Three-dimensional Convolutional Neural Network Research Articles

Text3D: 3D Convolutional Neural Networks for Text Classification

Convolutional Neural Networks (CNNs) have demonstrated promising performance in many NLP tasks owing to their excellent local feature-extraction capability. Many previous works have made word-level 2D CNNs deeper to capture global representations of text. Three-dimensional CNNs perform excellently in CV tasks through spatiotemporal feature learning, though they are little utilized in text classification task. This paper proposes a simple, yet effective, approach for hierarchy feature learning using 3D CNN in text classification tasks, named Text3D. Text3D efficiently extracts rich information through text representations structured in three dimensions produced by pretrained language model BERT. Specifically, our Text3D utilizes word order, word embedding and hierarchy information of BERT encoder layers as features of three dimensions. The proposed model with 12 layers outperforms the baselines on four benchmark datasets for sentiment classification and topic categorization. Text3D with a different hierarchy of output from BERT layers demonstrates that the linguistic features from different layers have varied effects on text classification.

Non-Invasive Estimation of Gleason Score by Semantic Segmentation and Regression Tasks Using a Three-Dimensional Convolutional Neural Network

The Gleason score (GS) is essential in categorizing prostate cancer risk using biopsy. The aim of this study was to propose a two-class GS classification (< and ≥GS 7) methodology using a three-dimensional convolutional neural network with semantic segmentation to predict GS non-invasively using multiparametric magnetic resonance images (MRIs). Four training datasets of T2-weighted images and apparent diffusion coefficient maps with and without semantic segmentation were used as test images. All images and lesion information were selected from a training cohort of the Society of Photographic Instrumentation Engineers, the American Association of Physicists in Medicine, and the National Cancer Institute (SPIE–AAPM–NCI) PROSTATEx Challenge dataset. Precision, recall, overall accuracy and area under the receiver operating characteristics curve (AUROC) were calculated from this dataset, which comprises publicly available prostate MRIs. Our data revealed that the GS ≥ 7 precision (0.73 ± 0.13) and GS < 7 recall (0.82 ± 0.06) were significantly higher using semantic segmentation (p < 0.05). Moreover, the AUROC in segmentation volume was higher than that in normal volume (ADCmap: 0.70 ± 0.05 and 0.69 ± 0.08, and T2WI: 0.71 ± 0.07 and 0.63 ± 0.08, respectively). However, there were no significant differences in overall accuracy between the segmentation and normal volume. This study generated a diagnostic method for non-invasive GS estimation from MRIs.

Crop Type Mapping Based on Polarization Information of Time Series Sentinel-1 Images Using Patch-Based Neural Network

Large-scale crop mapping is of fundamental importance to tackle food security problems. SAR remote sensing has lately received great attention for crop type mapping due to its stability in the revisit cycle and is not hindered by cloud cover. However, most SAR image-classification studies focused on the application of backscattering characteristics with machine learning models, while few investigated the potential of the polarization decomposition and deep-learning models. This study investigated whether the radar polarization information mined by polarization decomposition, the patch strategy and the approaches for combining recurrent and convolutional neural networks (Conv2d + LSTM and ConvLSTM2d) could effectively improve the accuracy of crop type mapping. Sentinel-1 SLC and GRD products in 2020 were collected as data sources to extract VH, VV, VH/VV, VV + VH, Entropy, Anisotropy, and Alpha 7-dimensional features for classification. The results showed that the three-dimensional Convolutional Neural Network (Conv3d) was the best classifier with an accuracy and kappa up to 88.9% and 0.875, respectively, and the ConvLSTM2d and Conv2d + LSTM achieved the second and third position. Compared to backscatter coefficients, the polarization decomposition features could provide additional phase information for classification in the time dimension. The optimal patch size was 17, and the patch-based Conv3d outperformed the pixel-based Conv1d by 11.3% in accuracy and 0.128 in kappa. This study demonstrated the value of applying polarization decomposition features to deep-learning models and provided a strong technical support to efficient large-scale crop mapping.

Research on the optimization of prefabricated building preset scheme integrating BIM technology and BiLSTM model

Abstract With the rapid and continuous innovation and development of science and technology in the construction industry in recent years, prefabricated building technology has greatly improved the overall efficiency in the management of the construction and production process and the application of BIM (building information model) technology in prefabricated buildings has also increased. More and more widely. BIM technology combined with the Bi-LSTM model to mine the characteristics of preset scheme optimization to realize intelligent analysis. Furthermore, by constructing a three-dimensional convolutional neural network (3D-CNN), it can effectively carry out multi-dimensional analysis on the preset scheme of prefabricated buildings. Compared with the traditional Bi-LSTM model, combined with BIM-CNN-Bi-LSTM technology, the F1 value coefficient can be increased from 0.3 to 0.87; the comprehensive use of construction technology process for comprehensive and effective comprehensive optimization of various technologies opens the transition from the traditional linear design process to the horizontal design process in which multiple parties participate in the design.

Automated segmentation of the human supraclavicular fat depot via deep neural network in water-fat separated magnetic resonance images.

Human brown adipose tissue (BAT), mostly located in the cervical/supraclavicular region, is a promising target in obesity treatment. Magnetic resonance imaging (MRI) allows for mapping the fat content quantitatively. However, due to the complex heterogeneous distribution of BAT, it has been difficult to establish a standardized segmentation routine based on magnetic resonance (MR) images. Here, we suggest using a multi-modal deep neural network to detect the supraclavicular fat pocket. A total of 50 healthy subjects [median age/body mass index (BMI) =36 years/24.3 kg/m2] underwent MRI scans of the neck region on a 3 T Ingenia scanner (Philips Healthcare, Best, Netherlands). Manual segmentations following fixed rules for anatomical borders were used as ground truth labels. A deep learning-based method (termed as BAT-Net) was proposed for the segmentation of BAT on MRI scans. It jointly leveraged two-dimensional (2D) and three-dimensional (3D) convolutional neural network (CNN) architectures to efficiently encode the multi-modal and 3D context information from multi-modal MRI scans of the supraclavicular region. We compared the performance of BAT-Net to that of 2D U-Net and 3D U-Net. For 2D U-Net, we analyzed the performance difference of implementing 2D U-Net in three different planes, denoted as 2D U-Net (axial), 2D U-Net (coronal), and 2D U-Net (sagittal). The proposed model achieved an average dice similarity coefficient (DSC) of 0.878 with a standard deviation of 0.020. The volume segmented by the network was smaller compared to the ground truth labels by 9.20 mL on average with a mean absolute increase in proton density fat fraction (PDFF) inside the segmented regions of 1.19 percentage points. The BAT-Net outperformed all implemented 2D U-Nets and the 3D U-Nets with average DSC enhancement ranging from 0.016 to 0.023. The current work integrates a deep neural network-based segmentation into the automated segmentation of supraclavicular fat depot for quantitative evaluation of BAT. Experiments show that the presented multi-modal method benefits from leveraging both 2D and 3D CNN architecture and outperforms the independent use of 2D or 3D networks. Deep learning-based segmentation methods show potential towards a fully automated segmentation of the supraclavicular fat depot.

Classification of lung cancer computed tomography images using a 3-dimensional deep convolutional neural network with multi-layer filter.

Lung cancer creates pulmonary nodules in the patient's lung, which may be diagnosed early on using computer-aided diagnostics. A novel automated pulmonary nodule diagnosis technique using three-dimensional deep convolutional neural networks and multi-layered filter has been presented in this paper. For the suggested automated diagnosis of lung nodule, volumetric computed tomographic images are employed. The proposed approach generates three-dimensional feature layers, which retain the temporal links between adjacent slices of computed tomographic images. The use of several activation functions at different levels of the proposed network results in increased feature extraction and efficient classification. The suggested approach divides lung volumetric computed tomography pictures into malignant and benign categories. The suggested technique's performance is evaluated using three commonly used datasets in the domain: LUNA 16, LIDC-IDRI, and TCIA. The proposed method outperforms the state-of-the-art in terms of accuracy, sensitivity, specificity, F-1 score, false-positive rate, false-negative rate, and error rate.

Fault Diagnosis in an Asynchronous Motor Using Three-Dimensional Convolutional Neural Network

Fault Diagnosis in an Asynchronous Motor Using Three-Dimensional Convolutional Neural Network

Hyperspectral Imaging Combined with Deep Learning to Detect Ischemic Necrosis in Small Intestinal Tissue

Obtaining adequate resection margins in small intestinal necrotic tissue remains challenging due to the lack of intraoperative feedback. Here, we used hyperspectral imaging (HSI), an imaging technique for objective identification, combined with deep learning methods for automated small intestine tissue classification. As part of a prospective experimental study, we recorded hyperspectral datasets of small intestine biopsies from seven white rabbits. Based on the differences in the spectral characteristics of normal and ischemic necrotic small intestinal tissues in the wavelength range of 400–1000 nm, we applied deep learning techniques to objectively distinguish between these two types of tissues. The results showed that three-dimensional convolutional neural networks were more effective in extracting both spectral and spatial features of small intestine tissue hyperspectral data for classification. The combination of a deep learning model and HSI provided a new idea for the objective identification of ischemic necrotic tissue in the small intestine.

Deep multi-scale three-dimensional convolutional neural network optimized with manta ray foraging optimization algorithm for classification of lung cancer on CT images

ABSTRACT Lung cancer starts in the lungs and spreads to other organs in the body. Premature identification can only help the doctor to make an exact diagnosis and it may save the life of patients. Numerous studies have been conducted in this area, but none of them attains the accuracy outcomes. To overcome this drawback, a deep multi-scale three dimensional convolutional neural network optimized with the manta ray foraging optimization algorithm is proposed in this article for lung cancer classification on CT images (LCCT-DMS3DCNN-MRFOA) which effectively classifies the lung cancer as benign or malignant. The simulation is executed in MATLAB. The ELCAP dataset is utilized to confirm the performance of the proposed LCCT-DMS3DCNN-MRFOA approach. The efficiency of the LCCT-DMS3DCNN-MRFOA approach attains 14.21%, 22.96% and 24.94% higher accuracy; 12.59%, 11.71% and 11.55% higher AUC and 59.83%, 53.05% and 61.41% lower computational time compared with existing methods.

A benchmark study of convolutional neural networks in fully automatic segmentation of aortic root.

Recent clinical studies have suggested that introducing 3D patient-specific aortic root models into the pre-operative assessment procedure of transcatheter aortic valve replacement (TAVR) would reduce the incident rate of peri-operative complications. Tradition manual segmentation is labor-intensive and low-efficient, which cannot meet the clinical demands of processing large data volumes. Recent developments in machine learning provided a viable way for accurate and efficient medical image segmentation for 3D patient-specific models automatically. This study quantitively evaluated the auto segmentation quality and efficiency of the four popular segmentation-dedicated three-dimensional (3D) convolutional neural network (CNN) architectures, including 3D UNet, VNet, 3D Res-UNet and SegResNet. All the CNNs were implemented in PyTorch platform, and low-dose CTA image sets of 98 anonymized patients were retrospectively selected from the database for training and testing of the CNNs. The results showed that despite all four 3D CNNs having similar recall, Dice similarity coefficient (DSC), and Jaccard index on the segmentation of the aortic root, the Hausdorff distance (HD) of the segmentation results from 3D Res-UNet is 8.56 ± 2.28, which is only 9.8% higher than that of VNet, but 25.5% and 86.4% lower than that of 3D UNet and SegResNet, respectively. In addition, 3D Res-UNet and VNet also performed better in the 3D deviation location of interest analysis focusing on the aortic valve and the bottom of the aortic root. Although 3D Res-UNet and VNet are evenly matched in the aspect of classical segmentation quality evaluation metrics and 3D deviation location of interest analysis, 3D Res-UNet is the most efficient CNN architecture with an average segmentation time of 0.10 ± 0.04 s, which is 91.2%, 95.3% and 64.3% faster than 3D UNet, VNet and SegResNet, respectively. The results from this study suggested that 3D Res-UNet is a suitable candidate for accurate and fast automatic aortic root segmentation for pre-operative assessment of TAVR.

Research on Radar Echo Extrapolation Method by Fusing Environment Grid Point Field Information

Short-term extrapolation by weather radar observations is one of the main tools for making weather forecasts. Recently, deep learning has been gradually applied to radar extrapolation techniques, achieving significant results. However, for radar echo images containing strong convective systems, it is difficult to obtain high-quality results with long-term extrapolation. Additionally, there are few attempts and discussions to incorporate environmental factors governing the occurrence and development of convective storms into the training process. To demonstrate the positive effect of environmental factors on radar echo extrapolation tasks, this paper designs a three-dimensional convolutional neural network. The paper outlines the processing steps for matching radar echo images with environmental data in the spatio–temporal dimension. Additionally, it develops an experimental study on the effectiveness of seven physical elements and their combinations in improving the quality of radar echo extrapolation. Furthermore, a loss function is adopted to guide the training process of the model to pay more attention to strong convective systems. The quantitative statistical evaluation shows the critical success index (CSI) of our model’s prediction is improved by 3.42% (threshold = 40 dBZ) and 2.35% (threshold = 30 dBZ) after incorporating specific environmental field data. Two representative cases indicate that environmental factors provide essential information about convective systems, especially in predicting the birth, extinction, merging, and splitting of convective cells.

A Study of Dance Movement Capture and Posture Recognition Method Based on Vision Sensors

With the development of technology, posture recognition methods have been applied in more and more fields. However, there is relatively little research on posture recognition in dance. Therefore, this paper studied the capture and posture recognition of dance movements to understand the usability of the proposed method in dance posture recognition. Firstly, the Kinect V2 visual sensor was used to capture dance movements and obtain human skeletal joint data. Then, a three-dimensional convolutional neural network (3D CNN) model was designed by fusing joint coordinate features with joint velocity features as general features for recognizing different dance postures. Through experiments on NTU60 and self-built dance datasets, it was found that the 3D CNN performed best with a dropout rate of 0.4, a ReLU activation function, and fusion features. Compared to other posture recognition methods, the recognition rates of the 3D CNN on CS and CV in NTU60 were 88.8% and 95.3%, respectively, while the average recognition rate on the dance dataset reached 98.72%, which was higher than others. The experimental results demonstrate the effectiveness of our proposed method for dance posture recognition, providing a new approach for posture recognition research and making contributions to the inheritance of folk dances. Doi: 10.28991/HIJ-2023-04-02-03 Full Text: PDF

Three-dimensional convolutional neural network model to identify clinically significant prostate cancer in transrectal ultrasound videos: a prospective, multi-institutional, diagnostic study.

Identifying patients with clinically significant prostate cancer (csPCa) before biopsy helps reduce unnecessary biopsies and improve patient prognosis. The diagnostic performance of traditional transrectal ultrasound (TRUS) for csPCa is relatively limited. This study was aimed to develop a high-performance convolutional neural network (CNN) model (P-Net) based on a TRUS video of the entire prostate and investigate its efficacy in identifying csPCa. Between January 2021 and December 2022, this study prospectively evaluated 832 patients from four centres who underwent prostate biopsy and/or radical prostatectomy. All patients had a standardised TRUS video of the whole prostate. A two-dimensional CNN (2D P-Net) and three-dimensional CNN (3D P-Net) were constructed using the training cohort (559 patients) and tested on the internal validation cohort (140 patients) as well as on the external validation cohort (133 patients). The performance of 2D P-Net and 3D P-Net in predicting csPCa was assessed in terms of the area under the receiver operating characteristic curve (AUC), biopsy rate, and unnecessary biopsy rate, and compared with the TRUS 5-point Likert score system as well as multiparametric magnetic resonance imaging (mp-MRI) prostate imaging reporting and data system (PI-RADS) v2.1. Decision curve analyses (DCAs) were used to determine the net benefits associated with their use. The study is registered at https://www.chictr.org.cn with the unique identifier ChiCTR2200064545. The diagnostic performance of 3D P-Net (AUC: 0.85-0.89) was superior to TRUS 5-point Likert score system (AUC: 0.71-0.78, P=0.003-0.040), and similar to mp-MRI PI-RADS v2.1 score system interpreted by experienced radiologists (AUC: 0.83-0.86, P=0.460-0.732) and 2D P-Net (AUC: 0.79-0.86, P=0.066-0.678) in the internal and external validation cohorts. The biopsy rate decreased from 40.3% (TRUS 5-point Likert score system) and 47.6% (mp-MRI PI-RADS v2.1 score system) to 35.5% (2D P-Net) and 34.0% (3D P-Net). The unnecessary biopsy rate decreased from 38.1% (TRUS 5-point Likert score system) and 35.2% (mp-MRI PI-RADS v2.1 score system) to 32.0% (2D P-Net) and 25.8% (3D P-Net). 3D P-Net yielded the highest net benefit according to the DCAs. 3D P-Net based on a prostate grayscale TRUS video achieved satisfactory performance in identifying csPCa and potentially reducing unnecessary biopsies. More studies to determine how AI models better integrate into routine practice and randomized controlled trials to show the values of these models in real clinical applications are warranted. The National Natural Science Foundation of China (Grants 82202174 and 82202153), the Science and Technology Commission of Shanghai Municipality (Grants 18441905500 and 19DZ2251100), Shanghai Municipal Health Commission (Grants 2019LJ21 and SHSLCZDZK03502), Shanghai Science and Technology Innovation Action Plan (21Y11911200), and Fundamental Research Funds for the Central Universities (ZD-11-202151), Scientific Research and Development Fund of Zhongshan Hospital of Fudan University (Grant 2022ZSQD07).

StrainNet: Improved Myocardial Strain Analysis of Cine MRI by Deep Learning from DENSE.

To develop a three-dimensional (two dimensions + time) convolutional neural network trained with displacement encoding with stimulated echoes (DENSE) data for displacement and strain analysis of cine MRI. In this retrospective multicenter study, a deep learning model (StrainNet) was developed to predict intramyocardial displacement from contour motion. Patients with various heart diseases and healthy controls underwent cardiac MRI examinations with DENSE between August 2008 and January 2022. Network training inputs were a time series of myocardial contours from DENSE magnitude images, and ground truth data were DENSE displacement measurements. Model performance was evaluated using pixelwise end-point error (EPE). For testing, StrainNet was applied to contour motion from cine MRI. Global and segmental circumferential strain (Ecc) derived from commercial feature tracking (FT), StrainNet, and DENSE (reference) were compared using intraclass correlation coefficients (ICCs), Pearson correlations, Bland-Altman analyses, paired t tests, and linear mixed-effects models. The study included 161 patients (110 men; mean age, 61 years ± 14 [SD]), 99 healthy adults (44 men; mean age, 35 years ± 15), and 45 healthy children and adolescents (21 males; mean age, 12 years ± 3). StrainNet showed good agreement with DENSE for intramyocardial displacement, with an average EPE of 0.75 mm ± 0.35. The ICCs between StrainNet and DENSE and FT and DENSE were 0.87 and 0.72, respectively, for global Ecc and 0.75 and 0.48, respectively, for segmental Ecc. Bland-Altman analysis showed that StrainNet had better agreement than FT with DENSE for global and segmental Ecc. StrainNet outperformed FT for global and segmental Ecc analysis of cine MRI.Keywords: Image Postprocessing, MR Imaging, Cardiac, Heart, Pediatrics, Technical Aspects, Technology Assessment, Strain, Deep Learning, DENSE Supplemental material is available for this article. © RSNA, 2023.

Exploring Dual-Energy CT Spectral Information for Machine Learning-Driven Lesion Diagnosis in Pre-Log Domain.

In this study, we proposed a computer-aided diagnosis (CADx) framework under dual-energy spectral CT (DECT), which operates directly on the transmission data in the pre-log domain, called CADxDE, to explore the spectral information for lesion diagnosis. The CADxDE includes material identification and machine learning (ML) based CADx. Benefits from DECT's capability of performing virtual monoenergetic imaging with the identified materials, the responses of different tissue types (e.g., muscle, water, and fat) in lesions at each energy can be explored by ML for CADx. Without losing essential factors in the DECT scan, a pre-log domain model-based iterative reconstruction is adopted to obtain decomposed material images, which are then used to generate the virtual monoenergetic images (VMIs) at selected n energies. While these VMIs have the same anatomy, their contrast distribution patterns contain rich information along with the n energies for tissue characterization. Thus, a corresponding ML-based CADx is developed to exploit the energy-enhanced tissue features for differentiating malignant from benign lesions. Specifically, an original image-driven multi-channel three-dimensional convolutional neural network (CNN) and extracted lesion feature-based ML CADx methods are developed to show the feasibility of CADxDE. Results from three pathologically proven clinical datasets showed 4.01% to 14.25% higher AUC (area under the receiver operating characteristic curve) scores than the scores of both the conventional DECT data (high and low energy spectrum separately) and the conventional CT data. The mean gain >9.13% in AUC scores indicated that the energy spectral-enhanced tissue features from CADxDE have great potential to improve lesion diagnosis performance.

An Efficient Cloud Classification Method Based on a Densely Connected Hybrid Convolutional Network for FY-4A

Understanding atmospheric motions and projecting climate changes depends significantly on cloud types, i.e., different cloud types correspond to different atmospheric conditions, and accurate cloud classification can help forecasts and meteorology-related studies to be more effectively directed. However, accurate classification of clouds is challenging and often requires certain manual involvement due to the complex cloud forms and dispersion. To address this challenge, this paper proposes an improved cloud classification method based on a densely connected hybrid convolutional network. A dense connection mechanism is applied to hybrid three-dimensional convolutional neural network (3D-CNN) and two-dimensional convolutional neural network (2D-CNN) architectures to use the feature information of the spatial and spectral channels of the FY-4A satellite fully. By using the proposed network, cloud categorization solutions with a high temporal resolution, extensive coverage, and high accuracy can be obtained without the need for any human intervention. The proposed network is verified using tests, and the results show that it can perform real-time classification tasks for seven different types of clouds and clear skies in the Chinese region. For the CloudSat 2B-CLDCLASS product as a test target, the proposed network can achieve an overall accuracy of 95.2% and a recall of more of than 82.9% for all types of samples, outperforming the other deep-learning-based techniques.

Prediction of compressive mechanical properties of three-dimensional mesoscopic aluminium foam based on deep learning method

To achieve efficient and accurate prediction of the mechanical properties of aluminium foam, this study proposes a deep learning-based mechanical property prediction framework. The aluminium foam modelling plug-in based on the Voronoi model is selected to establish a three-dimensional solid model of aluminium foam, and the voxelization method is utilized to transform the geometric model of aluminium foam into a voxel model that can be recognized by the neural network. The mechanical properties of aluminium foam are calculated by the finite element method, including the stress‒strain response, densification strain and plateau stress. A deep learning sample dataset containing the aluminium foam voxel model and mechanical properties is established. The deep learning model based on a three-dimensional convolutional neural network (3D-CNN) is trained to identify the mesostructure features of aluminium foam, and a high-precision mapping relationship between the mesostructure and the macroscale mechanical properties is established. The research results show that the deep learning model established in this research can efficiently and accurately predict the mechanical properties of aluminium foam. Compared with conventional prediction methods, the prediction method based on deep learning has more advantages in efficiency and accuracy, and is an effective alternative to numerical simulation. In addition, the mechanical property prediction framework is highly scalable, extending the application scope of deep learning in the field of materials.

Direct recognition of crystal structures via three-dimensional convolutional neural networks with high accuracy and tolerance to random displacements and missing atoms

Computational methods and machine learning algorithms for automatic information extraction are crucial to enable data-driven materials science. These approaches are changing materials characterization and analytics, which often require a user-specified threshold to e.g. detect structure or symmetries in structures with defects. Here, we present a machine learning-based approach that directly works on the original periodic arrangements of atoms based on a three-dimensional convolutional neural network without any transformation of descriptors. Our approach shows a high classification accuracy and tolerance to the presence of random displacements and missing atoms. Experimentally, we successfully reconstruct the ordered L12 precipitates extracted from atom probe tomography data, consistent with segmentation based on isocomposition surfaces. The convolutional layers are essential for the simultaneous identification of compositional and structural information, which also give rise to its high tolerance. Our work advances machine learning-based crystal structure identification for incomplete crystal structural data.

Development and validation of deep learning-based automatic brain segmentation for East Asians: A comparison with Freesurfer.

To develop and validate deep learning-based automatic brain segmentation for East Asians with comparison to data for healthy controls from Freesurfer based on a ground truth. A total of 30 healthy participants were enrolled and underwent T1-weighted magnetic resonance imaging (MRI) using a 3-tesla MRI system. Our Neuro I software was developed based on a three-dimensional convolutional neural networks (CNNs)-based, deep-learning algorithm, which was trained using data for 776 healthy Koreans with normal cognition. Dice coefficient (D) was calculated for each brain segment and compared with control data by paired t-test. The inter-method reliability was assessed by intraclass correlation coefficient (ICC) and effect size. Pearson correlation analysis was applied to assess the relationship between D values for each method and participant ages. The D values obtained from Freesurfer (ver6.0) were significantly lower than those from Neuro I. The histogram of the Freesurfer results showed remarkable differences in the distribution of D values from Neuro I. Overall, D values obtained by Freesurfer and Neuro I showed positive correlations, but the slopes and intercepts were significantly different. It was showed the largest effect sizes ranged 1.07-3.22, and ICC also showed significantly poor to moderate correlations between the two methods (0.498 ≤ ICC ≤ 0.688). For Neuro I, D values resulted in reduced residuals when fitting data to a line of best fit, and indicated consistent values corresponding to each age, even in young and older adults. Freesurfer and Neuro I were not equivalent when compared to a ground truth, where Neuro I exhibited higher performance. We suggest that Neuro I is a useful alternative for the assessment of the brain volume.

MOD3NN: A Framework for Automatic Signal Modulation Detection Using 3D CNN

In this work, we present an application of a three-dimensional convolutional neural network for the task of automatic modulation recognition from raw I/Q signal data. Raw I/Q signal data exhibits a special “helical” structure that can be exploited with three-dimensional convolutions (3D convolutions) to learn spatio-temporal features from the signal for the problem of modulation recognition. By tweaking the convolutional filters to learn the helical symmetry of the data, we can design a shallow network for automatic modulation recognition (AMR). We present the results of our experiments with raw I/Q signal data collected in an uncalibrated radio frequency (RF) environment using several different modulation schemes. We show that with our methods and implementation, we can achieve around 99 % accuracy for automatic modulation recognition, for a variety of practical modulation techniques without the need for explicit feature engineering.