Qualitative Classification of Proximal Femoral Bone Using Geometric Features and Texture Analysis in Collected MRI Images for Bone Density Evaluation.

The aim of this study was to use geometric features and texture analysis to discriminate between healthy and unhealthy femurs and to identify the most influential features. We scanned proximal femoral bone (PFB) of 284 Iranian cases (21 to 83 years old) using different dual-energy X-ray absorptiometry (DEXA) scanners and magnetic resonance imaging (MRI) machines. Subjects were labeled as "healthy" (T-score > -0.9) and "unhealthy" based on the results of DEXA scans. Based on the geometry and texture of the PFB in MRI, 204 features were retrieved. We used support vector machine (SVM) with different kernels, decision tree, and logistic regression algorithms as classifiers and the Genetic algorithm (GA) to select the best set of features and to maximize accuracy. There were 185 participants classified as healthy and 99 as unhealthy. The SVM with radial basis function kernels had the best performance (89.08%) and the most influential features were geometrical ones. Even though our findings show the high performance of this model, further investigation with more subjects is suggested. To our knowledge, this is the first study that investigates qualitative classification of PFBs based on MRI with reference to DEXA scans using machine learning methods and the GA.

CNN-Res: deep learning framework for segmentation of acute ischemic stroke lesions on multimodal MRI images.

BACKGROUND: Accurate segmentation of stroke lesions on MRI images is very important for neurologists in the planning of post-stroke care. Segmentation helps clinicians to better diagnose and evaluation of any treatment risks. However, manual segmentation of brain lesions relies on the experience of neurologists and is also a very tedious and time-consuming process. So, in this study, we proposed a novel deep convolutional neural network (CNN-Res) that automatically performs the segmentation of ischemic stroke lesions from multimodal MRIs. METHODS: CNN-Res used a U-shaped structure, so the network has encryption and decryption paths. The residual units are embedded in the encoder path. In this model, to reduce gradient descent, the residual units were used, and to extract more complex information in images, multimodal MRI data were applied. In the link between the encryption and decryption subnets, the bottleneck strategy was used, which reduced the number of parameters and training time compared to similar research. RESULTS: CNN-Res was evaluated on two distinct datasets. First, it was examined on a dataset collected from the Neuroscience Center of Tabriz University of Medical Sciences, where the average Dice coefficient was equal to 85.43%. Then, to compare the efficiency and performance of the model with other similar works, CNN-Res was evaluated on the popular SPES 2015 competition dataset where the average Dice coefficient was 79.23%. CONCLUSION: This study presented a new and accurate method for the segmentation of MRI medical images using a deep convolutional neural network called CNN-Res, which directly predicts segment maps from raw input pixels.

Computing semantic similarity of texts based on deep graph learning with ability to use semantic role label information.

We propose a deep graph learning approach for computing semantic textual similarity (STS) by using semantic role labels generated by a Semantic Role Labeling (SRL) system. SRL system output has significant challenges in dealing with graph-neural networks because it doesn't have a graph structure. To address these challenges, we propose a novel SRL graph by using semantic role labels and dependency grammar. For processing the SRL graph, we proposed a Deep Graph Neural Network (DGNN) based graph-U-Net model that is placed on top of the transformers to use a variety of transformers to process representations obtained from them. We investigate the effect of using the proposed DGNN and SRL graph on the performance of some transformers in computing STS. For the evaluation of our approach, we use STS2017 and SICK datasets. Experimental evaluations show that using the SRL graph accompanied by applying the proposed DGNN increases the performance of the transformers used in the DGNN.

Early Detection of Alzheimer's Disease Based on Clinical Trials, Three-Dimensional Imaging Data, and Personal Information Using Autoencoders.

BACKGROUND: A timely diagnosis of Alzheimer's disease (AD) is crucial to obtain more practical treatments. In this article, a novel approach using Auto-Encoder Neural Networks (AENN) for early detection of AD was proposed. METHOD: The proposed method mainly deals with the classification of multimodal data and the imputation of missing data. The data under study involve the MiniMental State Examination, magnetic resonance imaging, positron emission tomography, cerebrospinal fluid data, and personal information. Natural logarithm was used for normalizing the data. The Auto-Encoder Neural Networks was used for imputing missing data. Principal component analysis algorithm was used for reducing dimensionality of data. Support Vector Machine (SVM) was used as classifier. The proposed method was evaluated using Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Then, 10fold crossvalidation was used to audit the detection accuracy of the method. RESULTS: The effectiveness of the proposed approach was studied under several scenarios considering 705 cases of ADNI database. In three binary classification problems, that is AD vs. normal controls (NCs), mild cognitive impairment (MCI) vs. NC, and MCI vs. AD, we obtained the accuracies of 95.57%, 83.01%, and 78.67%, respectively. CONCLUSION: Experimental results revealed that the proposed method significantly outperformed most of the stateoftheart methods.

The Recognition of Persian Phonemes Using PPNet.

BACKGROUND: In this paper, a novel approach is proposed for the recognition of Persian phonemes in the Persian consonant-vowel combination (PCVC) speech dataset. Nowadays, deep neural networks (NNs) play a crucial role in classification tasks. However, the best results in speech recognition are not yet as perfect as human recognition rate. Deep learning techniques show outstanding performance over many other classification tasks, such as image classification and document classification. Furthermore, the performance is sometimes better than a human. The reason why automatic speech recognition systems are not as qualified as the human speech recognition system, mostly depends on features of data which are fed to deep NNs. METHODS: In this research, first, the sound samples are cut for the exact extraction of phoneme sounds in 50 ms samples. Then, phonemes are divided into 30 groups, containing 23 consonants, 6 vowels, and a silence phoneme. RESULTS: The short-time Fourier transform is conducted on them, and the results are given to PPNet (a new deep convolutional NN architecture) classifier and a total average of 75.87% accuracy is reached which is the best result ever compared to other algorithms on separated Persian phonemes (like in PCVC speech dataset). CONCLUSION: This method not only can be used for recognizing mono-phonemes but it can also be adopted as an input to the selection of the best words in speech transcription.