Single Subject Classification of Alzheimer’s Disease and Behavioral Variant Frontotemporal Dementia Using Anatomical, Diffusion Tensor, and Resting-State Functional Magnetic Resonance Imaging

Bouts, Mark J. R. J.; Möller, Christiane; Hafkemeijer, Anne; Swieten, John C. van; Dopper, Elise G.P.; Flier, Wiesje M. van der; Vrenken, Hugo; Wink, Alle Meije; Pijnenburg, Yolande A.L.; Scheltens, Philip; Barkhof, Frederik; Schouten, Tijn M.; Vos, Frank de; Feis, Rogier A.; Grond, Jeroen van der; Rooij, Mark de; Rombouts, Serge A.R.B.

doi:10.3233/jad-170893

Cited by 37 publications

(63 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Previous MRI‐based classification methods have been heralded as promising tools for accurate classification of AD (Bouts et al, ; Bron et al, ; Schouten et al, ), MCI (Cui et al, ; Eskildsen et al, ), or to differentiate between MCI subjects likely to develop dementia due to AD or those that do not progress (Adaszewski et al, ; Arbabshirani, Plis, Sui, & Calhoun, ; Eskildsen et al, ; Misra et al, ; Rathore et al, ). These studies generally aimed to maximize classification performance by using sparse, carefully selected clinical samples.…”

Section: Discussionmentioning

confidence: 99%

“…To determine the ability to detect MCI from normal aging within a community‐dwelling cohort, we employed four MRI‐based probabilistic classification models. This first model was recently introduced and validated in two separate clinical cohorts (Bouts et al, ; Schouten et al, ). We trained this model with AD patients and control subjects of a separate clinical AD cohort.…”

Section: Methodsmentioning

confidence: 99%

“…Both protocols included a 3D isotropic T1‐weighted image and a diffusion MRI dataset with a maximum b‐value of 1,000 s/mm 2 . Preprocessing procedures of the 3DT 1 w images and diffusion MRI were similar for both cohorts and followed those previously described (Bouts et al, ). The processed maps were subsequently used for feature extraction.…”

Section: Methodsmentioning

confidence: 99%

“…Model training and optimization procedures were in accordance with those detailed previously (Bouts et al, ; Schouten et al, ). In brief, after each feature was standardized to zero mean and unit variance, either single or all MRI measures (i.e., GMD, DGMV, WMD, FA, or MD) derived from the training data were alternately used to train a classification model using nested 10‐fold cross‐validation.…”

Section: Methodsmentioning

confidence: 99%

See 3 more Smart Citations

Detection of mild cognitive impairment in a community‐dwelling population using quantitative, multiparametric MRI‐based classification

Bouts

Vernooij

Koini

et al. 2019

Human Brain Mapping

Self Cite

View full text Add to dashboard Cite

Early and accurate mild cognitive impairment (MCI) detection within a heterogeneous, nonclinical population is needed to improve care for persons at risk of developing dementia. Magnetic resonance imaging (MRI)‐based classification may aid early diagnosis of MCI, but has only been applied within clinical cohorts. We aimed to determine the generalizability of MRI‐based classification probability scores to detect MCI on an individual basis within a general population. To determine classification probability scores, an AD, mild‐AD, and moderate‐AD detection model were created with anatomical and diffusion MRI measures calculated from a clinical Alzheimer's Disease (AD) cohort and subsequently applied to a population‐based cohort with 48 MCI and 617 normal aging subjects. Each model's ability to detect MCI was quantified using area under the receiver operating characteristic curve (AUC) and compared with an MCI detection model trained and applied to the population‐based cohort. The AD‐model and mild‐AD identified MCI from controls better than chance level (AUC = 0.600, p = 0.025; AUC = 0.619, p = 0.008). In contrast, the moderate‐AD‐model was not able to separate MCI from normal aging (AUC = 0.567, p = 0.147). The MCI‐model was able to separate MCI from controls better than chance ( p = 0.014) with mean AUC values comparable with the AD‐model (AUC = 0.611, p = 1.0). Within our population‐based cohort, classification models detected MCI better than chance. Nevertheless, classification performance rates were moderate and may be insufficient to facilitate robust MRI‐based MCI detection on an individual basis. Our data indicate that multiparametric MRI‐based classification algorithms, that are effective in clinical cohorts, may not straightforwardly translate to applications in a general population.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Detection of mild cognitive impairment in a community‐dwelling population using quantitative, multiparametric MRI‐based classification

Bouts

Vernooij

Koini

et al. 2019

Human Brain Mapping

Self Cite

View full text Add to dashboard Cite

show abstract

“…Advancements have been made in image acquisition and capacity to algorithmically sort images trained by a constellation of image and patient features. 56,57 Difficulties with learning, cognition, depression, or anxiety are well-recognized comorbidities of epilepsy. 47 Thus, it is unclear to what extent this could improve upon expert interpretation.…”

Section: Future Directionsmentioning

confidence: 99%

Network‐targeted approach and postoperative resting‐state functional magnetic resonance imaging are associated with seizure outcome

Boerwinkle

Cediel

Mirea

et al. 2019

Annals of Neurology

View full text Add to dashboard Cite

Objective: Postoperative resting-state functional magnetic resonance imaging (MRI) in children with intractable epilepsy has not been quantified in relation to seizure outcome. Therefore, its value as a biomarker for epileptogenic pathology is not well understood. Methods: In a sample of children with intractable epilepsy who underwent prospective resting-state seizure onset zone (SOZ)-targeted epilepsy surgery, postoperative resting-state functional MRI (rs-fMRI) was performed 6 to 12 months later. Graded normalization of the postoperative resting-state SOZ was compared to seizure outcomes, patient, surgery, and anatomical MRI characteristics. Results: A total of 64 cases were evaluated. Network-targeted surgery, followed by postoperative rs-fMRI normalization was significantly (p < 0.001) correlated with seizure reduction, with a Spearman rank correlation coefficient of 0.83. Of 39 cases with postoperative rs-fMRI SOZ normalization, 38 (97%) became completely seizure free. In contrast, of the 25 cases without complete rs-fMRI SOZ normalization, only 3 (5%) became seizure free. The accuracy of rs-fMRI as a biomarker predicting seizure freedom is 94%, with 96% sensitivity and 93% specificity. Interpretation: Among seizure localization techniques in pediatric epilepsy, network-targeted surgery, followed by postoperative rs-fMRI normalization, has high correlation with seizure freedom. This study shows that rs-fMRI SOZ can be used as a biomarker of the epileptogenic zone, and postoperative rs-fMRI normalization is a biomarker for SOZ quiescence.

show abstract

Artificial intelligence for dementia research methods optimization

Bucholc,

James,

Khleifat

et al. 2023

Alzheimer's & Dementia

View full text Add to dashboard Cite

Artificial intelligence (AI) and machine learning (ML) approaches are increasingly being used in dementia research. However, several methodological challenges exist that may limit the insights we can obtain from high‐dimensional data and our ability to translate these findings into improved patient outcomes. To improve reproducibility and replicability, researchers should make their well‐documented code and modeling pipelines openly available. Data should also be shared where appropriate. To enhance the acceptability of models and AI‐enabled systems to users, researchers should prioritize interpretable methods that provide insights into how decisions are generated. Models should be developed using multiple, diverse datasets to improve robustness, generalizability, and reduce potentially harmful bias. To improve clarity and reproducibility, researchers should adhere to reporting guidelines that are co‐produced with multiple stakeholders. If these methodological challenges are overcome, AI and ML hold enormous promise for changing the landscape of dementia research and care.HIGHLIGHTS Machine learning (ML) can improve diagnosis, prevention, and management of dementia. Inadequate reporting of ML procedures affects reproduction/replication of results. ML models built on unrepresentative datasets do not generalize to new datasets. Obligatory metrics for certain model structures and use cases have not been defined. Interpretability and trust in ML predictions are barriers to clinical translation.

show abstract

Single Subject Classification of Alzheimer’s Disease and Behavioral Variant Frontotemporal Dementia Using Anatomical, Diffusion Tensor, and Resting-State Functional Magnetic Resonance Imaging

Abstract: Background / Objective:

Cited by 37 publications

References 68 publications

Detection of mild cognitive impairment in a community‐dwelling population using quantitative, multiparametric MRI‐based classification

Detection of mild cognitive impairment in a community‐dwelling population using quantitative, multiparametric MRI‐based classification

Network‐targeted approach and postoperative resting‐state functional magnetic resonance imaging are associated with seizure outcome

Artificial intelligence for dementia research methods optimization

Contact Info

Product

Resources

About