A Deep Learning Model to Predict a Diagnosis of Alzheimer Disease by Using 18 F-FDG PET of the Brain
Open accessThe DOI matches its Crossref record; 24 of the 24 references it cites were found in a registry or an index.
Abstract
Purpose To develop and validate a deep learning algorithm that predicts the final diagnosis of Alzheimer disease (AD), mild cognitive impairment, or neither at fluorine 18 (18F) fluorodeoxyglucose (FDG) PET of the brain and compare its performance to that of radiologic readers. Materials and Methods Prospective 18F-FDG PET brain images from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) (2109 imaging studies from 2005 to 2017, 1002 patients) and retrospective independent test set (40 imaging studies from 2006 to 2016, 40 patients) were collected. Final clinical diagnosis at follow-up was recorded. Convolutional neural network of InceptionV3 architecture was trained on 90% of ADNI data set and tested on the remaining 10%, as well as the independent test set, with performance compared to radiologic readers. Model was analyzed with sensitivity, specificity, receiver operating characteristic (ROC), saliency map, and t-distributed stochastic neighbor embedding. Results The algorithm achieved area under the ROC curve of 0.98 (95% confidence interval: 0.94, 1.00) when evaluated on predicting the final clinical diagnosis of AD in the independent test set (82% specificity at 100% sensitivity), an average of 75.8 months prior to the final diagnosis, which in ROC space outperformed reader performance (57% [four of seven] sensitivity, 91% [30 of 33] specificity; P < .05). Saliency map demonstrated attention to known areas of interest but with focus on the entire brain. Conclusion By using fluorine 18 fluorodeoxyglucose PET of the brain, a deep learning algorithm developed for early prediction of Alzheimer disease achieved 82% specificity at 100% sensitivity, an average of 75.8 months prior to the final diagnosis. © RSNA, 2018 Online supplemental material is available for this article. See also the editorial by Larvie in this issue.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Recent studies have shown that short videos captured on consumer-grade technology can detect Parkinsonism.69,70”
From Review of Artificial Intelligence for Clinical Use in Alzheimer's Disease and Related Dementias (2026) · cites this paper as [69]
In the citing paper
“a deep learning algorithm analysing FDG-PET data from 1002 patients predicted AD diagnosis 6.3 years before clinical manifestation with 82% specificity and 100% sensitivity by detecting metabolic shifts in posterior cingulate regions”
From Multimodal neuroimaging and AI integration in cognitive disorders: advances, challenges, and future directions for precision medicine (2026) · cites this paper as Ding et al., 2019
In the citing paper
“Ding et al. (2018) used deep learning algorithm with fluorine, 18F-FDG PET scan of the brain for early prediction of AD. They attained 82% specificity with 100% sensitivity, at an average of 75.8 months ahead of the final diagnosis.”
From Recent Advancements in Pathogenesis, Diagnostics and Treatment of Alzheimer’s Disease (2020) · cites this paper as [138]
In the citing paper
“The deep learning algorithm developed itself learning from 90% of the dataset and then tested it on the remaining 10% of the dataset. Through deep learning, the algorithm trained itself to read metabolic patterns that correlated to Alzheimer’s and was able to predict every single case of AD.”
From Recent Advancements in Pathogenesis, Diagnostics and Treatment of Alzheimer’s Disease (2020) · cites this paper as [138]
Citations
Cites
McKhann, 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
McKhann, G. M., Knopman, D. S., Chertkow, H., Hyman, B. T., Jack, C. R., Kawas, C. H., Klunk, W. E., Koroshetz, W. J., Manly, J. J., Mayeux, R., et al. (2011) · Alzheimer's & Dementia · doi:10.1016/j.jalz.2011.03.005 · Cited by 18,657
pROC: an open-source package for R and S+ to analyze and compare ROC curves
Robin, X., Turck, N., Hainard, A., Tiberti, N., Lisacek, F., Sanchez, J.-C., & Müller, M. (2011) · BMC Bioinformatics · doi:10.1186/1471-2105-12-77 · Cited by 13,697
Forecasting the global burden of Alzheimer's disease
Brookmeyer, R., Johnson, E., Ziegler‐Graham, K., & Arrighi, H. M. (2007) · Alzheimer's & Dementia · doi:10.1016/j.jalz.2007.04.381 · Cited by 3,370
Scheltens, P., Blennow, K., Breteler, M. M. B., de Strooper, B., Frisoni, G. B., Salloway, S., & Van der Flier, W. M. (2016) · The Lancet · doi:10.1016/s0140-6736(15)01124-1 · Cited by 3,125
Jack, C. R., Albert, M. S., Knopman, D. S., McKhann, G. M., Sperling, R. A., Carrillo, M. C., Thies, B., & Phelps, C. H. (2011) · Alzheimer's & Dementia · doi:10.1016/j.jalz.2011.03.004 · Cited by 2,042
Brookmeyer, R., Gray, S., & Kawas, C. (1998) · American Journal of Public Health · doi:10.2105/ajph.88.9.1337 · Cited by 1,787
2014 IEEE Conference on Computer Vision and Pattern Recognition
(2014) · doi:10.1109/cvpr20399.2014 · Cited by 1,774
The Alzheimer's Disease Neuroimaging Initiative
Mueller, S. G., Weiner, M. W., Thal, L. J., Petersen, R. C., Jack, C., Jagust, W., Trojanowski, J. Q., Toga, A. W., & Beckett, L. (2005) · Neuroimaging Clinics of North America · doi:10.1016/j.nic.2005.09.008 · Cited by 1,525
Setio, A. A. A., Ciompi, F., Litjens, G., Gerke, P., Jacobs, C., van Riel, S. J., Wille, M. M. W., Naqibullah, M., Sanchez, C. I., & van Ginneken, B. (2016) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2016.2536809 · Cited by 1,258
Research works printed but not linked: 3
- van der Maaten L, 2008, J Mach Learn Res, 9, 2579
- Pedregosa F, 2011, J Mach Learn Res, 12, 2825
- Nie D, 2016, Med Image Comput Comput Assist Interv, 9901, 212
Cited by
Items 201–300 of 596
Kumari, R., Nigam, A., & Pushkar, S. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-07076-w · Cited by 28
“[74] Deep Neural Network FDG-PET 73 73 59”
Schuhmacher, D., Schörner, S., Küpper, C., Großerueschkamp, F., Sternemann, C., Lugnier, C., Kraeft, A., Jütte, H., Tannapfel, A., Reinacher‐Schick, A., et al. (2022) · Medical Image Analysis · doi:10.1016/j.media.2022.102594 · Cited by 26
S, N. N. R., & Priyadarshini, J. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-07750-z · Cited by 26
“Yechong Huang et al. [15] and Yiming Ding et al. [16] had done their AD diagnosis work using a Convolutional Neural Network (CNN).”
MethodHinton, B., Ma, L., Mahmoudzadeh, A. P., Malkov, S., Fan, B., Greenwood, H. I., Joe, B. N., Lee, V., Kerlikowske, K. M., & Shepherd, J. A. (2019) · Cancer Imaging · doi:10.1186/s40644-019-0227-3 · Cited by 26
“Various methods exist to input images from multiple views, from inputting images individually, to making separate networks for each view, to combining the images as a collage [38].”
MethodBarnard, L., Botha, H., Corriveau-Lecavalier, N., Graff-Radford, J., Dicks, E., Gogineni, V., Zhang, G., Burkett, B. J., Johnson, D. R., Huls, S. J., et al. (2025) · Neurology · doi:10.1212/wnl.0000000000213831 · Cited by 25
Construction and imaging of a neurovascular unit model
Dong, T., Wang, J., Li, M., Gao, F., & Wei, P. (2021) · Neural Regeneration Research · doi:10.4103/1673-5374.332131 · Cited by 27
“18F-FDG PET is helpful in identifying mild cognitive impairment and predicting the development of AD with higher sensitivity and specificity (Ding et al., 2019; Chung et al., 2020; Li et al., 2020b).”
BackgroundHammond, T. C., & Lin, A. (2022) · Journal of Cellular Immunology · doi:10.33696/immunology.4.128 · Cited by 29
“8 months prior to its final diagnosis with 82% specificity and 100% sensitivity [18].”
BackgroundArtificial intelligence: Potential tool to subside SARS-CoV-2 pandemic
Gopinath, N. (2021) · Process Biochemistry · doi:10.1016/j.procbio.2021.08.001 · Cited by 25
“With an estimated 180 million cases and 3.9 million deaths as of July 2021 according to world meter, the various efforts being made have yet to bring an end to the global pandemic [10,11].”
InfluentialAlzheimer's disease diagnostic accuracy by fluid and neuroimaging ATN framework
Xiong, X., He, H., Ye, Q., Qian, S., Zhou, S., Feng, F., Fang, E. F., & Xie, C. (2023) · CNS Neuroscience & Therapeutics · doi:10.1111/cns.14357 · Cited by 27
Multiscale spatial gradient features for 18F-FDG PET image-guided diagnosis of Alzheimer’s disease
Pan, X., Adel, M., Fossati, C., Gaidon, T., Wojak, J., & Guedj, É. (2019) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2019.105027 · Cited by 24
AutoEncoder-based feature ranking for Alzheimer Disease classification using PET image
Tuấn, P. M., Phan, T.-L., Adel, M., Guedj, É., & Trung, N. L. (2021) · Machine Learning with Applications · doi:10.1016/j.mlwa.2021.100184 · Cited by 23
Alzheimer's Disease Prediction using Machine Learning and Transfer Learning Models
Amrutesh, A., G, G. B. C., Amruthamsh, A., Asha Rani, K. P., & Gowrishankar, S. (2022) · International Conference on Computation System and Information Technology for Sustainable Solutions (CSITSS) · doi:10.1109/csitss57437.2022.10026365 · Cited by 23
“Bernoulli A machine learning version of the Naive Bayes algorithm is called Naive Bayes [19].”
BackgroundMethodInfluentialBroad learning for early diagnosis of Alzheimer's disease using FDG-PET of the brain
Duan, J., Liu, Y., Wu, H., Wang, J., Chen, L., & Chen, C. L. P. (2023) · Frontiers in Neuroscience · doi:10.3389/fnins.2023.1137567 · Cited by 27
“Some researchers have attempted to analyze 18F-FDG-PET for AD predictions, but these studies have yielded limited success (Liu et al., 2018; Lu et al., 2018; Pan et al., 2018; Ding et al., 2019; Huang et al., 2019; Hamdi et al., 2022).”
BackgroundA survey on artificial intelligence in pulmonary imaging
Saha, P. K., Nadeem, S. A., & Comellas, A. P. (2023) · Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery · doi:10.1002/widm.1510 · Cited by 26
Multi input–Multi output 3D CNN for dementia severity assessment with incomplete multimodal data
Gravina, M., Garcia-Pedrero, A. M., Gonzalo‐Martín, C., Sansone, C., & Soda, P. (2024) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2024.102774 · Cited by 26
Longitudinal Pooling & Consistency Regularization to Model Disease Progression From MRIs
Ouyang, J., Zhao, Q., Sullivan, E. V., Pfefferbaum, A., Tapert, S. F., Adeli, E., & Pohl, K. M. (2020) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2020.3042447 · Cited by 29
“Therefore, it is conceivable that the findings discussed herein are likely to generalize to more advanced network architectures [77]–[79].”
Sutoko, S., Masuda, A., Kandori, A., Sasaguri, H., Saito, T., Saido, T. C., & Funane, T. (2021) · iScience · doi:10.1016/j.isci.2021.102198 · Cited by 24
Mukherji, D., Mukherji, M., Mukherji, N., & Initiative, A. D. N. (2022) · Brain Informatics · doi:10.1186/s40708-022-00169-1 · Cited by 27
Deep Learning Techniques for the Effective Prediction of Alzheimer’s Disease: A Comprehensive Review
Shastry, K. A., Vijayakumar, V., Manoj Kumar, M., V, Manjunatha, B. A., & Chandrashekhar, B. (2022) · Healthcare · doi:10.3390/healthcare10101842 · Cited by 28
Recognition of weeds in corn crops: System with convolutional neural networks
Wessner, R. N., Frozza, R., BAGATINI, D. D. D. S., & Molz, R. F. (2023) · Journal of Agriculture and Food Research · doi:10.1016/j.jafr.2023.100669 · Cited by 22
An Early Detection and Classification of Alzheimer's Disease Framework Based on ResNet-50
Nithya, V. P., Mohanasundaram, N., & Santhosh, R. (2023) · Current Medical Imaging Formerly Current Medical Imaging Reviews · doi:10.2174/1573405620666230825113344 · Cited by 32
Musculoskeletal radiographs classification using deep learning
Harini, N., Ramji, B., Sriram, S., Sowmya, V., & Soman, K. P. (2020) · Elsevier eBooks · doi:10.1016/b978-0-12-819764-6.00006-5 · Cited by 22
Anatomical Landmarks and DAG Network Learning for Alzheimer’s Disease Diagnosis
Tian, Z., Cao, C., Wang, Z., Xu, G., & Qiao, J. (2020) · IEEE Access · doi:10.1109/access.2020.3037107 · Cited by 24
“The metabolic level of glucose in fluorodeo-xygluce positron emission tomography (FDG-PET) is measured as AD neuron dysfunction [14], [15].”
MethodBuvat, I., & Orlhac, F. (2021) · Journal of Nuclear Medicine · doi:10.2967/jnumed.120.261586 · Cited by 25
Use of Artificial Intelligence in Imaging Dementia
Aljuhani, M., Ashraf, A., & Edison, P. (2024) · Cells · doi:10.3390/cells13231965 · Cited by 22
Kaushik, D. K., Jangra, P., Verma, R., Purohit, D., Pandey, P., Sharma, S., & Sharma, R. K. (2021) · Journal of Biosciences · doi:10.1007/s12038-021-00147-5 · Cited by 22
“The RPs are generally administered by oral, intravenous, and inhalation routes to study the functioning of various organs such as lungs, heart, kidney, brain, blood circulation, and bone metabolism (Drozdovitch et al. 2015; Payolla et al. 2019).”
BackgroundUnderstanding the Research Landscape of Deep Learning in Biomedical Science: Scientometric Analysis
Nam, S., Kim, D., Jung, W., & Zhu, Y. (2022) · Journal of Medical Internet Research · doi:10.2196/28114 · Cited by 24
“Inception Brain positron emission tomography with Alzheimer Classification A17 [59]”
MethodLi, C., Wang, Q., Liu, X., & Hu, B. (2022) · Frontiers in Aging Neuroscience · doi:10.3389/fnagi.2022.930584 · Cited by 21
“…alleviate this problem by not requiring many pre-processing steps on the data, and just feeding the simply processed data to the algorithmic model, which can be trained to learn the features of the data and can classify and identify AD (Ding et al., 2019; Sharma et al., 2020; Suh et al., 2020).”
BackgroundNeural networks from biological to artificial and vice versa
Baba, A. (2024) · Biosystems · doi:10.1016/j.biosystems.2023.105110 · Cited by 23
Artificial intelligence in assessment of hepatocellular carcinoma treatment response
Spieler, B. M., Sabottke, C. F., Moawad, A. W., Gabr, A., Bashir, M. R., Gian, R. K., Yaghmai, V., Rozenberg, R., Gerena, M., Yacoub, J. H., et al. (2021) · Abdominal Radiology · doi:10.1007/s00261-021-03056-1 · Cited by 21
Das, N., Ren, J., Spence, J. S., & Chapman, S. B. (2021) · Frontiers in Neuroscience · doi:10.3389/fnins.2021.641739 · Cited by 22
“The model showed a sensitivity of 100% and specificity of 82% in predicting the final diagnosis within an average timeline of 75.8 months before the AD diagnosis (Ding et al., 2019).”
BackgroundInfluentialIs a PET All You Need? A Multi-modal Study for Alzheimer’s Disease Using 3D CNNs
Narazani, M., Sarasúa, I., Pölsterl, S., Lizarraga, A., Yakushev, I. Y., & Wachinger, C. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-16431-6_7 · Cited by 31
Addressing the challenges of artificial intelligence in medicine
Smith, M., & Jeffery, R. C. H. (2020) · Internal Medicine Journal · doi:10.1111/imj.15017 · Cited by 23
Generating and Weighting Semantically Consistent Sample Pairs for Ultrasound Contrastive Learning
Chen, Y., Zhang, C., Ding, C. H. Q., & Liu, L. (2022) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2022.3228254 · Cited by 21
“disease [27], and abnormalities with X-ray [28].”
Kim, N. J., Oh, J., Kim, S., Cha, J., Choi, J., Im, S. G., Choi, S., & Jang, B. C. (2024) · Advanced Functional Materials · doi:10.1002/adfm.202305136 · Cited by 21
Verde, F., Stanzione, A., Romeo, V., Cuocolo, R., Maurea, S., & Brunetti, A. (2019) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-019-00246-8 · Cited by 24
Syed, K., Sleeman, W. C., Nalluri, J. J., Kapoor, R., Hagan, M., Palta, J. R., & Ghosh, P. (2020) · Elsevier eBooks · doi:10.1016/b978-0-12-817133-2.00002-1 · Cited by 26
Alzheimer’s Disease Detection Using Ensemble Learning and Artificial Neural Networks
Bandyopadhyay, A., Ghosh, S., Bose, M., Singh, A., Othmani, A., & Santosh, K. (2023) · Communications in computer and information science · doi:10.1007/978-3-031-23599-3_2 · Cited by 19
García‐Gutiérrez, F., Hernández-Lorenzo, L., Cabrera‐Martín, M. N., Matías‐Guiu, J. A., & Ayala, J. L. (2024) · NeuroImage · doi:10.1016/j.neuroimage.2024.120695 · Cited by 24
“So far, most work has focused on differentiating clinical 11–13, 16, 17], predicting cognitive decline [21, 22, 68, 69], or atrophy progression [14, 25, 70].”
BackgroundDetection of Alzheimer’s disease using ECD SPECT images by transfer learning from FDG PET
Ni, Y.-C., Tseng, F.-P., Pai, M., Hsiao, I., Lin, K., Lin, Z.-K., Lin, W.-B., Chiu, P., Hung, G., Chang, C., et al. (2021) · Annals of Nuclear Medicine · doi:10.1007/s12149-021-01626-3 · Cited by 19
Reith, F. H., Mormino, E. C., & Zaharchuk, G. (2021) · Alzheimer s & Dementia Translational Research & Clinical Interventions · doi:10.1002/trc2.12212 · Cited by 22
Prats-Climent, J., Gandia‐Ferrero, M. T., Torres-Espallardo, I., Álvarez‐Sánchez, L., Martínez‐Sanchis, B., Cháfer‐Pericás, C., Junquero, I. G.-R., Cerdá-Alberich, L., Aparici, F., Baquero‐Toledo, M., et al. (2022) · Journal of Medical Systems · doi:10.1007/s10916-022-01836-w · Cited by 21
“Another limitation of the study is thought to be the small size of the dataset, compared with other studies [24] which are of the order of thousands of images in the training process.”
BackgroundMethodResultInfluentialLongitudinal MRI analysis using a hybrid DenseNet-BiLSTM method for Alzheimer's disease prediction
Jomeiri, A., Navin, A. H., & Shamsi, M. (2024) · Behavioural Brain Research · doi:10.1016/j.bbr.2024.114900 · Cited by 21
Chen, M.-W., Zhu, H., Xiong, C., Li, J., Zhao, L., Chen, H., & Qiu, Y. L. (2019) · Cellular and Molecular Neurobiology · doi:10.1007/s10571-019-00752-x · Cited by 19
Can DXA image-based deep learning model predict the anisotropic elastic behavior of trabecular bone?
Xiao, P., Haque, E., Zhang, T., Dong, X., Huang, Y., & Wang, X. (2021) · Journal of the mechanical behavior of biomedical materials/Journal of mechanical behavior of biomedical materials · doi:10.1016/j.jmbbm.2021.104834 · Cited by 20
Ouyang, M., Zheng, R.-X., Wang, Y., Zuo, Z., Gu, L.-D., Tian, Y.-Q., Wei, Y., Huang, X., Tang, K., & Wang, L. (2022) · Frontiers in Oncology · doi:10.3389/fonc.2022.915871 · Cited by 18
“org 5 studies using deep learning (including the two studies discussed above) only performed single-modality analyses because integrating multimodal data is vulnerable to overfitting and poor generalization (22, 33).”
BackgroundAutomated Multimodal Fusion Technique for the Classification of Human Brain on Alzheimer’s Disorder
Vivekanandam, B. (2021) · Journal of Electrical Engineering and Automation · doi:10.36548/jeea.2021.3.005 · Cited by 18
Intraoperative Detection of Surgical Gauze Using Deep Convolutional Neural Network
Lai, S.-L., Chen, C.-S., Lin, B., & Chang, R. (2022) · Annals of Biomedical Engineering · doi:10.1007/s10439-022-03033-9 · Cited by 18
Cao, E., Ma, D., Nayak, S., & Duong, T. Q. (2023) · Neurobiology of Disease · doi:10.1016/j.nbd.2023.106310 · Cited by 19
“By contrast, DL predictions of MCI to AD conversion using whole-brain FDG-PET images are sparse (De Santi et al., 2023; Ding et al., 2019; Etminani et al., 2022; Liu et al., 2018; Yee et al., 2020; Zhou et al., 2021).”
Ni, Y.-C., Tseng, F.-P., Pai, M., Hsiao, I., Lin, K., Lin, Z.-K., Lin, C., Chiu, P., Hung, G., Chang, C., et al. (2021) · Diagnostics · doi:10.3390/diagnostics11112091 · Cited by 17
Optimal hybrid feature selection technique for diabetic retinopathy grading using fundus images
Mohan, N. J., Murugan, R., Goel, T., Mirjalili, S., Singh, Y. K., Deb, D., & Roy, P. (2023) · Sadhana · doi:10.1007/s12046-023-02175-3 · Cited by 17
Ma, D., Yee, E., Stocks, J. K., Jenkins, L. M., Popuri, K., Chausse, G., Wang, L., Probst, S., & Beg, M. F. (2021) · Journal of Alzheimer s Disease · doi:10.3233/jad-201591 · Cited by 17
“More recently, Ding and colleagues [12] validated their automatic method on an independent clinical data set.”
Li, W., Zhao, Z., Liu, M., Yan, S., An, Y., Qiao, L., Wang, G., Qi, Z., & Lu, J. (2021) · Journal of Alzheimer s Disease · doi:10.3233/jad-215338 · Cited by 16
Workflow Integration of Research AI Tools into a Hospital Radiology Rapid Prototyping Environment
Kanakaraj, P., Ramadass, K., Bao, S., Basford, M., Jones, L., Lee, H. H., Xu, K., Schilling, K. G., Carr, J. J., Terry, J. G., et al. (2022) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-022-00601-2 · Cited by 18
“Research techniques/initiates implementing AI algorithms using deep convolution neural networks to detect breast cancer [2], diagnose intracranial hemorrhage [3], detect pneumonia in chest X-rays images [4], detect sepsis [4, 5], detect brain metastases [6], diagnose tumoral genetic mutations [7], diagnose neurogenera…”
BackgroundZhou, M., Zhang, Y., Liu, T., Yang, Y., & Yang, P. (2022) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3511808.3557406 · Cited by 16
“• To further show the high interpretability of our formulations, which existing deep learning methods [21][9] [12][39] [38][42] fail to have, we also identify and analyze the temporal pattern of stable MRI biomarkers.”
BackgroundDeep Learning for Perfusion Cerebral Blood Flow (CBF) and Volume (CBV) Predictions and Diagnostics
Talebi, S., Gai, S., Sossin, A., Zhu, V., Tong, E., & Mofrad, M. R. K. (2024) · Annals of Biomedical Engineering · doi:10.1007/s10439-024-03471-7 · Cited by 22
“Besides using DL for detection and segmentation intracranial abnormalities in brain images [25, 26], there are also DL models for predictions from input images [27, 28].”
MethodBaker, C., Suárez‐Méndez, I., Smith, G., Marsh, E. B., Funke, M. E., Mosher, J. C., Maestú, F., Xu, M., & Pantazis, D. (2024) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2024.3416890 · Cited by 24
“Ongoing research efforts aim to discern such patterns from the early stages of AD, even at the SCD stage, using non-invasive neuroimaging methods, including functional magnetic resonance imaging (fMRI) [12], [13], positron emission tomography (PET) [14], and magnetoencephalography (MEG) [15].”
BackgroundThulasimani, V., Shanmugavadivel, K., Cho, J., & Easwaramoorthy, S. V. (2024) · Neuropsychiatric Disease and Treatment · doi:10.2147/ndt.s496307 · Cited by 17
“Inception V3 used in 48 and Inception V4 developed in 51,57 are architectures that utilise inception modules and optimise the computational resources.”
Modeling autosomal dominant Alzheimer's disease with machine learning
Luckett, P. H., McCullough, A. A., Gordon, B. A., Strain, J. F., Flores, S. E., Dincer, A., McCarthy, J. E., Kuffner, T. A., Stern, A., Meeker, K. L., et al. (2021) · Alzheimer s & Dementia · doi:10.1002/alz.12259 · Cited by 19
“6,9,10 In ADAD, studies have shown FDG uptake in MCs is decreased in the precuneus”
Yoshida, A., Ueda, D., Higashiyama, S., Katayama, Y., Matsumoto, T., Yamanaga, T., Miki, Y., & Kawabe, J. (2022) · Annals of Nuclear Medicine · doi:10.1007/s12149-022-01726-8 · Cited by 16
Advanced brain imaging for the diagnosis of Alzheimer disease
Wang, Y.-T. T., Rosa‐Neto, P., & Gauthier, S. G. (2023) · Current Opinion in Neurology · doi:10.1097/wco.0000000000001198 · Cited by 17
Verma, K., Sikka, G., Swaraj, A., Kumar, S., & Kumar, A., V (2024) · SN Computer Science · doi:10.1007/s42979-024-02695-7 · Cited by 19
“Deep learning approaches have been widely utilized in applications involving medical image analysis such as skin cancer classification [17], breast cancer detection [18], electroencephalography (EEG) based diagnosis [19–22], brain diseases [23–25].”
Deep learning improves utility of tau PET in the study of Alzheimer's disease
Zou, J., Park, D., Johnson, A., Feng, X., Pardo, M., France, J., Tomljanovic, Z., Brickman, A. M., Devanand, D. P., Luchsinger, J. A., et al. (2021) · Alzheimer's & Dementia: Diagnosis, Assessment & Disease Monitoring · doi:10.1002/dad2.12264 · Cited by 15
“22 The main metrics of the models compare similarly with prior deep learning classification tasks that used different sets of PET radioligands, 16,22,46 though comparisons are of course difficult given differences in available clinical outcomes.”
BackgroundMethodResultInfluentialDeatsch, A. E., Perovnik, M., Namías, M., Trošt, M., Jeraj, R., & Initiative, A. D. N. (2022) · Physics in Medicine and Biology · doi:10.1088/1361-6560/ac8f10 · Cited by 15
Medenica, V., Ivanović, L., & Milošević, N. (2024) · Applied Neuropsychology Adult · doi:10.1080/23279095.2024.2364229 · Cited by 19
A review of machine learning techniques for diagnosing Alzheimer’s disease using imaging modalities
Kishore, N., & Goel, N. (2024) · Neural Computing and Applications · doi:10.1007/s00521-024-10399-5 · Cited by 15
Role of Deep Learning in Predicting Aging-Related Diseases: A Scoping Review
Wassan, J. T., Zheng, H., & Wang, H. (2021) · Cells · doi:10.3390/cells10112924 · Cited by 17
“Remarkable performance (high AUC of 98%) was achieved in studies involving DL [83] to predict AD in aging people.”
BackgroundMethodInfluentialVenugopal, V. K., Takhar, R., Gupta, S. K., Saboo, A., & Mahajan, V. (2022) · Journal of Medical Systems · doi:10.1007/s10916-022-01806-2 · Cited by 15
Komori, S., Cross, D. J., Mills, M. K., Ouchi, Y., Nishizawa, S., Okada, H., Norikane, T., Thientunyakit, T., Anzai, Y., & Minoshima, S. (2022) · Annals of Nuclear Medicine · doi:10.1007/s12149-022-01775-z · Cited by 15
What is needed to mainstream artificial intelligence in health care?
Scott, I. A., Abdel‐Hafez, A., Barras, M. A., & Canaris, S. (2021) · Australian Health Review · doi:10.1071/ah21034 · Cited by 17
Fakoya, A., & Parkinson, S. (2024) · IEEE Access · doi:10.1109/access.2024.3412850 · Cited by 16
Neuro-Symbolic Neurodegenerative Disease Modeling as Probabilistic Programmed Deep Kernels
Lavin, A. (2022) · Studies in computational intelligence · doi:10.1007/978-3-030-93080-6_5 · Cited by 20
Liu, G., Mitra, D., Jones, E. F., Franc, B. L., Behr, S. C., Nguyen, A., Bolouri, M. S., Wisner, D. J., Joe, B. N., Esserman, L. J., et al. (2021) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-021-00449-y · Cited by 16
Self-citationSavaş, S., Topaloğlu, N., Kazcı, Ö., & Koşar, P. N. (2022) · Bilişim Teknolojileri Dergisi · doi:10.17671/gazibtd.804617 · Cited by 17
Deep Learning in Healthcare: Applications, Challenges, and Opportunities
Chaki, J. (2022) · Studies in computational intelligence · doi:10.1007/978-981-19-2416-3_2 · Cited by 16
ADPM: An Alzheimer’s Disease Prediction Model for Time Series Neuroimage Analysis
Hong, X., Lin, R., Yang, C., Cai, C., & Clawson, K. (2020) · IEEE Access · doi:10.1109/access.2020.2979969 · Cited by 15
Enterprise imaging and big data: A review from a medical physics perspective
McCarthy, N., Dahlan, A., Cook, T. S., Hare, N. O., Ryan, M.-L., John, B. S., Lawlor, A., & Curran, K. M. (2021) · Physica Medica · doi:10.1016/j.ejmp.2021.04.004 · Cited by 22
“Chen et al. [133] trained a CNNs on a dataset of simultaneously acquired MRI and ultralow-dose PET, and were able to generate full-dose-like amyloid PET images, with a variation of only 89% vs 91% accuracy in intra-reader reproducibility.”
BackgroundInfluentialUsefulness of Heat Map Explanations for Deep-Learning-Based Electrocardiogram Analysis
Storås, A. M., Andersen, O. E., Lockhart, S. M., Thielemann, R., Gnesin, F., Thambawita, V. L., Hicks, S. A., Kanters, J. K., Strümke, I., Halvorsen, P., et al. (2023) · Diagnostics · doi:10.3390/diagnostics13142345 · Cited by 15
“One study explaining a deep neural network predicting Alzheimer’s disease found heat maps not to produce medical imaging biomarkers that could be interpreted by humans [24].”
BackgroundClassification of lung cancer with deep learning Res-U-Net and molecular imaging
Malligeswari, N., & Kavya, G. (2023) · Signal Image and Video Processing · doi:10.1007/s11760-023-02635-7 · Cited by 13
Kršek, A., Schleicher, L. M. S., Jagodic, A., & Batičić, L. (2025) · International Journal of Molecular Sciences · doi:10.3390/ijms26189178 · Cited by 16
A Novel Chaos Theory Inspired Neuronal Architecture
Harikrishnan, N. B., & Nagaraj, N. (2019) · IEEE Global Conference for Advancement in Technology (GCAT) · doi:10.1109/gcat47503.2019.8978360 · Cited by 13
“mimic the human brain. DL and ML algorithms have a wide variety of practical applications in computer vision, natural language processing, speech processing [6], cyber-security [7], medical diagnosis [8] etc. However, these algorithms do not use the essential 1http://yann.lecun.com/exdb/mnist/index.html 2http://archiv…”
MethodSoliman, A., Chang, J. R., Etminani, K., Byttner, S., Davidsson, A., Martínez‐Sanchis, B., Camacho, V., Bauckneht, M., Stegeran, R., Ressner, M., et al. (2022) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-022-02054-7 · Cited by 16
“Specifically, TL models have shown to be timely efficient in classifying AD dementia patients and achieving a good performance [7, 14, 15].”
BackgroundMethodDeep learning for risk-based stratification of cognitively impaired individuals
Romano, M. F., Zhou, X., Balachandra, A. R., Jadick, M. F., Qiu, S., Nijhawan, D. A., Joshi, P. S., Mohammad, S., Lee, P. H., Smith, M. J., et al. (2023) · iScience · doi:10.1016/j.isci.2023.107522 · Cited by 13
Early Diagnosis of Alzheimer’s Disease Using 18F-FDG PET With Soften Latent Representation
Rehman, A., Yi, M.-K., Majeed, A., & Hwang, S. O. (2024) · IEEE Access · doi:10.1109/access.2024.3418508 · Cited by 13
Sanganahalli, B. G., Mihailovic, J. M., Vekaria, H. J., Coman, D., Yackzan, A. T., Flemister, A., Aware, C. B., Wenger, K., Hubbard, W. B., Sullivan, P. G., et al. (2024) · Journal of Cerebral Blood Flow & Metabolism · doi:10.1177/0271678x241261942 · Cited by 14
“44 In a large clinical data analysis from the Framingham Heart Study, increased cerebral glucose levels in midlife are shown to be highly associated with the risk of AD.”
Chang, A. C. (2020) · Elsevier eBooks · doi:10.1016/b978-0-12-823337-5.00005-6 · Cited by 14
A survey of bone abnormalities detection using machine learning algorithms
Barhoom, A. M., Jubair, M. R., & Abu-Naser, S. S. (2023) · AIP conference proceedings · doi:10.1063/5.0133139 · Cited by 11
Poonam, K., Guha, R., & Chakrabarti, P. P. (2024) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2024.3386801 · Cited by 11
“Previous studies have predominantly focused on static scenarios, either predicting the disease status at a single time point [10], [11] or a pre-defined series of future time points [12], [13].”
BackgroundA Novel Deep-Learning-Based Model for Medical Text Classification
Shen, Z., & Zhang, S. (2020) · International Conference on Computing and Pattern Recognition (ICCPR) · doi:10.1145/3436369.3436469 · Cited by 11
“[4] address early prediction of Alzheimer disease via using 18F-FDG PET of the brain based on a deep learning algorithm.”
MethodReview of artificial intelligence clinical applications in Nuclear Medicine
Panagiotidis, E., Papachristou, K., Makridou, A., Zoglopitou, L.-A., Paschali, A. N., Kalathas, T., Chatzimarkou, M., & Chatzipavlidou, V. (2023) · Nuclear Medicine Communications · doi:10.1097/mnm.0000000000001786 · Cited by 11
“The authors were able to show that the ML algorithm was 100% sensitive to predicting the final clinical diagnosis in the independent test set, on average 75.8 months (6.3 years) before the final diagnosis [46].”
InfluentialAlzheimer disease classification using optimal clustering based pre-trained SqueezeNet model
Rani, K. E. E., & Baulkani, S. (2024) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2024.107032 · Cited by 11
“Many DL approaches including Convolutional Neural Networks (CNN) and Support Vector Machines (SVM) have produced good results with high accuracy in AD identification [8,9].”
Fiani, B., Pasko, K. B. D., Sarhadi, K. J., & Covarrubias, C. (2021) · Reviews in the Neurosciences · doi:10.1515/revneuro-2021-0101 · Cited by 17
Dementia diagnosis by ensemble deep neural networks using FDG-PET scans
Yiğit, A., Baştanlar, Y., & Işık, Z. (2022) · Signal Image and Video Processing · doi:10.1007/s11760-022-02185-4 · Cited by 11
“The creation of the 2D input was inspired by the study performed at the University of California [20].”
Machine Learning in Radiology: Resistance Is Futile
Larvie, M. (2018) · Radiology · doi:10.1148/radiol.2018182312 · Cited by 11
Neural Networks for Fashion Image Classification and Visual SearchPreprint
Li, F., Kant, S., Araki, S., Bangera, S., & Shukla, S. S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.08170 · Cited by 11
“Inception V3, the third iteration of the inception architecture, uses 48 deep layers and stacks 11 inception modules, each consisting of pooling layers and convolutional filters (Ding et al., 2019).”
MethodAgyekum, E. A., Wang, Y., Issaka, E., Ren, Y., Tan, G., Shen, X., & Qian, X. (2025) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-025-02989-7 · Cited by 10
Distinct visual biases affect humans and artificial intelligence in medical imaging diagnoses
McLeod, G. A., Stanley, E. A. M., Rosenal, T., & Forkert, N. D. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-02226-5 · Cited by 15
Zhang, J., He, X., Qing, L., Xu, Y., Liu, Y., & Chen, H. (2022) · Journal of Neural Engineering · doi:10.1088/1741-2552/ac8450 · Cited by 11
“Ding et al [32] divided the FDG-PET scan into 16 evenly spaced sections and then passed them into the InceptionV3 architecture to learn the general features for AD classification.”
Doorenbos, L., Torbaniuk, O., Cavuoti, S., Paolillo, M., Longo, G., Brescia, M., Sznitman, R., & Márquez-Neila, P. (2022) · Astronomy and Astrophysics · doi:10.1051/0004-6361/202243900 · Cited by 14
Thakur, M., & Umapathy, S. (2022) · Physical and Engineering Sciences in Medicine · doi:10.1007/s13246-022-01196-2 · Cited by 10
Metadata
- Authors
- Ding, Y., Sohn, J. H., Kawczynski, M. G., Trivedi, H., Harnish, R., Jenkins, N. W., Lituiev, D., Copeland, T. P., Aboian, M. S., Mari Aparici, C., Behr, S. C., Flavell, R. R., Huang, S.-Y., Zalocusky, K. A., Nardo, L., Seo, Y., Hawkins, R. A., Hernandez Pampaloni, M., Hadley, D., & Franc, B. L.
- Affiliations
- University of California, San Francisco (US)
- ORCID
- Venue
- Radiology
- Published
- 2019-02
- Volume
- 290
- Issue
- 2
- Pages
- 456-464
- ISSN
- 0033-8419 (ISSN-L)
- 1527-1315
- PMC
- PMC6358051
- OpenAlex
- W2899635607
- Cited by
- 577
- References
- 24
- Citations by year
- 2026: 33 · 2025: 46 · 2024: 83 · 2023: 82 · 2022: 93 · 2021: 115 · 2020: 79 · 2019: 43
- FWCI
- 46.89
- Type
- journal article
- Language
- en
- Open access
- green
- www.ncbi.nlm.nih.gov
- Locations
- Radiology (publishedVersion)
- PubMed Central (publishedVersion)
- PubMed (publishedVersion)
- eScholarship (California Digital Library) (submittedVersion)
- Funders
- Foundation for the National Institutes of Health (5T32EB001631-10)
- National Institutes of Health (U01 AG024904)
- U.S. Department of Defense (W81XWH-12-2-0012)
- University of California, San Francisco
- Topics
- Health Sciences › Medicine › Psychiatry and Mental health › Dementia and Cognitive Impairment Research
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Medical Imaging Techniques and Applications
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Keywords
- Alzheimer's disease, mild cognitive impairment, 18F-FDG PET, deep learning, convolutional neural networks, InceptionV3, early diagnosis, radiologist comparison, saliency maps, t-SNE, ADNI
- MeSH terms
- Deep Learning, Aged, Aged, 80 and over, Algorithms, Alzheimer Disease, Female, Humans, Image Interpretation, Computer-Assisted, Male, Middle Aged, Retrospective Studies, Sensitivity and Specificity, Fluorodeoxyglucose F18, Positron-Emission Tomography, Cognitive Dysfunction
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.