• Smart Media Journal
• /
• v.13 no.10
• /
• pp.28-34
• /
• 2024

Alzheimer's disease is a form of dementia that can be managed by identifying the disease in its initial phases. In recent times, numerous computer-aided diagnostic techniques utilizing magnetic resonance imaging (MRI) have demonstrated promising outcomes in the categorization of Alzheimer's disease (AD). The OASIS MRI dataset was utilized which has 80,000 brain MRI images. It is suggested to resample this dataset as it is highly imbalanced and posed a challenge in preventing bias toward majority class while employing the convolution neural network (CNN) model for classification. This paper examines and extracts patterns and features of 461 patients taken from the OASIS dataset. The research has aimed at utilizing the Base Model of EfficientNetV2B0 with custom classification layers, and simplified custom CNN model, also exploring Multi-class classification across four distinct classes: Non-Demented, Very Mild Demented, Mild Demented, Moderate Demented in addition to binary classification as Non-Demented and treating other classes as demented. Furthermore, different dataset sizes were experimented with 5,000 and 20,000 for each class to be discussed in this paper. The experiment results indicate that EfficientNetV2B0 achieved the accuracy of 98% in binary classification, 99% in multiclass. Whereas custom sequential CNN model in multiclass classification presents the accuracy of 96% for 20,000 dataset size and 98% for 80,000 dataset size.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.12
• /
• pp.1729-1738
• /
• 2021

Machine learning has a close relationship with cognitive psychology and brain science and is developing together. This paper analyzes the OASIS-3 dataset using machine learning techniques and proposes a model for predicting dementia. Dimensional reduction through PCA (Principal Component Analysis) is performed on the data quantifying the volume of each area among OASIS-3 data, and only important elements (features) are extracted and then various machine learning including gradient boosting and stacking Apply the models and compare the performance of each. Unlike previous studies, the proposed technique has a great differentiation because it uses not only the brain biometric data, but also basic information data such as the participant's gender and medical information data of the participant. In addition, it was shown that the proposed technique through various performance evaluations is a model that can better predict dementia by finding features that are more related to dementia among various numerical data.

• Annual Conference of KIPS
• /
• 2024.10a
• /
• pp.686-687
• /
• 2024

This study aims to predict MMSE scores in Alzheimer's disease (AD) patients using a CNN-LSTM model that processes MRI images and metadata. The OASIS-2 dataset was used, with MRI slices (central, ±10mm, and ±15mm) and metadata. Two datasets were created: one with central and ±10mm slices (10mm dataset), and another with central, ±10mm, and ±15mm slices (combined dataset). The CNN-LSTM model extracted features using VGG16 and combined them with metadata to predict MMSE scores. The 10mm model outperformed the combined model, achieving an MSE of 0.527 and MAE of 0.509. This study highlights the potential of predicting MMSE scores using MRI and metadata for early diagnosis of AD.

• Journal of Society of Preventive Korean Medicine
• /
• v.28 no.2
• /
• pp.131-150
• /
• 2024

Objectives : The aim of this study was to perform network analysis and analysis using the K-HERB database on inflammatory bowel disease (IBD), to verify the similarity between the derived networks and existing prescriptions, and to explore the possibility of developing new IBD prescriptions preliminarily. Methods : We conducted a comprehensive literature search on July 6, 2024, utilizing databases such as ScienceON, RISS, and OASIS. Clinical studies assessing the efficacy of herbal medicine in treating Crohn's disease and ulcerative colitis were identified and compiled into a structured database. This dataset, which included related prescriptions and herbal formulations, was subsequently analyzed using NetMiner 4 for centrality and Louvain clustering analyses. We then compared the networks derived from the K-HERB database with existing therapeutic prescriptions to assess their similarity. Results : A total of 24 prescriptions and 66 herbs were identified across the surveyed studies on IBD. Paeoniae Radix Alba(白芍藥) emerged as the most frequently utilized herb for both Crohn's disease and ulcerative colitis. Prominent herb combinations included Paeoniae Radix Alba-Angelicae Sinensis Radix (白芍藥-當歸), Angelicae Sinensis Radix-Coptidis Rhizoma (當歸-黃連), and Coptidis Rhizoma-Scutellariae Radix (黃連-黃芩) for ulcerative colitis. Centrality analysis revealed that Poria cocos (茯苓) and Paeoniae Radix Alba (白芍藥) had high centrality in the Crohn's disease, while Angelicae Sinensis Radix (當歸) and Paeoniae Radix Alba (白芍藥) had high centrality in the ulcerative colitis, indicating their prominent roles within the networks. Cohesion analysis resulted in 7 networks for Crohn's disease and 16 networks for ulcerative colitis. After excluding networks with a single herb, three networks related to Crohn's disease and two related to ulcerative colitis were examined using the K-HERB database. Among the 14 derived prescriptions for Crohn's disease and seven for ulcerative colitis, all except Oryeong-san (五苓散) were non-traditional in the context of IBD treatment. Conclusion : This preliminary study may provide a basis for the understanding and application of herbal prescriptions for IBD based on network analysis and the K-HERB database.