Convolutional neural networks for classification of Alzheimer's disease: Overview and reproducible evaluation.

Deep learning, a state-of-the-art machine learning approach, has shown outstanding performance over traditional machine learning in identifying intricate structures in complex high-dimensional data, especially in the domain of computer vision. The application of deep learning to early detection and automated classification of Alzheimer's disease (AD) has recently gained considerable attention, as rapid progress in neuroimaging techniques has generated large-scale multimodal neuroimaging data. A systematic review of publications using deep learning approaches and neuroimaging data for diagnostic classification of AD was performed. A PubMed and Google Scholar search was used to identify deep learning papers on AD published between January 2013 and July 2018. These papers were reviewed, evaluated, and classified by algorithm and neuroimaging type, and the findings were summarized. Of 16 studies meeting full inclusion criteria, 4 used a combination of deep learning and traditional machine learning approaches, and 12 used only deep learning approaches. The combination of traditional machine learning for classification and stacked auto-encoder (SAE) for feature selection produced accuracies of up to 98.8% for AD classification and 83.7% for prediction of conversion from mild cognitive impairment (MCI), a prodromal stage of AD, to AD. Deep learning approaches, such as convolutional neural network (CNN) or recurrent neural network (RNN), that use neuroimaging data without pre-processing for feature selection have yielded accuracies of up to 96.0% for AD classification and 84.2% for MCI conversion prediction. The best classification performance was obtained when multimodal neuroimaging and fluid biomarkers were combined. Deep learning approaches continue to improve in performance and appear to hold promise for diagnostic classification of AD using multimodal neuroimaging data. AD research that uses deep learning is still evolving, improving performance by incorporating additional hybrid data types, such as-omics data, increasing transparency with explainable approaches that add knowledge of specific disease-related features and mechanisms.

/pdf/deep-learning-in-alzheimer-s-disease-diagnostic-535v1rlqlh.pdf

Deep Learning in Alzheimer's Disease: Diagnostic Classification and Prognostic Prediction Using Neuroimaging Data

This paper presents a novel end-to-end system for table understanding in document images called DeepDeSRT In particular, the contribution of DeepDeSRT is two-fold First, it presents a deep learning-based solution for table detection in document images Secondly, it proposes a novel deep learning-based approach for table structure recognition, ie identifying rows, columns, and cell positions in the detected tables In contrast to existing rule-based methods, which rely on heuristics or additional PDF metadata (like, for example, print instructions, character bounding boxes, or line segments), the presented system is data-driven and does not need any heuristics or metadata to detect as well as to recognize tabular structures in document images Furthermore, in contrast to most existing table detection and structure recognition methods, which are applicable only to PDFs, DeepDeSRT processes document images, which makes it equally suitable for born-digital PDFs (as they can automatically be converted into images) as well as even harder problems, eg scanned documents To gauge the performance of DeepDeSRT, the system is evaluated on the publicly available ICDAR 2013 table competition dataset containing 67 documents with 238 pages overall Evaluation results reveal that DeepDeSRT outperforms state-of-the-art methods for table detection and structure recognition and achieves F1-measures of 9677% and 9144% for table detection and structure recognition, respectively Additionally, DeepDeSRT is evaluated on a closed dataset from a real use case of a major European aviation company comprising documents which are highly unlike those in ICDAR 2013 Tested on a randomly selected sample from this dataset, DeepDeSRT achieves high detection accuracy for tables which demonstrates the sound generalization capabilities of our system

DeepDeSRT: Deep Learning for Detection and Structure Recognition of Tables in Document Images

Deep learning to detect Alzheimer's disease from neuroimaging: A systematic literature review.

Recognizing the layout of unstructured digital documents is an important step when parsing the documents into structured machine-readable format for downstream applications. Deep neural networks that are developed for computer vision have been proven to be an effective method to analyze layout of document images. However, document layout datasets that are currently publicly available are several magnitudes smaller than established computing vision datasets. Models have to be trained by transfer learning from a base model that is pre-trained on a traditional computer vision dataset. In this paper, we develop the PubLayNet dataset for document layout analysis by automatically matching the XML representations and the content of over 1 million PDF articles that are publicly available on PubMed Central. The size of the dataset is comparable to established computer vision datasets, containing over 360 thousand document images, where typical document layout elements are annotated. The experiments demonstrate that deep neural networks trained on PubLayNet accurately recognize the layout of scientific articles. The pre-trained models are also a more effective base mode for transfer learning on a different document domain. We release the dataset (this https URL) to support development and evaluation of more advanced models for document layout analysis.

PubLayNet: largest dataset ever for document layout analysis.

Table detection is a challenging problem and plays an important role in document layout analysis. In this paper, we propose an effective method to identify the table region from document images. First, the regions of interest (ROIs) are recognized as the table candidates. In each ROI, we locate text components and extract text blocks. After that, we check all text blocks to determine if they are arranged horizontally or vertically and compare the height of each text block with the average height. If the text blocks satisfy a series of rules, the ROI is regarded as a table. Experiments on the ICDAR 2013 dataset show that the results obtained are very encouraging. This proves the effectiveness and superiority of our proposed method.

Table Detection from Document Image using Vertical Arrangement of Text Blocks

In the last decade, pattern recognition methods using neuroimaging data for the diagnosis of Alzheimer's disease (AD) have been the subject of extensive research. Deep learning has recently been a great interest in AD classification. Previous works had done almost on single modality dataset, such as Magnetic Resonance Imaging (MRI) or Positron Emission Tomography (PET), shown high performances. However, identifying the distinctions between Alzheimer's brain data and healthy brain data in older adults (age > 75) is challenging due to highly similar brain patterns and image intensities. The corporation of multimodalities can solve this issue since it discovers and uses the further complementary of hidden biomarkers from other modalities instead of only one, which itself cannot provide. We therefore propose a deep learning method on fusion multimodalities. In details, our approach includes Sparse Autoencoder (SAE) and convolution neural network (CNN) train and test on combined PET-MRI data to diagnose the disease status of a patient. We focus on advantages of multimodalities to help providing complementary information than only one, lead to improve classification accuracy. We conducted experiments in a dataset of 1272 scans from ADNI study, the proposed method can achieve a classification accuracy of 90% between AD patients and healthy controls, demonstrate the improvement than using only one modality.

Multimodal learning using convolution neural network and Sparse Autoencoder

Twitter has become a potential data source to explore useful information mentioned by users. For instance, Twitter tweets related to an earthquake will be utilized to detect temporal occurrence as well as location information by a humanitarian organization. Therefore, we proposed a Convolution Neural Network (CNN) based method to determine informative tweet and the real-time event detection algorithm to detect the timely occurrence of the given event. In this study, CNN model trained from the tweets related to the earthquake in the past labeled by crowdsourcing plays a role as the classifier to predict an earthquake keyword related tweet is informative or not. Then these informative tweets are considered as input streaming data of time detection phase. Our system with the aid of CNN module can detect the earthquake after it happens in the level of tolerance and ensure earlier than an announcement from official disaster website of government.

Real-Time Earthquake Detection Using Convolutional Neural Network and Social Data

Electroencephalogram (EEG) is a signal recording of human brain or animal brain activities An EEG data is usually considered as a three-order tensor with a number of segments recorded in many time In this paper, a combination of Fast Fourier Transform (FFT) and Tucker decomposition (TD) is proposed to extract features from raw EEG data We used FFT as a way to remove some excess information effectively In order to extract better features, Tucker algorithm is also applied to decompose the tensor data into smaller part, but better, called the core part We evaluate the effect of the proposed method on epilepsy EEG data and compare the results of the way only used FFT Furthermore, we also show the difference between the data signal of one channel and its decomposer

Fast Fourier Transform and Tucker Decomposition for Feature Extraction in EEG Signals

With an objective of discovering compact features of unlabeled time series data and assessing the performance of grouping homogeneous patterns, this paper thus propose a mathematical modeling that could be capable of the general problem of multi-label time series clustering with high accuracy and reliability. The proposed method is an extension of original Kalman Filter algorithm that offers its main advantages by handling the complex characteristic of time series including: noise, temporal dynamics, correlation, time-lags, and harmonics. Consequently, the vital low-rank features extracted from the proposed approach have benefit properties including comprehensible, interpretable and visualizable that boost clustering quality. The experimental result on real-world dataset is presented to verify the contributions of the proposed method via improving significant performance compared with well-known competitors in both terms of its effectiveness and scalability.

A-Ran Oh

Papers

Table Detection from Document Image using Vertical Arrangement of Text Blocks

Multimodal learning using convolution neural network and Sparse Autoencoder

Real-Time Earthquake Detection Using Convolutional Neural Network and Social Data

Fast Fourier Transform and Tucker Decomposition for Feature Extraction in EEG Signals

Low-Feature Extraction for Multi-label Patterns Analyzing in Complex Time Series Mining