Alzheimer's disease (AD) is a neurodegenerative disorder that affects the life quality of millions of people worldwide. To diagnose new cases in a timely manner, we propose a new novelty detection technique that combines Autoencoder and Minimum Covariance Determinant (MCD). The technique consists of two steps: first, we use an Autoencoder to extract low-dimensional and discriminative features from the publicly available ADNI dataset, where we only train the Autoencoder with normal data, making the abnormal data more distinguishable in the feature space; second, based on the features of normal data, we use MCD to construct a decision boundary, and judge the degree of abnormality by the distance of the test point to the boundary. Compared with traditional methods without using Autoencoder, our technique has significant advantages in terms of accuracy and sensitivity, and can effectively deal with data imbalance problem. Experimental results show that our method can efficiently detect novel AD cases, and has a wide range of application prospects.
Alzheimer's disease (AD) is a common neurodegenerative disease, whose early diagnosis is crucial for disease control and treatment. This study aims to explore the use of ensemble learning to analyze data from AD patients using multimodal inputs, including MRI image features extracted by convolutional neural networks (CNN), age, gender, APOE status and clinical functional scales. Firstly, we preprocess and extract the key image information features related to AD from MRI images. We then used multiple machine learning (ML) methods to build different classifiers, and combined these different classifiers by voting to obtain more accurate prediction results. Our method has been validated on a large AD patient database.The results demonstrated that the analysis of multimodal data can significantly improve the diagnostic accuracy of AD compared to single-mode data, while ensemble learning further improves the stability of the model.
Artificial intelligence techniques have been deeply involved in the heterogeneous data aspects of biomedical applications. However, the high dimensionality and computational complexity of data can make classification, pattern recognition and data visualization difficult. Choosing appropriate dimensionality reduction techniques can help increase processing speed, reduce the time and effort required to extract valuable information, and ensure high accuracy. In this study, Alzheimer's disease data were taken as an example. Individual cases with missing values were removed, and non-digital data were converted to digital data using Min-Max normalization. Then principal component analysis (PCA) was applied to map the original feature space to 1 dimension and the variance of the validation set was calculated by 5-fold cross-validation to find the appropriate K value. The results showed that when PCA was applied to reduce the data to 1 dimension, the AUC (95% confidence interval) of the KNN classifier reached 0.898 ± 0.014, which was 30.4%higher than the case without PCA. Our current findings suggest that in many busy clinics and hospitals, it is quite worthwhile to use dimensionality reduction methods to save model computing time and to use KNN models to obtain better accuracy.
Fluorescence correlation spectroscopy (FCS) is a powerful technique that could provide high temporal resolution and detection for the diffusions of biomolecules at extremely low concentrations. The accuracy of this approach primarily depends on experimental condition requirements and the data analysis model. In this study, we have set up a confocal-based FCS system. And then we used a Rhodamine6G solution to calibrate the system and get the related parameters. An experimental measurement was carried out on one-component solution to evaluate the relationship between a certain number of molecules and concentrations. The results showed FCS system we built was stable and valid. Finally, a two-component solution experiment was carried out to show the importance of analysis model selection. It is a promising method for single molecular diffusion study in living cells.
Cell mitosis plays a crucial role in cell life activity, which is one of the important phases in cell division cycle. During the mitosis, the cytoskeleton micro-structure of the cell changed and the biomechanical properties of the cell may vary depending upon different mitosis stages. In this study, the elasticity property of HeLa cells during mitosis was monitored by atomic force microscopy. Also, the actin filaments in different mitosis stages of the cells were observed by confocal imaging. Our results show that the cell in anaphase is stiffer than that in metaphase and telophase. Furthermore, lots of actin filaments gathered in cells’ center area in anaphase, which contributes to the rigidity of the cell in this phase. Our findings demonstrate that the nano-biomechanics of living cells could provide a new index for characterizing cell physiological states.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.