{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T16:11:29Z","timestamp":1781107889227,"version":"3.54.1"},"reference-count":17,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T00:00:00Z","timestamp":1769990400000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>\n                    Early and accurate detection of Alzheimer\u2019s disease (AD), particularly at the very mild and mild cognitive impairment stages, remains a significant clinical challenge due to subtle anatomical changes and overlapping imaging features between classes. This study evaluates the effectiveness of synthetic MRI image augmentation using Deep Convolutional Generative Adversarial Networks (DCGANs) to improve the classification performance of deep learning models for early-stage AD detection. The dataset consists of Magnetic Resonance Imaging (MRI) scans categorized into \u201cNo Dementia,\u201d \u201cVery Mild Dementia,\u201d \u201cMild Dementia,\u201d and \u201cModerate Dementia\u201d classes, sourced from a publicly available repository. A baseline Convolutional Neural Network (CNN) was initially trained on traditionally augmented images and evaluated on a validation set. To address class imbalance and improve sensitivity for the \u201cVery Mild Dementia\u201d class, a DCGAN was trained on this subset to generate synthetic MRI images. Generator models were checkpointed based on their Frechet Inception Distance (FID) scores, and 500 synthetic images from each selected generator were incorporated into the training set. Comparative analysis revealed that while the baseline CNN achieved a validation accuracy of 98% and a precision of 0.97 for the \u201cVery Mild Dementia\u201d class, the augmented model utilizing synthetic images from the Epoch 72 generator improved performance to 99% accuracy with a macro F1-score of 1.00. Statistical significance was confirmed\n                    <jats:italic>via<\/jats:italic>\n                    McNemar\u2019s test (\n                    <jats:italic>p<\/jats:italic>\n                    &lt; 0.05), highlighting the potential of GAN-based augmentation for enhancing early AD classification. These findings underscore the importance of strategic checkpoint selection in GAN-based data augmentation to ensure clinically meaningful performance improvements.\n                  <\/jats:p>","DOI":"10.7717\/peerj-cs.3453","type":"journal-article","created":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T08:08:57Z","timestamp":1770019737000},"page":"e3453","source":"Crossref","is-referenced-by-count":1,"title":["Analysis of deep convolutional GAN-based data augmentation for early detection of Alzheimer\u2019s disease"],"prefix":"10.7717","volume":"12","author":[{"given":"Jayashree","family":"Shetty","sequence":"first","affiliation":[{"name":"Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pranav Kumar","family":"K.","sequence":"additional","affiliation":[{"name":"Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manjula K.","family":"Shenoy","sequence":"additional","affiliation":[{"name":"Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sucheta V.","family":"Kolekar","sequence":"additional","affiliation":[{"name":"Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"M. Mukhyaprana","family":"Prabhu","sequence":"additional","affiliation":[{"name":"Department of General Medicine, Kasturba Medical College, Manipal Academy of Higher Education, Manipal, India"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"4443","published-online":{"date-parts":[[2026,2,2]]},"reference":[{"key":"10.7717\/peerj-cs.3453\/ref-1","first-page":"1","article-title":"Applying convolutional neural networks for pre-detection of Alzheimer\u2019s disease from structural MRI data","author":"Gunawardena","year":"2017"},{"key":"10.7717\/peerj-cs.3453\/ref-2","first-page":"143","article-title":"Application of machine learning on MRI scans for Alzheimer\u2019s disease early detection","author":"Hernandez","year":"2023"},{"key":"10.7717\/peerj-cs.3453\/ref-3","first-page":"1","article-title":"Enhancing diagnostic accuracy in medical imaging: integrating GAN-based data augmentation for balanced dataset creation","author":"Karnati","year":"2024"},{"key":"10.7717\/peerj-cs.3453\/ref-4","first-page":"1","article-title":"A multi-class classification framework with smote based data augmentation technique for Alzheimer\u2019s disease progression","author":"Krishna","year":"2024"},{"issue":"2","key":"10.7717\/peerj-cs.3453\/ref-5","doi-asserted-by":"publisher","first-page":"91452","DOI":"10.1109\/access.2020.3018911","article-title":"Constrained oversampling: an oversampling approach to reduce noise generation in imbalanced datasets with class overlapping","volume":"10","author":"Liu","year":"2022","journal-title":"IEEE Access"},{"key":"10.7717\/peerj-cs.3453\/ref-6","first-page":"50","article-title":"Alzheimer\u2019s disease classification with a hybrid CNN-SVM approach on enhanced MRI data","author":"Rahman","year":"2024"},{"key":"10.7717\/peerj-cs.3453\/ref-7","first-page":"1","article-title":"A novel spatial attention module (SAM) for Alzheimer\u2019s detection from MRI images","author":"Roy","year":"2024"},{"key":"10.7717\/peerj-cs.3453\/ref-8","first-page":"122","article-title":"Enhancing grayscale image synthesis with deep conditional GAN and transfer learning","author":"Ryspayeva","year":"2024"},{"key":"10.7717\/peerj-cs.3453\/ref-9","first-page":"1","article-title":"Comparative analysis of oversampling techniques on small and imbalanced datasets using deep learning","author":"Sabha","year":"2023"},{"issue":"21","key":"10.7717\/peerj-cs.3453\/ref-10","doi-asserted-by":"publisher","first-page":"2363","DOI":"10.3390\/diagnostics14212363","article-title":"A feature-fusion technique-based Alzheimer\u2019s disease classification using magnetic resonance imaging","volume":"14","author":"Sait","year":"2024","journal-title":"Diagnostics"},{"key":"10.7717\/peerj-cs.3453\/ref-11","first-page":"1","article-title":"Streamlining deep learning based Alzheimer\u2019s disease classification: a simplified approach with ADASYN","author":"Saravanan","year":"2024"},{"key":"10.7717\/peerj-cs.3453\/ref-12","first-page":"105","article-title":"GAN. s approach on generating synthetical skin image dataset for imbalance dataset","author":"Setiawan","year":"2024"},{"issue":"3","key":"10.7717\/peerj-cs.3453\/ref-13","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1016\/j.procs.2024.08.021","article-title":"Deep learning in smart healthcare: a GAN-based approach for imbalanced Alzheimer\u2019s disease classification","volume":"241","author":"Tufail","year":"2024","journal-title":"Procedia Computer Science"},{"key":"10.7717\/peerj-cs.3453\/ref-14","first-page":"1","article-title":"Classifying early and late mild cognitive impairment stages of Alzheimer\u2019s disease by analyzing different brain areas","author":"Uysal","year":"2020"},{"key":"10.7717\/peerj-cs.3453\/ref-15","doi-asserted-by":"crossref","DOI":"10.1109\/ACCESS.2025.3540567","article-title":"Leveraging bi-focal perspectives and granular feature integration for accurate reliable early Alzheimer\u2019s detection","author":"Venkatraman","year":"2025","journal-title":"IEEE Access"},{"key":"10.7717\/peerj-cs.3453\/ref-16","doi-asserted-by":"publisher","first-page":"105063","DOI":"10.1016\/j.compbiomed.2021.105063","article-title":"Generative adversarial networks in medical image segmentation: a review","volume":"140","author":"Xun","year":"2022","journal-title":"Computers in Biology and Medicine"},{"issue":"7964","key":"10.7717\/peerj-cs.3453\/ref-17","doi-asserted-by":"publisher","first-page":"121210","DOI":"10.1016\/j.neuroimage.2025.121210","article-title":"IT: an interpretable transformer model for Alzheimer\u2019s disease prediction based on PET\/Mr images","volume":"311","author":"Yao","year":"2025","journal-title":"NeuroImage"}],"container-title":["PeerJ Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/peerj.com\/articles\/cs-3453.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3453.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3453.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3453.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T08:09:02Z","timestamp":1770019742000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/articles\/cs-3453"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,2]]},"references-count":17,"alternative-id":["10.7717\/peerj-cs.3453"],"URL":"https:\/\/doi.org\/10.7717\/peerj-cs.3453","archive":["CLOCKSS","LOCKSS","Portico"],"relation":{},"ISSN":["2376-5992"],"issn-type":[{"value":"2376-5992","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,2]]},"article-number":"e3453"}}