Evaluating the Effectiveness of Synthetic Datasets for Dementia Diagnosis Using Deep Learning DOI

Andrew Romitti,

Jiya Shetty,

Praveen Rao

et al.

Published: Sept. 27, 2023

Early and accurate diagnosis of dementia can lead to better treatment the disease improve patients' quality life. Advanced neuroimaging technologies such as magnetic resonance imaging (MRI) deep learning hold promise for early diagnosis. However, there is limited number real-world MRI datasets training deep-learning models classify a patient's degree dementia. Generative adversarial networks (GANs) are learning-based generative that generate synthetic data samples based on real dataset's distribution. They have been successfully used in clinical studies. In this work, we investigate how images generated by GANs performance accurately classifying level (i.e., very mildly demented, moderately no dementia.) We trained state-of-the-art model image classification, namely, Data-Efficient Image Transformer (DeiT) using dataset along with GANs. combined during varying proportion set. evaluated accuracy F1-score DeiT images. Our results showed achieve good even Hence, offer promising solution improving via especially when scarce.

Language: Английский

Self-Supervised Contrastive Learning to Predict the Progression of Alzheimer’s Disease with 3D Amyloid-PET DOI Creative Commons
Min Gu Kwak, Yi Su, Kewei Chen

et al.

Bioengineering, Journal Year: 2023, Volume and Issue: 10(10), P. 1141 - 1141

Published: Sept. 28, 2023

Early diagnosis of Alzheimer’s disease (AD) is an important task that facilitates the development treatment and prevention strategies, may potentially improve patient outcomes. Neuroimaging has shown great promise, including amyloid-PET, which measures accumulation amyloid plaques in brain—a hallmark AD. It desirable to train end-to-end deep learning models predict progression AD for individuals at early stages based on 3D amyloid-PET. However, commonly used are trained a fully supervised manner, they inevitably biased toward given label information. To this end, we propose selfsupervised contrastive method accurately conversion with mild cognitive impairment (MCI) The proposed method, SMoCo, uses both labeled unlabeled data capture general semantic representations underlying images. As downstream as classification converters vs. non-converters, unlike self-supervised problem aims generate task-agnostic representations, SMoCo additionally utilizes information pre-training. demonstrate performance our conducted experiments Disease Initiative (ADNI) dataset. results confirmed capable providing appropriate resulting accurate classification. showed best over existing methods, AUROC = 85.17%, accuracy 81.09%, sensitivity 77.39%, specificity 82.17%. While SSL demonstrated success other application domains computer vision, study provided initial investigation using model, effectively MCI

Language: Английский

Citations

2
Early Detection of Dementia Disease Using Machine Learning Approach DOI Open Access

Manihrii Krichena

INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT, Journal Year: 2024, Volume and Issue: 08(03), P. 1 - 5

Published: March 25, 2024

Early dementia detection is a crucial but challenging task in Bangladesh. Often, not recognized until it too late to receive effective care. This results part from lack of knowledge about the illness and its signs symptoms. Recent improvements machine learning algorithms, however, may change this. In recent study, we developed model that can identify early Bangladesh using algorithms. research paper proposed an efficient learning-based approach for disease A dataset 199 people with 175 healthy controls was used develop model. 96% cases, algorithm correctly identified dementia. significant accomplishment could revolutionize Bangladesh's process. For patients get care they require, essential. study offers proof-of-concept use & The this suggest models be as powerful tool Index Terms—Dementia, Machine Learning, Prediction, Accuracy

Language: Английский

Citations

0
Halk Sağlığı Alanında Makine Öğrenimi Analizinin Kullanımı DOI Open Access
Kübra Ecem TURGUTKAYA, Emine Didem Evci Kiraz

Journal of Intelligent Systems Theory and Applications, Journal Year: 2024, Volume and Issue: 7(1), P. 27 - 29

Published: March 27, 2024

Yaklaşık olarak son on yılda, büyük veri ve yüksek işlem gücündeki ilerlemelerle desteklenen yapay zeka teknolojisi, hızlı bir gelişme göstermiş çeşitli uygulama alanlarında olağanüstü evreye girmiştir. Makine öğrenimi (MÖ), kümelerini kullanarak otomatik öğrenen doğru tahminler öngörüler elde etmek için insan tarafından denetlenen veya denetlenmeyen sistemler oluşturmak geliştirilen gelişmiş istatistiksel olasılıksal tekniklere dayanmaktadır. Bu yazıda halk sağlığı alanında kullanılan MÖ uygulamalarını araştırmak amaçlanmıştır. uygulamalar 5 başlık altında incelenecektir. Bunlar; sağlık hizmeti kaynaklarının optimizasyonu, sürveyans, salgın tespiti acil durum yönetimi, davranışı analizi müdahale, hastalık teşhisi prognozu ise kişiselleştirilmiş tıp. Yıllar içinde teknoloji ilerledikçe, bu alanlardaki uygulamaların entegrasyonu, hizmetlerinin planlanması, dönüştürülmesi toplum sonuçlarının iyileştirilmesinde daha da önemli rol oynayacaktır.

Citations

0
Tecnologías asistivas para pacientes ancianos con demencia: perspectivas desde la bioética de los cuidados en salud DOI Creative Commons

Isis Laynne de Oliveira Machado Cunha

Salud Colectiva, Journal Year: 2023, Volume and Issue: 19, P. e4488 - e4488

Published: Oct. 3, 2023

La demencia es actualmente una de las enfermedades más comunes que afecta a personas mayores, siendo la séptima causa principal muerte. Provoca pérdida memoria, dificultad para razonar y, por consiguiente, dificultades tomar y ejecutar decisiones, lo tecnologías asistencia estimulación cognitiva son valiosos recursos en el proceso cuidado. Desde investigación teórica basada bioética los cuidados salud investigaciones Aline Albuquerque Victor Montori, este artículo aborda, primer lugar, concepto cuidado salud, atención centrada paciente idea empatía clínica; segundo se centra empleo asistivas adultos mayores con último, plantea discusión sobre si podría ser considerado como tecnología sanitaria.

Citations

1
Evaluating the Effectiveness of Synthetic Datasets for Dementia Diagnosis Using Deep Learning DOI

Andrew Romitti,

Jiya Shetty,

Praveen Rao

et al.

Published: Sept. 27, 2023

Early and accurate diagnosis of dementia can lead to better treatment the disease improve patients' quality life. Advanced neuroimaging technologies such as magnetic resonance imaging (MRI) deep learning hold promise for early diagnosis. However, there is limited number real-world MRI datasets training deep-learning models classify a patient's degree dementia. Generative adversarial networks (GANs) are learning-based generative that generate synthetic data samples based on real dataset's distribution. They have been successfully used in clinical studies. In this work, we investigate how images generated by GANs performance accurately classifying level (i.e., very mildly demented, moderately no dementia.) We trained state-of-the-art model image classification, namely, Data-Efficient Image Transformer (DeiT) using dataset along with GANs. combined during varying proportion set. evaluated accuracy F1-score DeiT images. Our results showed achieve good even Hence, offer promising solution improving via especially when scarce.

Language: Английский

Citations

1