & Saverino, C. (2019) · IEEE Access · doi:10.1109/access.2019.2949577 · Cited by 78
Lee, E., Choi, J.-S., Kim, M., & Suk, H.-I. (2019) · NeuroImage · doi:10.1016/j.neuroimage.2019.116113 · Cited by 61
“A region-based approach considers structurally or functionally prede fi ned brain regions and extracts representative handcrafted features ( e.g. , mean volume) from each region (Liu et al., 2015).”
BackgroundU-net based analysis of MRI for Alzheimer’s disease diagnosis
Fan, Z., Li, J., Zhang, L., Zhu, G., Li, P., Lu, X., Shen, P., Shah, S. A. A., Bennamoun, M., Hua, T., et al. (2021) · Neural Computing and Applications · doi:10.1007/s00521-021-05983-y · Cited by 71
“[46] SAE-Zeromask MRI?PET ADNI (758) AD vs.”
Lahmiri, S. (2022) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2022.104375 · Cited by 71
Leela, M., Helenprabha, K., & Sharmila, L. (2023) · Measurement Sensors · doi:10.1016/j.measen.2023.100749 · Cited by 83
Rashid, M. U., Singh, H., & Goyal, V. (2020) · Expert Systems · doi:10.1111/exsy.12644 · Cited by 68
Deep learning for Alzheimer prediction using brain biomarkers
Goenka, N., & Tiwari, S. (2021) · Artificial Intelligence Review · doi:10.1007/s10462-021-10016-0 · Cited by 63
Wang, M., Wei, Z., Jia, M., Chen, L., & Ji, H. (2022) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-022-01776-y · Cited by 69
“AI techniques are used in the detection of lymph node metastasis in women with breast cancer [9], skin cancer dermatological level classification [10], diabetic retinopathy and diabetic macular edema [11], and multiple diagnoses of Alzheimer’s disease [12].”
MethodLamar, M., Boots, E. A., Arfanakis, K., Barnes, L. L., & Schneider, J. A. (2020) · Neuropsychology Review · doi:10.1007/s11065-020-09460-6 · Cited by 62
Liu, Y., Yue, L., Xiao, S., Yang, W., Shen, D., & Liu, M. (2022) · Medical Image Analysis · doi:10.1016/j.media.2021.102266 · Cited by 58
Deep multimodal learning for lymph node metastasis prediction of primary thyroid cancer
Wu, X., Li, M., Cui, X., & Xu, G. (2022) · Physics in Medicine and Biology · doi:10.1088/1361-6560/ac4c47 · Cited by 63
“…etc. Inmedical applications, these datamodalities normally refer to amultitude of multimodal data in the formof 2D/3D image slides (e.g.,MRI/CT/PET/X-Ray/ultrasound images), clinical records, genomic, proteomic and drug data (Liu et al 2015,Mamoshina et al 2016, Simonovsky et al 2016).”
BackgroundWang, S., Wang, H., Shen, Y., & Wang, X. (2018) · International Conference on Machine Learning and Applications · doi:10.1109/icmla.2018.00083 · Cited by 59
“[24] trained a deep neural network contained autoencoders to combine multimodal features which were extracted from 83 ROIs of PET and MRI scans.”
MethodLazli, L., Boukadoum, M., & Mohamed, O. A. (2020) · Applied Sciences · doi:10.3390/app10051894 · Cited by 64
Deep-learning-based classification of FDG-PET data for Alzheimer's disease categories
Singh, S., Srivastava, A., Mi, L., Chen, K., Wang, Y., Caselli, R. J., Goradia, D. D., & Reiman, E. M. (2017) · International Symposium on Medical Information Processing and Analysis (SIPAIM) · doi:10.1117/12.2294537 · Cited by 66
Toshkhujaev, S., Lee, K. H., Choi, K. Y., Lee, J. J., Kwon, G., Gupta, Y., & Lama, R. K. (2020) · Journal of Healthcare Engineering · doi:10.1155/2020/3743171 · Cited by 57
“Recently, Liu et al. [14] proposed deep learning based on multiclass classification among normal control (NC), MCI not converted (ncMCI), MCI transformers converted (cMCI), and AD patients grounded on 83 ROI of MRI images and the conforming disclosed PET images.”
BackgroundNagasato, D., Tabuchi, H., Ohsugi, H., Masumoto, H., Enno, H., Ishitobi, N., Sonobe, T., Kameoka, M., Niki, M., & Mitamura, Y. (2019) · International Journal of Ophthalmology · doi:10.18240/ijo.2019.01.15 · Cited by 56
Nagasato, D., Tabuchi, H., Masumoto, H., Enno, H., Ishitobi, N., Kameoka, M., Niki, M., & Mitamura, Y. (2019) · PLoS ONE · doi:10.1371/journal.pone.0223965 · Cited by 57
Deep Neural Generative Model of Functional MRI Images for Psychiatric Disorder Diagnosis
Matsubara, T., Tashiro, T., & Uehara, K. (2019) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2019.2895663 · Cited by 58
“es have attempted to find specific biomarkers of neurological and psychiatric disorders in brain images using machine learning techniques [2], e.g., for schizophrenia [3], [4], Alzheimer’s disease (AD) [5]– [9], and others [10]–[14]. Resting-state fMRI (rs-fMRI) has received considerable attention [7], [11], [13]. This…”
MethodHow Big Data and High-Performance Computing Drive Brain Science
Chen, S., He, Z., Han, X., He, X., Li, R., Zhu, H., Zhao, D., Dai, C., Zhang, Y., Lu, Z., et al. (2019) · Genomics Proteomics & Bioinformatics · doi:10.1016/j.gpb.2019.09.003 · Cited by 59
“Payan [28] used 3D-CNN to achieve accuracy (cid”
BackgroundMethodImproved detection performance in blood cell count by an attention-guided deep learning method
Jiang, Z., Liu, X., Yan, Z., Gu, W., & Jiang, J. (2021) · OSA Continuum · doi:10.1364/osac.413787 · Cited by 53
Garg, N., Choudhry, M. S., & Bodade, R. M. (2022) · Journal of Neuroscience Methods · doi:10.1016/j.jneumeth.2022.109745 · Cited by 68
Qureshi, M. N. I., Ryu, S., Song, J., Lee, K. H., & Lee, B. (2019) · Frontiers in Aging Neuroscience · doi:10.3389/fnagi.2019.00008 · Cited by 54
“Among these, there are numerous studies that classified dementia, MCI, and healthy individuals (Suk and Shen, 2013; Liu et al., 2015; Suk et al., 2015).”
BackgroundForouzannezhad, P., Abbaspour, A., Li, C., Fang, C., Williams, U., Cabrerizo, M., Barreto, A. B., Andrian, J. H., Rishe, N. D., Curiel, R. E., et al. (2019) · Journal of Neuroscience Methods · doi:10.1016/j.jneumeth.2019.108544 · Cited by 52
“…(APOE) ε 4 allele (Li et al., 2017, 2017b), Amyloid β ( Aβ ) (Bateman et al., 2012; Clark et al., 2016), and combination of biomarkers (Liu et al., 2015; Westman et al., 2012; Yuan et al., 2012; Ithapu et al., 2015; Duara et al., 2013) to predict AD and its different conversion phases.”
MUFASA: Multimodal Fusion Architecture Search for Electronic Health Records
Xu, Z., So, D. R., & Dai, A. M. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i12.17260 · Cited by 52
A novel Alzheimer’s disease detection approach using GAN-based brain slice image enhancement
Bai, T., Du, M., Li, Z., Ren, L., Ruan, L., Yang, Y., Qian, G., Meng, Z., Zhao, L., & Deen, M. J. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.04.012 · Cited by 59
“Some studies [4,17–21], to obtain high accuracy under the circumstance of less labeled training samples, combined sparse auto-encoders with 3D convolutional neural networks (3D-CNNs), and performed better than 2D-CNNs on slices in their experiment, which shows a good potential of 3D approach to…”
Sonobe, T., Tabuchi, H., Ohsugi, H., Masumoto, H., Ishitobi, N., Morita, S., Enno, H., & Nagasato, D. (2018) · International Ophthalmology · doi:10.1007/s10792-018-1016-x · Cited by 52
Forouzannezhad, P., Abbaspour, A., Li, C., Cabrerizo, M., & Adjouadi, M. (2018) · International Conference on Machine Learning and Applications · doi:10.1109/icmla.2018.00218 · Cited by 52
MUFASA: Multimodal Fusion Architecture Search for Electronic Health Records
Xu, Z., So, D. R., & Dai, A. M. (2021) · arXiv · doi:10.48550/arxiv.2102.02340 · Cited by 52
“…fusion strategies are data-level or early fusion (Valada et al. 2016; Rajkomar et al. 2018); intermediate-level or hybrid fusion (Liang et al. 2014; Liu et al. 2014); and classifier-level or late fusion (Kahou et al. 2016; Simonyan and Zisserman 2014) (See Figure 2 for an example of each strategy).”
BackgroundA Survey of Deep Learning for Alzheimer’s Disease
Zhou, Q., Wang, J., Yu, X., Wang, S., & Zhang, Y. (2023) · Machine Learning and Knowledge Extraction · doi:10.3390/make5020035 · Cited by 68
“Liu, Liu, Cai, Che, Pujol, Kikinis, Feng and Fulham [230] performed the zero-masking of a single modality for a stacked autoencoder, which took both MRI and PET as input and achieved the fusion of the two modalities through data reconstruction of one zeromasked modality with only the other modality.”
BackgroundMethodInfluentialAnter, A. M., Wei, Y., Su, J., Yuan, Y., Lei, B., Duan, G., Mai, W., Nong, X., Yu, B., Li, C., et al. (2019) · Information Sciences · doi:10.1016/j.ins.2019.07.026 · Cited by 52
Li, A., Li, F., Elahifasaee, F., Liu, M., Zhang, L., & Initiative, T. A. D. N. (2021) · Brain Imaging and Behavior · doi:10.1007/s11682-020-00427-y · Cited by 54
“Liu et al. (2015) proposed a novel diagnostic framework with the deep-stacked autoencoder to learn high-level features of ROIs and with a zero-masking strategy for fusion of features from multiple image modalities.”
BackgroundHazarika, R. A., Maji, A. K., Sur, S. N., Paul, B. S., & Kandar, D. (2021) · IEEE Access · doi:10.1109/access.2021.3072559 · Cited by 57
“One of the major advantages of using the multi-modal approaches is that these methods are competent in wrapping multimodal neuro-imaging features together which requires fewer labeled data as well [202].”
BackgroundPei, Z., Wan, Z., Zhang, Y., Wang, M., Leng, C., & Yang, Y. (2022) · Pattern Recognition · doi:10.1016/j.patcog.2022.108825 · Cited by 55
Yan, B., Li, Y., Li, L., Yang, X., Li, T., Yang, G., & Jiang, M. (2022) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2022.105944 · Cited by 51
Ahmed, S., Kim, B. C., Lee, K. H., Jung, H. Y., & Initiative, A. D. N. (2020) · PLoS ONE · doi:10.1371/journal.pone.0242712 · Cited by 62
“11% [11] ADNI MRI+PET Region Stacked Sparse AE+Zero Mask + SoftMax 91.”
BackgroundTran, A. T., Zeevi, T., & Payabvash, S. (2025) · BioMedInformatics · doi:10.3390/biomedinformatics5020020 · Cited by 73
Acar, E., Schenker, C., Levin‐Schwartz, Y., Calhoun, V. D., & Adalı, T. (2019) · Frontiers in Neuroscience · doi:10.3389/fnins.2019.00416 · Cited by 49
Chen, H., Guo, H., Xing, L., Chen, D., Yuan, T., Zhang, Y., & Zhang, X. (2023) · IET Image Processing · doi:10.1049/ipr2.12841 · Cited by 48
Costa, L., Gago, M. F., Yelshyna, D., Ferreira, J., da Silva, H. D. M., Rocha, L. A., Sousa, N., & Bicho, E. G. (2016) · Computational Intelligence and Neuroscience · doi:10.1155/2016/3891253 · Cited by 59
“DBNs are a recent machine-learning model that is exhibiting performance records on classification accuracy also on medical fields such as AD, based on MRI/PET neuroimaging data [14, 15].”
BackgroundMultilevel Feature Representation of FDG-PET Brain Images for Diagnosing Alzheimer's Disease
Pan, X., Adel, M., Fossati, C., Gaidon, T., & Guedj, É. (2018) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2018.2857217 · Cited by 50
“[13] developed a method under deep learning architecture which used a zero-masking strategy for data fusion to extract complementary information from MRI and FDG-PET.”
Zheng, C., Xia, Y., Pan, Y., & Chen, J. (2015) · Brain Informatics · doi:10.1007/s40708-015-0027-x · Cited by 49
“The recent studies also suggest that deep learning, which is usually based on a hierarchical ANN, is effective in capturing high-level variations of brain images and improves the dementia classification [107–109].”
BackgroundArtificial intelligence based smart diagnosis of alzheimer's disease and mild cognitive impairment
Farooq, A., Anwar, S. M., Awais, M., & Alnowami, M. R. (2017) · IEEE International Smart Cities Conference (ISC2) · doi:10.1109/isc2.2017.8090871 · Cited by 54
“[9] used zero-masking strategy for fusing data from MRI, PET and CSF and trained a stacked autoencoder (SAE) network for classification.”
MethodXu, J., & Zhang, M. (2019) · ACS Chemical Neuroscience · doi:10.1021/acschemneuro.9b00207 · Cited by 52
Maruoka, S., Tabuchi, H., Nagasato, D., Masumoto, H., Chikama, T.-I., Kawai, A., Oishi, N., Maruyama, T., Kato, Y., Hayashi, T., et al. (2020) · Cornea · doi:10.1097/ico.0000000000002279 · Cited by 47
Wang, M., Shao, W., Huang, S., & Zhang, D. (2023) · Medical Image Analysis · doi:10.1016/j.media.2023.102883 · Cited by 56
“In many existing studies, it has been shown that integrating multi-modal data can improve clinical diagnosis (Jie et al., 2015; Li et al., 2015; Peng et al., 2016; Lei et al., 2017; Adeli et al., 2019; Liu et al., 2015; Suk et al., 2016).”
Detection of Alzheimer’s Disease Using Deep Convolutional Neural Network
Kaur, S., Gupta, S., Singh, S., & Gupta, I. (2021) · International Journal of Image and Graphics · doi:10.1142/s021946782140012x · Cited by 49
Bhatkoti, P., & Paul, M. (2016) · International Conference on Image and Vision Computing New Zealand (IVCNZ) · doi:10.1109/ivcnz.2016.7804459 · Cited by 46
MMTFN : Multi‐modal multi‐scale transformer fusion network for Alzheimer's disease diagnosis
Miao, S., Xu, Q., Li, W., Yang, C., Sheng, B., Liu, F., Bezabih, T. T., & Xiao, Y. (2023) · International Journal of Imaging Systems and Technology · doi:10.1002/ima.22970 · Cited by 55
“Recent years of multi-modal end-to-end AD recognition approaches 20 – 24 have shown that the complement of images from different device sources of Alzheimer's patients can improve the possibility of disease recognition performance.”
InfluentialAghdam, M. A., Bozdag, S., Saeed, F., & Initiative, A. D. N. (2025) · Brain Informatics · doi:10.1186/s40708-025-00252-3 · Cited by 68
Nagasawa, T., Tabuchi, H., Masumoto, H., Enno, H., Niki, M., Ohsugi, H., & Mitamura, Y. (2018) · PeerJ · doi:10.7717/peerj.5696 · Cited by 43
Han, R., Liu, Z., & Chen, C. L. P. (2022) · Applied Soft Computing · doi:10.1016/j.asoc.2022.108660 · Cited by 47
“ROI-SVM and ROI-SAE [46] are both diagnosis algorithms based on ROI definition.”
Zheng, B., Gao, A., Huang, X., Li, Y., Liang, D., & Long, X. (2022) · IET Image Processing · doi:10.1049/ipr2.12618 · Cited by 53
Tao, L., Zhang, C., Zeng, L., Zhu, S., Li, N., Li, W., Zhang, H., Zhao, Y., Zhan, S., & Ji, H. (2020) · JMIR Medical Informatics · doi:10.2196/16912 · Cited by 42
“Similar diagnostic tools based on different AI algorithms had good accuracy for the detection of lymph node metastases in women with breast cancer [1], dermatologist-level classification of skin cancer [4], diabetic retinopathy and diabetic macular edema [41], and multiclass diagnosis of Alzheimer disease [42].”
MethodQiao, J., Lv, Y., Cao, C., Wang, Z., & Li, A. (2018) · Frontiers in Aging Neuroscience · doi:10.3389/fnagi.2018.00417 · Cited by 43
“Advanced deep learning techniques have been successfully applied for the diagnosis of AD based on PET and sMRI (Suk and Shen, 2013; Liu S. et al., 2015; Ortiz et al., 2016; Lu et al., 2018; Shi et al., 2018).”
MethodBhattacharya, S., Prusty, S., Pande, S. P., Gulhane, M., Lavate, S. H., Rakesh, N., & Veerasamy, S. (2025) · Frontiers in Human Neuroscience · doi:10.3389/fnhum.2025.1552178 · Cited by 41
“Liu et al. (2015) achieved 93.2% accuracy using ADNI with multimodal neuroimaging features, while Lu et al. (2018) achieved 95.6% accuracy with a deep neural network on the same dataset.”
InfluentialInitiative, T. A. D. N., Chen, X., Zhang, H., Lee, S., & Shen, D. G. (2017) · Neuroinformatics · doi:10.1007/s12021-017-9330-4 · Cited by 44
Classification of Alzheimer’s Disease by Cascaded Convolutional Neural Networks Using PET Images
Cheng, D., & Liu, M. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-67389-9_13 · Cited by 40
“[7] extracted a set of latent features from 83 ROIs of the MRI and PET scans and trained a multi-layered neural network consisting of several auto-encoders to combine multimodal features for classification.”
MethodMachine learning for bioinformatics and neuroimaging
Serra, A., Galdi, P., & Tagliaferri, R. (2018) · Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery · doi:10.1002/widm.1248 · Cited by 46
“In Liu et al. (2015), a multilayered neural network consisting of several AEs and a soft-max layer is used for the diagnostic of the Alzheimer ’ s disease.”
MethodMulti-modal AD classification via self-paced latent correlation analysis
Zhu, Q., Yuan, N., Huang, J., Hao, X., & Zhang, D. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.04.066 · Cited by 40
Wang, S., Wang, H., Cheung, A. C., Shen, Y., & Gan, M. (2020) · Advances in intelligent systems and computing · doi:10.1007/978-981-15-1816-4_4 · Cited by 40
Employing multimodal co-learning to evaluate the robustness of sensor fusion for industry 5.0 tasks
Rahate, A., Mandaokar, S., Chandel, P., Walambe, R. A., Ramanna, S., & Kotecha, K. V. (2022) · Soft Computing · doi:10.1007/s00500-022-06802-9 · Cited by 40
“Multimodal fusion is used in multiple domains such as automotive (Kim and Ghosh 2016) (Chen et al. 2017), medical imaging (Kiros et al. 2014) (Liu et al. 2015b), and affective computing (Poria et al. 2017) (Zhang et al. 2020).”
BackgroundKim, J. S., Han, J. W., Bae, J. B., Moon, D. G., Shin, J. Y., Kong, J. E., Lee, H., Yang, H. W., Lim, E., Kim, J. Y., et al. (2022) · Scientific Reports · doi:10.1038/s41598-022-22917-3 · Cited by 48
Metadata
- Authors
- Liu, S., Liu, S., Cai, W., Che, H., Pujol, S., Kikinis, R., Feng, D., Fulham, M. J., & ADNI
- Affiliations
- Brigham and Women's Hospital (US)
- The University of Sydney (AU)
- ORCID
- Venue
- IEEE Transactions on Biomedical Engineering
- Published
- 2015-04
- Volume
- 62
- Issue
- 4
- Pages
- 1132-1140
- ISSN
- 0018-9294 (ISSN-L)
- 1558-2531
- PMC
- PMC4394860
- OpenAlex
- W2130371234
- Cited by
- 637
- References
- 76
- Citations by year
- 2026: 49 · 2025: 54 · 2024: 59 · 2023: 68 · 2022: 64 · 2021: 64 · 2020: 63 · 2019: 95 · 2018: 53 · 2017: 44 · 2016: 18 · 2015: 5
- FWCI
- 17.04
- Type
- journal article
- Language
- en
- Open access
- green
- www.ncbi.nlm.nih.gov
- Locations
- IEEE Transactions on Biomedical Engineering (publishedVersion)
- PubMed (publishedVersion)
- PubMed Central (acceptedVersion)
- The Sydney eScholarship Repository (The University of Sydney) (submittedVersion)
- Funders
- ARC
- AADRF
- NA-MIC (NIH U54EB005149)
- NAC (NIH P41EB015902)
- Topics
- Health Sciences › Medicine › Psychiatry and Mental health › Dementia and Cognitive Impairment Research
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Life Sciences › Neuroscience › Cellular and Molecular Neuroscience › Alzheimer's disease research and treatments
- Keywords
- Alzheimer's disease, computer-aided diagnosis, multimodal neuroimaging, representation learning, data fusion, neuroimaging biomarkers, multi-class classification, deep learning, early diagnosis
- MeSH terms
- Alzheimer Disease, Brain, Humans, Image Interpretation, Computer-Assisted, Neuroimaging, Support Vector Machine, Multimodal Imaging
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.