Ph.D in Biotechnology who has recently joined an eCommerce startup in Hong Kong
Do our memories, which fade as we age define who we are? Do we not exist if our memories fail us?
How Exactly Does Memory Work? The function for short term memory storage came to light from the case of Henry Molaison in the 1950s, during epilepsy surgry both his hippocampus were damaged and was unable to make new memories but retained his old ones before the operation (read more). A recent study has found that 2 duplicate memories are created simultaneously and are stored in both the hippocampus - for short term and the cortex - for long-term retrival. (read more)
I Am Because I Loved Alzheimer's disease is an irreversible brain disorder that slowly and progressively wipes away memory and cognitive skills. It is caused by faulty proteins amyloid and tau that build up in the brain. In the movie "Eternal Sunshine of the Spotless Mind" Jim Carrey and Kate Winslet play lovers who after a terrible fight (read more) hires Lacuna, a firm that specialises in wiping away all references of one's memory for a particular episode in life. The movie had a happy ending, meeting unwittingly 2 years after the procedure only to fall in love again.
Helping Family Members With Dementia Caring for family members with dementia is heartbreaking. Joey Daley whose mother Molly, breaks down in front of the camera when she struggles to remember who he is - he documents his life with his mother on a daily basis (read more), his pain is evident. David Baddiel uses humour to manage his pain by creating a reality tv show 'My Family:Not the Sitcom', an exploration of his father - diagnosed with picks disease, a form of dementia (read more).
Staying Sharp Researchers at Massachusetts General Hospital, scanned brain areas of a unique group of adults in their 60s and 70s with minds as sharp as people n their 20s, in that are related to memory such as the anterior insula and orbitofrontal cortex and the hippocampus using Magnetic Resonance Imaging (MRI). They called super agers whose scanned areas were thicker than their younger counterpartrs. Factors that prevent dementia include having a good nights sleep, not smoking and overall low cholesterol (read more)
Abstract: Neurodegenerative diseases are frequently associated with structural changes in the brain. Magnetic resonance imaging (MRI) scans can show these variations and therefore can be used as a supportive feature for a number of neurodegenerative diseases. The hippocampus has been known to be a biomarker for Alzheimer disease and other neurological and psychiatric diseases. However, it requires accurate, robust, and reproducible delineation of hippocampal structures. Fully automatic methods are usually the voxel based approach; for each voxel a number of local features were calculated. In this paper, we compared four different techniques for feature selection from a set of 315 features extracted for each voxel: (i) filter method based on the Kolmogorov-Smirnov test; two wrapper methods, respectively, (ii) sequential forward selection and (iii) sequential backward elimination; and (iv) embedded method based on the Random Forest Classifier on a set of 10 T1-weighted brain MRIs and tested on an independent set of 25 subjects. The resulting segmentations were compared with manual reference labelling. By using only 23 feature for each voxel (sequential backward elimination) we obtained comparable state-of-the-art performances with respect to the standard tool FreeSurfer.
Pub.: 20 Jun '15, Pinned: 17 Apr '17
Abstract: Egocentric vision technology consists in capturing the actions of persons from their own visual point of view using wearable camera sensors. We apply this new paradigm to instrumental activities monitoring with the objective of providing new tools for the clinical evaluation of the impact of the disease on persons with dementia. In this paper, we introduce the current state of the development of this technology and focus on two technology modules: automatic location estimation and visual saliency estimation for content interpretation.
Pub.: 13 Mar '13, Pinned: 17 Apr '17
Abstract: We classify very-mild to moderate dementia in patients (CDR ranging from 0 to 2) using a support vector machine classifier acting on dimensionally reduced feature set derived from MRI brain scans of the 416 subjects available in the OASIS-Brains dataset. We use image segmentation and principal component analysis to reduce the dimensionality of the data. Our resulting feature set contains 11 features for each subject. Performance of the classifiers is evaluated using 10-fold cross-validation. Using linear and (gaussian) kernels, we obtain a training classification accuracy of 86.4% (90.1%), test accuracy of 85.0% (85.7%), test precision of 68.7% (68.5%), test recall of 68.0% (74.0%), and test Matthews correlation coefficient of 0.594 (0.616).
Pub.: 25 Jun '14, Pinned: 17 Apr '17
Abstract: Episodic memories initially require rapid synaptic plasticity within the hippocampus for their formation and are gradually consolidated in neocortical networks for permanent storage. However, the engrams and circuits that support neocortical memory consolidation have thus far been unknown. We found that neocortical prefrontal memory engram cells, which are critical for remote contextual fear memory, were rapidly generated during initial learning through inputs from both the hippocampal-entorhinal cortex network and the basolateral amygdala. After their generation, the prefrontal engram cells, with support from hippocampal memory engram cells, became functionally mature with time. Whereas hippocampal engram cells gradually became silent with time, engram cells in the basolateral amygdala, which were necessary for fear memory, were maintained. Our data provide new insights into the functional reorganization of engrams and circuits underlying systems consolidation of memory.
Pub.: 08 Apr '17, Pinned: 17 Apr '17
Abstract: For the last decade, it has been shown that neuroimaging can be a potential tool for the diagnosis of Alzheimer's Disease (AD) and its prodromal stage, Mild Cognitive Impairment (MCI), and also fusion of different modalities can further provide the complementary information to enhance diagnostic accuracy. Here, we focus on the problems of both feature representation and fusion of multimodal information from Magnetic Resonance Imaging (MRI) and Positron Emission Tomography (PET). To our best knowledge, the previous methods in the literature mostly used hand-crafted features such as cortical thickness, gray matter densities from MRI, or voxel intensities from PET, and then combined these multimodal features by simply concatenating into a long vector or transforming into a higher-dimensional kernel space. In this paper, we propose a novel method for a high-level latent and shared feature representation from neuroimaging modalities via deep learning. Specifically, we use Deep Boltzmann Machine (DBM)(2), a deep network with a restricted Boltzmann machine as a building block, to find a latent hierarchical feature representation from a 3D patch, and then devise a systematic method for a joint feature representation from the paired patches of MRI and PET with a multimodal DBM. To validate the effectiveness of the proposed method, we performed experiments on ADNI dataset and compared with the state-of-the-art methods. In three binary classification problems of AD vs. healthy Normal Control (NC), MCI vs. NC, and MCI converter vs. MCI non-converter, we obtained the maximal accuracies of 95.35%, 85.67%, and 74.58%, respectively, outperforming the competing methods. By visual inspection of the trained model, we observed that the proposed method could hierarchically discover the complex latent patterns inherent in both MRI and PET.
Pub.: 22 Jul '14, Pinned: 17 Apr '17
Abstract: Accurate classification of Alzheimer's disease (AD) and its prodromal stage, mild cognitive impairment (MCI), plays a critical role in possibly preventing progression of memory impairment and improving quality of life for AD patients. Among many research tasks, it is of a particular interest to identify noninvasive imaging biomarkers for AD diagnosis. In this paper, we present a robust deep learning system to identify different progression stages of AD patients based on MRI and PET scans. We utilized the dropout technique to improve classical deep learning by preventing its weight coadaptation, which is a typical cause of overfitting in deep learning. In addition, we incorporated stability selection, an adaptive learning factor, and a multitask learning strategy into the deep learning framework. We applied the proposed method to the ADNI dataset, and conducted experiments for AD and MCI conversion diagnosis. Experimental results showed that the dropout technique is very effective in AD diagnosis, improving the classification accuracies by 5.9% on average as compared to the classical deep learning methods.
Pub.: 09 May '15, Pinned: 17 Apr '17