Autism Spectrum Disorder Detection by Hybrid Convolutional Recurrent Neural Networks from Structural and Resting State Functional MRI Images.

This study aims to increase the accuracy of autism spectrum disorder (ASD) diagnosis based on cognitive and behavioral phenotypes through multiple neuroimaging modalities. We apply machine learning (ML) algorithms to classify ASD patients and healthy control (HC) participants using structural magnetic resonance imaging (s-MRI) together with resting state functional MRI (rs-f-MRI and f-MRI) data from the large multisite data repository ABIDE (autism brain imaging data exchange) and identify important brain connectivity features. The 2D f-MRI images were converted into 3D s-MRI images, and datasets were preprocessed using the Montreal Neurological Institute (MNI) atlas. The data were then denoised to remove any confounding factors. We show, by using three fusion strategies such as early fusion, late fusion, and cross fusion, that, in this implementation, hybrid convolutional recurrent neural networks achieve better performance in comparison to either convolutional neural networks (CNNs) or recurrent neural networks (RNNs). The proposed model classifies subjects as autistic or not according to how functional and anatomical connectivity metrics provide an overall diagnosis based on the autism diagnostic observation schedule (ADOS) standard. Our hybrid network achieved an accuracy of 96% by fusing s-MRI and f-MRI together, which outperforms the methods used in previous studies.

A New Approach for Multimodal Usage of Gene Expression and Its Image Representation for the Detection of Alzheimer's Disease.

Alzheimer's disease (AD) is a complex neurodegenerative disorder and the multifaceted nature of it requires innovative approaches that integrate various data modalities to enhance its detection. However, due to the cost of collecting multimodal data, multimodal datasets suffer from an insufficient number of samples. To mitigate the impact of a limited sample size on classification, we introduce a novel deep learning method (One2MFusion) which combines gene expression data with their corresponding 2D representation as a new modality. The gene vectors were first mapped to a discriminative 2D image for training a convolutional neural network (CNN). In parallel, the gene sequences were used to train a feed forward neural network (FNN) and the outputs of the FNN and CNN were merged, and a joint deep network was trained for the binary classification of AD, normal control (NC), and mild cognitive impairment (MCI) samples. The fusion of the gene expression data and gene-originated 2D image increased the accuracy (area under the curve) from 0.86 (obtained using a 2D image) to 0.91 for AD vs. NC and from 0.76 (obtained using a 2D image) to 0.88 for MCI vs. NC. The results show that representing gene expression data in another discriminative form increases the classification accuracy when fused with base data.

Prediction of Alzheimer's Disease by a Novel Image-Based Representation of Gene Expression.

Early intervention can delay the progress of Alzheimer's Disease (AD), but currently, there are no effective prediction tools. The goal of this study is to generate a reliable artificial intelligence (AI) model capable of detecting the high risk of AD, based on gene expression arrays from blood samples. To that end, a novel image-formation method is proposed to transform single-dimension gene expressions into a discriminative 2-dimensional (2D) image to use convolutional neural networks (CNNs) for classification. Three publicly available datasets were pooled, and a total of 11,618 common genes' expression values were obtained. The genes were then categorized for their discriminating power using the Fisher distance (AD vs. control (CTL)) and mapped to a 2D image by linear discriminant analysis (LDA). Then, a six-layer CNN model with 292,493 parameters were used for classification. An accuracy of 0.842 and an area under curve (AUC) of 0.875 were achieved for the AD vs. CTL classification. The proposed method obtained higher accuracy and AUC compared with other reported methods. The conversion to 2D in CNN offers a unique advantage for improving accuracy and can be easily transferred to the clinic to drastically improve AD (or any disease) early detection.

Detection of aflatoxin and surface mould contaminated figs by using Fourier transform near-infrared reflectance spectroscopy.

BACKGROUND: Aflatoxins are toxic metabolites that are mainly produced by members of the Aspergillus section Flavi on many agricultural products. Certain agricultural products such as figs are known to be high risk products for aflatoxin contamination. Aflatoxin contaminated figs may show a bright greenish yellow fluorescence (BGYF) under ultraviolet (UV) light at a wavelength of 365 nm. Traditionally, BGYF positive figs are manually selected by workers. However, manual selection depends on the expertise level of the workers and it may cause them skin-related health problems due to UV radiation. RESULTS: In this study, we propose a non-invasive approach to detect aflatoxin and surface mould contaminated figs by using Fourier transform near-infrared (FT-NIR) reflectance spectroscopy. A classification accuracy of 100% is achieved for classifying the figs into aflatoxin contaminated/uncontaminated and surface mould contaminated/uncontaminated categories. In addition, a strong correlation has been found between aflatoxin and surface mould. CONCLUSION: Combined with pattern classification methods, the NIR spectroscopy can be used to detect aflatoxin contaminated figs non-invasively. Furthermore, a positive correlation between surface mould and aflatoxin contamination leads to a promising alternative indicator for the detection of aflatoxin-contaminated figs. © 2016 Society of Chemical Industry.

Non-invasive detection of aflatoxin-contaminated figs using fluorescence and multispectral imaging.

Agricultural products are prone to aflatoxin (AF)-producing moulds (Aspergillus flavus, A. parasiticus) during harvesting, drying, processing and also storage. AF is a mycotoxin that may cause liver cancer when consumed in amounts higher than allowed limits. Figs, like other agricultural products, are mostly affected by AF-producing moulds and these moulds usually produce kojic acid together with AF. Kojic acid is a fluorescent compound and exhibiting bright greenish yellow fluorescence (BGYF) under ultraviolet (UV) light. Using this fluorescence property, fig-processing plants manually select and remove the BGYF+ figs to reduce the AF level of the processed figs. Although manual selection is based on subjective criteria and strongly depends on the expertise level of the workers, it is known as the most effective way of removing AF-contaminated samples. However, during manual selection, workers are exposed to UV radiation and this brings skin health problems. In this study, we individually investigated the figs to measure their fluorescence level, surface mould concentration and AF levels and noted a strong correlation between mould concentration and BGYF and AF, and BGYF and surface. In addition to a pairwise correlation, we proposed a machine-vision and machine-learning approach to detect the AF-contaminated figs using their multispectral images under UV light. The figs were classified in two different approaches considering their surface mould and AF level with error rates of 9.38% and 11.98%, respectively.

Automated colorectal cancer diagnosis for whole-slice histopathology.

In this study, we propose a computational diagnosis system for detecting the colorectal cancer from histopathological slices. The computational analysis was usually performed on patch level where only a small part of the slice is covered. However, slice-based classification is more realistic for histopathological diagnosis. The developed method combines both textural and structural features from patch images and proposes a two level classification scheme. In the first level, the patches in slices are classified into possible classes (adenomatous, inflamed, cancer and normal) and the distribution of the patches into these classes is considered as the information representing the slices. Then the slices are classified using a logistic linear classifier. In patch level, we obtain the correct classification accuracies of 94.36% and 96.34% for the cancer and normal classes, respectively. However, in slice level, the accuracies of the 79.17% and 92.68% are achieved for cancer and normal classes, respectively.

Sampling of sentinel lymph nodes: a simulation study.

OBJECTIVE: To analyze the effects of various slicing schemes on the detection of metastases in lymph nodes. STUDY DESIGN: Use of an advanced computer simulation tool. RESULTS: Bisectioning along the longitudinal axis is an inadequate approach. Slicing ellipsoid lymph nodes along their longitudinal axis also results in a lower rate of detecting metastases since metastatic deposits have a predilection to localize subcapsularly. CONCLUSION: Ellipsoid lymph nodes must be sliced perpendicular to the longest axis to increase the rate of detecting metastases.