CoChat

Optimized Convolutional Fusion for Multimodal Neuroimaging in Alzheimer’s Disease Diagnosis: Enhancing Data Integration and Feature Extraction

Open access
Odusami, Modupe, Maskeliūnas, Rytis, Damaševičius, Robertas · 2023 · Journal of Personalized Medicine

The DOI matches its Crossref record; 42 of the 43 references it cites were found in a registry or an index, and 1 are not checked yet.

Abstract

Multimodal neuroimaging has gained traction in Alzheimer’s Disease (AD) diagnosis by integrating information from multiple imaging modalities to enhance classification accuracy. However, effectively handling heterogeneous data sources and overcoming the challenges posed by multiscale transform methods remains a significant hurdle. This article proposes a novel approach to address these challenges. To harness the power of diverse neuroimaging data, we employ a strategy that leverages optimized convolution techniques. These optimizations include varying kernel sizes and the incorporation of instance normalization, both of which play crucial roles in feature extraction from magnetic resonance imaging (MRI) and positron emission tomography (PET) images. Specifically, varying kernel sizes allow us to adapt the receptive field to different image characteristics, enhancing the model’s ability to capture relevant information. Furthermore, we employ transposed convolution, which increases spatial resolution of feature maps, and it is optimized with varying kernel sizes and instance normalization. This heightened resolution facilitates the alignment and integration of data from disparate MRI and PET data. The use of larger kernels and strides in transposed convolution expands the receptive field, enabling the model to capture essential cross-modal relationships. Instance normalization, applied to each modality during the fusion process, mitigates potential biases stemming from differences in intensity, contrast, or scale between modalities. This enhancement contributes to improved model performance by reducing complexity and ensuring robust fusion. The performance of the proposed fusion method is assessed on three distinct neuroimaging datasets, which include: Alzheimer’s Disease Neuroimaging Initiative (ADNI), consisting of 50 participants each at various stages of AD for both MRI and PET (Cognitive Normal, AD, and Early Mild Cognitive); Open Access Series of Imaging Studies (OASIS), consisting of 50 participants each at various stages of AD for both MRI and PET (Cognitive Normal, Mild Dementia, Very Mild Dementia); and whole-brain atlas neuroimaging (AANLIB) (consisting of 50 participants each at various stages of AD for both MRI and PET (Cognitive Normal, AD). To evaluate the quality of the fused images generated via our method, we employ a comprehensive set of evaluation metrics, including Structural Similarity Index Measurement (SSIM), which assesses the structural similarity between two images; Peak Signal-to-Noise Ratio (PSNR), which measures how closely the generated image resembles the ground truth; Entropy (E), which assesses the amount of information preserved or lost during fusion; the Feature Similarity Indexing Method (FSIM), which assesses the structural and feature similarities between two images; and Edge-Based Similarity (EBS), which measures the similarity of edges between the fused and ground truth images. The obtained fused image is further evaluated using a Mobile Vision Transformer. In the classification of AD vs. Cognitive Normal, the model achieved an accuracy of 99.00%, specificity of 99.00%, and sensitivity of 98.44% on the AANLIB dataset.

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.3390/jpm13101496

Cites

42 of 43 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 Framework of Proposed Fusion Method.
Figure 1 Framework of Proposed Fusion Method.CC BY · PubMed Central
Figure 2 Sample Images from the AANLIB database.
Figure 2 Sample Images from the AANLIB database.CC BY · PubMed Central
Figure 3 Sample Images from the ADNI database.
Figure 3 Sample Images from the ADNI database.CC BY · PubMed Central
Figure 4 Sample Images from OASIS Database.
Figure 4 Sample Images from OASIS Database.CC BY · PubMed Central
Figure 5 Sample Images after Laplace Sharpening.
Figure 5 Sample Images after Laplace Sharpening.CC BY · PubMed Central
Figure 6 Sample of Fused Images.
Figure 6 Sample of Fused Images.CC BY · PubMed Central
Figure 7 Average Metrics Value of AANLIB.
Figure 7 Average Metrics Value of AANLIB.CC BY · PubMed Central
Figure 8 Average Metrics Value of ADNI.
Figure 8 Average Metrics Value of ADNI.CC BY · PubMed Central
Figure 9 Average Metrics Value of OASIS.
Figure 9 Average Metrics Value of OASIS.CC BY · PubMed Central
Figure 10 Training Accuracy, Validation Accuracy, Training Loss, and Validation Loss using Fused Data from AANLIB.
Figure 10 Training Accuracy, Validation Accuracy, Training Loss, and Validation Loss using Fused Data from AANLIB.CC BY · PubMed Central
Figure 11 Training Accuracy, Validation Accuracy, Training Loss, and Validation Loss using Fused Data from ADNI.
Figure 11 Training Accuracy, Validation Accuracy, Training Loss, and Validation Loss using Fused Data from ADNI.CC BY · PubMed Central
Figure 12 Training Accuracy, Validation Accuracy, Training Loss, and Validation Loss using Fused Data from OASIS.
Figure 12 Training Accuracy, Validation Accuracy, Training Loss, and Validation Loss using Fused Data from OASIS.CC BY · PubMed Central
Figure 13 Confusion Matrix for (a) MRI Test Data from AANLIB, (b) PET Test Data from AANLIB, (c) MRI Test Data from ADNI, (d) PET Test Data from ADNI, (e) MRI Test Data from OASIS, (f) PET Test Data from OASIS.
Figure 13 Confusion Matrix for (a) MRI Test Data from AANLIB, (b) PET Test Data from AANLIB, (c) MRI Test Data from ADNI, (d) PET Test Data from ADNI, (e) MRI Test Data from OASIS, (f) PET Test Data from OASIS.CC BY · PubMed Central
Figure 14 ROC Curve for Proposed Model for Classification of AD vs. CN: (a) AANLIB MRI Test Data, (b) AANLIB PET Test Data, (c) ADNI MRI Test Data, (d) ADNI PET Test Data, (e) OASIS MRI Test Data, (f) OASIS PET Test Data.
Figure 14 ROC Curve for Proposed Model for Classification of AD vs. CN: (a) AANLIB MRI Test Data, (b) AANLIB PET Test Data, (c) ADNI MRI Test Data, (d) ADNI PET Test Data, (e) OASIS MRI Test Data, (f) OASIS PET Test Data.CC BY · PubMed Central

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.

A few free checks a day · papers already verified open instantly · results are public

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?

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

Show all 43 references

Research works printed but not linked: 4

  1. Beyer, L., Zhai, X., and Kolesnikov, A. (2022). Better plain ViT baselines for ImageNet-1k. arXiv.
  2. Burduk, R., Kurzynski, M., and Wozniak, M. (2020). Advances in Intelligent Systems and Computing, Springer International Publishing.
  3. Chi, L., Jiang, B., and Mu, Y. (2020). Advances in Neural Information Processing Systems, Curran Associates, Inc.. Available online: https://proceedings.neurips.cc/paper/2020/hash/2fd5d41ec6cfab47e32164d5624269b1-Abstract.html.
  4. Ulyanov, D., Vedaldi, A., and Lempitsky, V. (2016). Instance normalization: The missing ingredient for fast stylization. arXiv.

Cited by

See all 42

Metadata

Authors
Odusami, M., Maskeliūnas, R., & Damaševičius, R.
Affiliations
  • Kaunas University of Technology (LT)
  • Vytautas Magnus University (LT)
Corresponding author
Damaševičius, Robertas
Venue
Journal of Personalized Medicine
Publisher
MDPI AG
Published
2023-10-14
Volume
13
Issue
10
Pages
1496
ISSN
2075-4426 (ISSN-L)
OpenAlex
W4387642613
Cited by
42
References
39
Citations by year
2026: 11 · 2025: 21 · 2024: 10
FWCI
8.52
Type
journal article
Language
en
Open access
Locations
  • Journal of Personalized Medicine (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • KTUePubl (Repository of Kaunas University of Technology) (submittedVersion, other-oa)
  • Vytautas Magnus University (submittedVersion, cc-by)
Funders
National Institute on Aging (P01AG003991, P30AG066444, P01AG026276)
Topics
  • Health Sciences › Medicine › Psychiatry and Mental health › Dementia and Cognitive Impairment Research
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
  • Physical Sciences › Engineering › Media Technology › Advanced Image Fusion Techniques
Keywords
multimodal neuroimaging, Alzheimer's disease diagnosis, cross-modal fusion, MRI-PET fusion, convolutional neural networks, instance normalization, transposed convolution, feature extraction, ADNI, OASIS, multimodal data integration, fusion quality evaluation, SSIM, FSIM, entropy, brain MRI, brain PET, whole-brain atlas

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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Optimized Convolutional Fusion for Multimodal Neuroimaging in Alzheimer’s Disease Diagnosis: Enhancing Data Integration and Feature Extraction. https://app.cochat.ai/papers/10.3390/jpm13101496
The paper
Odusami, M., Maskeliūnas, R., & Damaševičius, R. (2023). Optimized Convolutional Fusion for Multimodal Neuroimaging in Alzheimer’s Disease Diagnosis: Enhancing Data Integration and Feature Extraction. Journal of Personalized Medicine. https://doi.org/10.3390/jpm13101496

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.