Adapting to evolving MRI data: A transfer learning approach for Alzheimer’s disease prediction
Integrating 3D magnetic resonance imaging (MRI) with machine learning has shown promising results in healthcare, especially in detecting Alzheimer’s Disease (AD). However, changes in MRI technologies and acquisition protocols often yield limited data, leading to potential overfitting. This study exp...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-02-01
|
| Series: | NeuroImage |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1053811925000163 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832087879473430528 |
|---|---|
| author | Rosanna Turrisi Sarthak Pati Giovanni Pioggia Gennaro Tartarisco |
| author_facet | Rosanna Turrisi Sarthak Pati Giovanni Pioggia Gennaro Tartarisco |
| author_sort | Rosanna Turrisi |
| collection | DOAJ |
| description | Integrating 3D magnetic resonance imaging (MRI) with machine learning has shown promising results in healthcare, especially in detecting Alzheimer’s Disease (AD). However, changes in MRI technologies and acquisition protocols often yield limited data, leading to potential overfitting. This study explores Transfer Learning (TL) approaches to enhance AD diagnosis using a Baseline model consisting of a 3D-Convolutional Neural Network trained on 80 3T MRI scans.Two scenarios are explored: (A) utilizing historical data to address changes in MRI acquisitions (from 1.5T to 3T MRI), and (B) adapting 2D models pre-trained on ImageNet (ResNet18, ResNet50, ResNet101) for 3D image processing when historical data is unavailable. In both scenarios, two modeling approaches are tested. The General Approach involves distinct feature extraction and classification steps, using Radiomic features and TL-based features evaluated with six classifiers. The Deep Approach integrates these steps by fine-tuning the pre-trained models for AD diagnosis.In scenario (A), TL significantly boosts the Baseline’s accuracy from 63% to 99%. In scenario (B), Radiomic features better represents 3D MRI than TL-features in the General Approach. Nonetheless, fine-tuning models pre-trained on natural images can increase the Baseline’s accuracy by up to 12 percentage points, achieving an overall accuracy of 83%. |
| format | Article |
| id | doaj-art-f9ab5ec5113c4fafab380c063b2a7af4 |
| institution | Kabale University |
| issn | 1095-9572 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Elsevier |
| record_format | Article |
| series | NeuroImage |
| spelling | doaj-art-f9ab5ec5113c4fafab380c063b2a7af42025-02-06T05:11:06ZengElsevierNeuroImage1095-95722025-02-01307121016Adapting to evolving MRI data: A transfer learning approach for Alzheimer’s disease predictionRosanna Turrisi0Sarthak Pati1Giovanni Pioggia2Gennaro Tartarisco3Institute for Biomedical Research and Innovation (IRIB), National Research Council of Italy (CNR), Messina, Italy; Machine Learning Genoa Center (MaLGa), University of Genoa, Genoa, Italy; Corresponding author at: Institute for Biomedical Research and Innovation (IRIB), National Research Council of Italy (CNR), Messina, Italy.Department of Pathology and Laboratory Medicine, Indiana University School of Medicine, Indianapolis IN, USA; Medical Research Group, MLCommons, San Francisco CA, USAInstitute for Biomedical Research and Innovation (IRIB), National Research Council of Italy (CNR), Messina, ItalyInstitute for Biomedical Research and Innovation (IRIB), National Research Council of Italy (CNR), Messina, ItalyIntegrating 3D magnetic resonance imaging (MRI) with machine learning has shown promising results in healthcare, especially in detecting Alzheimer’s Disease (AD). However, changes in MRI technologies and acquisition protocols often yield limited data, leading to potential overfitting. This study explores Transfer Learning (TL) approaches to enhance AD diagnosis using a Baseline model consisting of a 3D-Convolutional Neural Network trained on 80 3T MRI scans.Two scenarios are explored: (A) utilizing historical data to address changes in MRI acquisitions (from 1.5T to 3T MRI), and (B) adapting 2D models pre-trained on ImageNet (ResNet18, ResNet50, ResNet101) for 3D image processing when historical data is unavailable. In both scenarios, two modeling approaches are tested. The General Approach involves distinct feature extraction and classification steps, using Radiomic features and TL-based features evaluated with six classifiers. The Deep Approach integrates these steps by fine-tuning the pre-trained models for AD diagnosis.In scenario (A), TL significantly boosts the Baseline’s accuracy from 63% to 99%. In scenario (B), Radiomic features better represents 3D MRI than TL-features in the General Approach. Nonetheless, fine-tuning models pre-trained on natural images can increase the Baseline’s accuracy by up to 12 percentage points, achieving an overall accuracy of 83%.http://www.sciencedirect.com/science/article/pii/S1053811925000163Alzheimer’s diseaseEvolving MRIDomain adaptationTransfer learningACS convolutions |
| spellingShingle | Rosanna Turrisi Sarthak Pati Giovanni Pioggia Gennaro Tartarisco Adapting to evolving MRI data: A transfer learning approach for Alzheimer’s disease prediction NeuroImage Alzheimer’s disease Evolving MRI Domain adaptation Transfer learning ACS convolutions |
| title | Adapting to evolving MRI data: A transfer learning approach for Alzheimer’s disease prediction |
| title_full | Adapting to evolving MRI data: A transfer learning approach for Alzheimer’s disease prediction |
| title_fullStr | Adapting to evolving MRI data: A transfer learning approach for Alzheimer’s disease prediction |
| title_full_unstemmed | Adapting to evolving MRI data: A transfer learning approach for Alzheimer’s disease prediction |
| title_short | Adapting to evolving MRI data: A transfer learning approach for Alzheimer’s disease prediction |
| title_sort | adapting to evolving mri data a transfer learning approach for alzheimer s disease prediction |
| topic | Alzheimer’s disease Evolving MRI Domain adaptation Transfer learning ACS convolutions |
| url | http://www.sciencedirect.com/science/article/pii/S1053811925000163 |
| work_keys_str_mv | AT rosannaturrisi adaptingtoevolvingmridataatransferlearningapproachforalzheimersdiseaseprediction AT sarthakpati adaptingtoevolvingmridataatransferlearningapproachforalzheimersdiseaseprediction AT giovannipioggia adaptingtoevolvingmridataatransferlearningapproachforalzheimersdiseaseprediction AT gennarotartarisco adaptingtoevolvingmridataatransferlearningapproachforalzheimersdiseaseprediction |