Deep Learning Based Morphometric Analysis for Alzheimer's Diagnosis

Selahattin Barış Çelebi; Bülent Gürsel Emiroğlu

Article Details

Deep Learning Based Morphometric Analysis for Alzheimer's Diagnosis

Authors:

Selahattin Barış Çelebi | Bülent Gürsel Emiroğlu

Publisher:

Igdir University

Main Topics:

Bilgisayar Yazılımı

Journal:

Iğdır Üniversitesi Fen Bilimleri Enstitüsü Dergisi Vol.13 Issue 3, pp.1454-1467

Document Type:

Article

Publication Date:

1/2023

Document Language:

Turkish

Document ID (Org No.):

2001296838

pISSN:

2536-4618

Keywords:

Abstract:

 Alzheimers disease is the most common type of dementia in the world, and the treatment methods currently used are aimed only at preventing the progression of the disease. Brain tissue volume changes due to Alzheimers disease AD. With the help of tensor-based morphometry TBM, changes in brain tissues caused by the disease can be monitored. This study aimed to develop an effective method to differentiate between AD patients and the Cognitive Normal CN group subjects. TBM, or small local volume differences, are adopted as classification features. Axial brain image slices with 5-pixel intervals covering the hippocampus and temporal lobe from 3D TBM morphometric images belonging to the ADCN class were recorded in 2D. Then, 60 of the dataset obtained from each clinical group AD; CN was allocated as training, 20 as validation, and 20 as test datasets training: 480; validation: 120; testing: 120. The model performed ADCN estimation with validation 92.5 and testing 89 accuracy values. The results show that TBM obtained from slices covering the hippocampus and temporal lobe with deep learning can be applied with high accuracy in the diagnosis of AD.

 Alzheimers disease is the most common type of dementia in the world, and the treatment methods currently used are aimed only at preventing the progression of the disease. Brain tissue volume changes due to Alzheimers disease AD. With the help of tensor-based morphometry TBM, changes in brain tissues caused by the disease can be monitored. This study aimed to develop an effective method to differentiate between AD patients and the Cognitive Normal CN group subjects. TBM, or small local volume differences, are adopted as classification features. Axial brain image slices with 5-pixel intervals covering the hippocampus and temporal lobe from 3D TBM morphometric images belonging to the ADCN class were recorded in 2D. Then, 60 of the dataset obtained from each clinical group AD; CN was allocated as training, 20 as validation, and 20 as test datasets training: 480; validation: 120; testing: 120. The model performed ADCN estimation with validation 92.5 and testing 89 accuracy values. The results show that TBM obtained from slices covering the hippocampus and temporal lobe with deep learning can be applied with high accuracy in the diagnosis of AD.

 Alzheimers disease is the most common type of dementia in the world, and the treatment methods currently used are aimed only at preventing the progression of the disease. Brain tissue volume changes due to Alzheimers disease AD. With the help of tensor-based morphometry TBM, changes in brain tissues caused by the disease can be monitored. This study aimed to develop an effective method to differentiate between AD patients and the Cognitive Normal CN group subjects. TBM, or small local volume differences, are adopted as classification features. Axial brain image slices with 5-pixel intervals covering the hippocampus and temporal lobe from 3D TBM morphometric images belonging to the ADCN class were recorded in 2D. Then, 60 of the dataset obtained from each clinical group AD; CN was allocated as training, 20 as validation, and 20 as test datasets training: 480; validation: 120; testing: 120. The model performed ADCN estimation with validation 92.5 and testing 89 accuracy values. The results show that TBM obtained from slices covering the hippocampus and temporal lobe with deep learning can be applied with high accuracy in the diagnosis of AD.

 Alzheimer, dünyadaki en yaygın bunama türüdür ve şu an için kullanılan tedavi yöntemleri sadece hastalığın ilerleyişini önleme amacına yöneliktir. Beyin dokusu hacmi Alzheimer hastalığı AD nedeniyle değişir. Tensör tabanlı morfometri TBM yardımıyla, hastalığın beyin dokularında neden olduğu değişiklikler izlenebilir. Bu çalışmada AD hastaları ve Bilişsel Normaller CNler grubu denekleri arasında ayrım yapmak için etkili bir yöntem geliştirmek amaçlanmıştır. TBM veya küçük yerel hacim farklılıkları, sınıflandırma özelliği olarak benimsenmiştir. ADCN sınıfına ait 3D TBM morfometrik görüntülerinden hipokampus ve temporal lobu kapsayan 5 piksel aralıklı eksenel beyin görüntü dilimleri 2D olarak kaydedildi. Daha sonra her bir klinik gruptan AD; CN elde edilen veri setinin 60ı eğitim, 20si validasyon ve 20si test veri setleri olarak ayrıldı Eğitim: 480; doğrulama: 120; test: 120. Model validasyon 92.5 ve test 89 doğruluk değerleri ile ADCN tahmini gerçekleştirdi. Sonuçlar, Derin öğrenme ile hipokampus ve temporal lobu kapsayan dilimlerden elde edilen TBMnin ADnin tanısında yüksek doğrulukla uygulanabileceğini göstermektedir.

Article Details

Deep Learning Based Morphometric Analysis for Alzheimer's Diagnosis

Authors:

Selahattin Barış Çelebi | Bülent Gürsel Emiroğlu

Publisher:

Igdir University

Main Topics:

Bilgisayar Yazılımı

Journal:

Iğdır Üniversitesi Fen Bilimleri Enstitüsü Dergisi Vol.13 Issue 3, pp.1454-1467

Document Type:

Article

Publication Date:

1/2023

Document Language:

Turkish

Document ID (Org No.):

2001296838

pISSN:

2536-4618

Alzheimer

Data augmentation

Deep Learning

Tensor-based morphometryTensor tabanlı morfometri

Alzheimer

Derin Öğrenme

Veri artırımı

Issues

Article Details

Authors: Selahattin Barış Çelebi | Bülent Gürsel Emiroğlu

Publisher: Igdir University

Main Topics: Bilgisayar Yazılımı

Journal: Iğdır Üniversitesi Fen Bilimleri Enstitüsü Dergisi Vol.13 Issue 3, pp.1454-1467

Document Type: Article

Publication Date: 1/2023

Document Language: Turkish

Document ID (Org No.): 2001296838

pISSN: 2536-4618

Issues

Authors:

Selahattin Barış Çelebi | Bülent Gürsel Emiroğlu

Publisher:

Igdir University

Main Topics:

Bilgisayar Yazılımı

Journal:

Iğdır Üniversitesi Fen Bilimleri Enstitüsü Dergisi Vol.13 Issue 3, pp.1454-1467

Document Type:

Article

Publication Date:

1/2023

Document Language:

Turkish

Document ID (Org No.):

2001296838

pISSN:

2536-4618