Multi-view Convolutional Neural Network Research Articles

Mammography classification with multi-view deep learning techniques: Investigating graph and transformer-based architectures

The potential and promise of deep learning systems to provide an independent assessment and relieve radiologists’ burden in screening mammography have been recognized in several studies. However, the low cancer prevalence, the need to process high-resolution images, and the need to combine information from multiple views and scales still pose technical challenges. Multi-view architectures that combine information from the four mammographic views to produce an exam-level classification score are a promising approach to the automated processing of screening mammography. However, training such architectures from exam-level labels, without relying on pixel-level supervision, requires very large datasets and may result in suboptimal accuracy. Emerging architectures such as Visual Transformers (ViT) and graph-based architectures can potentially integrate ipsi-lateral and contra-lateral breast views better than traditional convolutional neural networks, thanks to their stronger ability of modeling long-range dependencies. In this paper, we extensively evaluate novel transformer-based and graph-based architectures against state-of-the-art multi-view convolutional neural networks, trained in a weakly-supervised setting on a middle-scale dataset, both in terms of performance and interpretability. Extensive experiments on the CSAW dataset suggest that, while transformer-based architecture outperform other architectures, different inductive biases lead to complementary strengths and weaknesses, as each architecture is sensitive to different signs and mammographic features. Hence, an ensemble of different architectures should be preferred over a winner-takes-all approach to achieve more accurate and robust results. Overall, the findings highlight the potential of a wide range of multi-view architectures for breast cancer classification, even in datasets of relatively modest size, although the detection of small lesions remains challenging without pixel-wise supervision or ad-hoc networks.

Deciphering Optimal Radar Ensemble for Advancing Sleep Posture Prediction through Multiview Convolutional Neural Network (MVCNN) Approach Using Spatial Radio Echo Map (SREM).

Assessing sleep posture, a critical component in sleep tests, is crucial for understanding an individual's sleep quality and identifying potential sleep disorders. However, monitoring sleep posture has traditionally posed significant challenges due to factors such as low light conditions and obstructions like blankets. The use of radar technolsogy could be a potential solution. The objective of this study is to identify the optimal quantity and placement of radar sensors to achieve accurate sleep posture estimation. We invited 70 participants to assume nine different sleep postures under blankets of varying thicknesses. This was conducted in a setting equipped with a baseline of eight radars-three positioned at the headboard and five along the side. We proposed a novel technique for generating radar maps, Spatial Radio Echo Map (SREM), designed specifically for data fusion across multiple radars. Sleep posture estimation was conducted using a Multiview Convolutional Neural Network (MVCNN), which serves as the overarching framework for the comparative evaluation of various deep feature extractors, including ResNet-50, EfficientNet-50, DenseNet-121, PHResNet-50, Attention-50, and Swin Transformer. Among these, DenseNet-121 achieved the highest accuracy, scoring 0.534 and 0.804 for nine-class coarse- and four-class fine-grained classification, respectively. This led to further analysis on the optimal ensemble of radars. For the radars positioned at the head, a single left-located radar proved both essential and sufficient, achieving an accuracy of 0.809. When only one central head radar was used, omitting the central side radar and retaining only the three upper-body radars resulted in accuracies of 0.779 and 0.753, respectively. This study established the foundation for determining the optimal sensor configuration in this application, while also exploring the trade-offs between accuracy and the use of fewer sensors.

Vessel-targeted compensation of deformable motion in interventional cone-beam CT

The present standard of care for unresectable liver cancer is transarterial chemoembolization (TACE), which involves using chemotherapeutic particles to selectively embolize the arteries supplying hepatic tumors. Accurate volumetric identification of intricate fine vascularity is crucial for selective embolization. Three-dimensional imaging, particularly cone-beam CT (CBCT), aids in visualization and targeting of small vessels in such highly variable anatomy, but long image acquisition time results in intra-scan patient motion, which distorts vascular structures and tissue boundaries. To improve clarity of vascular anatomy and intra-procedural utility, this work proposes a targeted motion estimation and compensation framework that removes the need for any prior information or external tracking and for user interaction. Motion estimation is performed in two stages: (i) a target identification stage that segments arteries and catheters in the projection domain using a multi-view convolutional neural network to construct a coarse 3D vascular mask; and (ii) a targeted motion estimation stage that iteratively solves for the time-varying motion field via optimization of a vessel-enhancing objective function computed over the target vascular mask. The vessel-enhancing objective is derived through eigenvalues of the local image Hessian to emphasize bright tubular structures. Motion compensation is achieved via spatial transformer operators that apply time-dependent deformations to partial angle reconstructions, allowing efficient minimization via gradient backpropagation. The framework was trained and evaluated in anatomically realistic simulated motion-corrupted CBCTs mimicking TACE of hepatic tumors, at intermediate (3.0 mm) and large (6.0 mm) motion magnitudes. Motion compensation substantially improved median vascular DICE score (from 0.30 to 0.59 for large motion), image SSIM (from 0.77 to 0.93 for large motion), and vessel sharpness (0.189 mm−1 to 0.233 mm−1 for large motion) in simulated cases. Motion compensation also demonstrated increased vessel sharpness (0.188 mm−1 before to 0.205 mm−1 after) and reconstructed vessel length (median increased from 37.37 to 41.00 mm) on a clinical interventional CBCT. The proposed anatomy-aware motion compensation framework presented a promising approach for improving the utility of CBCT for intra-procedural vascular imaging, facilitating selective embolization procedures.

A multiview deep learning-based prediction pipeline augmented with confident learning can improve performance in determining knee arthroplasty candidates.

Preoperative prudent patient selection plays a crucial role in knee osteoarthritis management but faces challenges in appropriate referrals such as total knee arthroplasty (TKA), unicompartmental knee arthroplasty (UKA)and nonoperative intervention. Deep learning (DL) techniques can build prediction models for treatment decision-making. The aim is to develop and evaluate a knee arthroplasty prediction pipeline using three-view X-rays to determine the suitable candidates for TKA, UKAor are not arthroplasty candidates. A study was conducted using three-view (anterior-posterior, lateraland patellar) X-rays and surgical data of patients undergoing TKA, UKAor nonarthroplasty interventions from sites A and B. Data from site A were used to derive and validate models. Data from site B were used as external test set. A DL pipeline combining YOLOv3 and ResNet-18 with confident learning (CL) was developed. Multiview Convolutional Neural Network, EfficientNet-b4, ResNet-101and the proposed model without CLwere also trained and tested. The models were evaluated using metrics such as area under the receiver operating characteristic curve (AUC), accuracy, precision, specificity, sensitivityand F1 score. The data set comprised a total of 1779 knees. Of which 1645 knees were from site A as a derivation set and an internal validation cohort. The external validation cohort consisted of 134 knees. The internal validation cohort demonstrated superior performance for the proposed model augmented with CL, achieving an AUC of 0.94 and an accuracy of 85.9%. External validation further confirmed the model's generalisation, with an AUC of 0.93 and an accuracy of 82.1%. Comparative analysis with other neural network models showed the proposed model's superiority. The proposed DL pipeline, integrating YOLOv3, ResNet-18and CL, provides accurate predictions for knee arthroplasty candidates based on three-view X-rays. This prediction model could be useful in performing decision making for the type of arthroplasty procedure in an automated fashion. Level III, diagnostic study.

A multi-view convolutional neural network method combining attention mechanism for diagnosing autism spectrum disorder

Autism Spectrum Disorder (ASD) is a neurodevelopmental condition whose current psychiatric diagnostic process is subjective and behavior-based. In contrast, functional magnetic resonance imaging (fMRI) can objectively measure brain activity and is useful for identifying brain disorders. However, the ASD diagnostic models employed to date have not reached satisfactory levels of accuracy. This study proposes the use of MAACNN, a method that utilizes multi-view convolutional neural networks (CNNs) in conjunction with attention mechanisms for identifying ASD in multi-scale fMRI. The proposed algorithm effectively combines unsupervised and supervised learning. In the initial stage, we employ stacked denoising autoencoders, an unsupervised learning method for feature extraction, which provides different nodes to adapt to multi-scale data. In the subsequent stage, we perform supervised learning by employing multi-view CNNs for classification and obtain the final results. Finally, multi-scale data fusion is achieved by using the attention fusion mechanism. The ABIDE dataset is used to evaluate the model we proposed., and the experimental results show that MAACNN achieves superior performance with 75.12% accuracy and 0.79 AUC on ABIDE-I, and 72.88% accuracy and 0.76 AUC on ABIDE-II. The proposed method significantly contributes to the clinical diagnosis of ASD.

White matter hyperintensities associate with pathological stages of neurodegenerative disease.

AbstractBackgroundWhite matter hyper‐intensities (WMH) are observed on FLAIR MRI, increase with age and are more prominent in neurodegenerative diseases such as in Alzheimer’s disease (AD) and Parkinson’s disease (PD). The aim of this study was to assess the association between WMH and neuropathological staging of amyloid‐beta, neurofibrillary tangles (NFT) and α‐synuclein (α‐syn).MethodIn‐situ 3T‐MRI 3DT1‐weighted and 3D‐FLAIR data were collected for 77 clinically defined and pathologically‐confirmed brain donors; 31 AD, 21 PD and PD dementia (PDD), and 25 controls. WMH were segmented on FLAIR using an in‐house developed multiview convolutional neural network, followed by manual checking, and volume was obtained with FSL. Fifteen brain regions were dissected at autopsy, immunostained and evaluated for neuropathological diagnosis, including Thal amyloid phase, CAA type, and Braak stages for NFT and α‐syn. Group differences were assessed with linear models (corrected for age, gender, post‐mortem delay), and associations with Spearman and Pearson partial correlations.ResultCompared to controls, WMH load was higher in AD (p<0.001), specifically amnestic AD (p = 0.003) rather than non‐amnestic AD (p = 0.053), and higher in PD (p = 0.016), specifically non‐demented PD (p = 0.015) rather than PDD (p = 1.0). No difference in gender was observed (p = 0.38). Without the influence of pathology (in controls), WMH was associated with age (r = 0.49,p = 0.016).In the whole cohort, WMH was associated with Fazekas score (r = 0.67; p<0.001), normalized brain volume (NBV; r = ‐0.31,p = 0.007), gray matter volume (NGMV; r = ‐0.36,p = 0.002), Thal phase (r = 0.24,p0.034), Braak NFT stage (r = 0.33,p = 0.004), and Braak α‐syn stage (r = 0.27, p0.018).Across controls and AD, WMH associated with NBV (r = ‐0.39,p = 0.004), NGMV (r = ‐0.42,p = 0.002), left and right hippocampal volume (r = ‐0.36,p = 0.008 and r = ‐0.32,p = 0.022), Braak NFT (r = 0.41,p<0.001), Thal phase (r = 0.41,p = 0.002), and CAA (r = 0.34,p = 0.01). Amnestic and non‐amnestic AD showed similar results, except for CAA, which was associated with WMH in non‐amnestic AD only (r = 0.33,p = 0.04).Across controls and PD(D), WMH associated with Braak NFT stage (r = 0.39,p = 0.008) and Braak α‐syn stage (r = 0.60,p<0.001), but not with MRI outcome measures. In this respect PD and PDD showed different results; in PD WMH associated with NGMV (r = ‐0.37,p = 0.031), in PDD with left and right hippocampal volume (r = ‐0.44,p = 0.014 and r = ‐0.44,p = 0.015).ConclusionWMH associate with pathological stages of AD and PD(D), and contributes to MRI atrophy.

DTV-CNN: Neural network based on depth and thickness views for efficient 3D shape classification

Fast and effective algorithms for deep learning on 3D shapes are keys to innovate mechanical and electronic engineering design workflow. In this paper, an efficient 3D shape to 2D images projection algorithm and a shallow 2.5D convolutional neural network architecture is proposed. A smaller convolutional neural network (CNN) model is achieved by information enrichment at the preprocessing stage, i.e. 3D geometry is compressed into 2D “thickness view” and “depth view”. Fusing the depth view and thickness view (DTV) from the same projection view into a dual-channel grayscale image, can improve information locality for geometry and topology feature extraction. This approach bridges the gap between mature image deep learning technologies to the applications of 3D shape. Enhanced by several essential scalar geometry properties and only 3 projection views, a mixed CNN and multiple linear parameter (MLP) neural network model achives a validation accuracy of 92 % for ModelNet10 mesh-based dataset, while the training time is one order of magnitude less than the original multi-view CNN approach. This study also creates new 3D shape datasets from 2 open source CAD projects. Higher validation accuracy is obtained for realistic CAD datasets, i.e. 97 % for FreeCAD's mechanical part library and 95 % for KiCAD electronic part library. The training cost reduces to tens of minutes on a laptop CPU, given the smaller input data size and shallow neural network design. It is expected that this approach can be adapted for other machine learning scenarios involved in CAD geometry.

Automated diagnosis of anterior cruciate ligament via a weighted multi-view network.

Objective: To build a three-dimensional (3D) deep learning-based computer-aided diagnosis (CAD) system and investigate its applicability for automatic detection of anterior cruciate ligament (ACL) of the knee joint in magnetic resonance imaging (MRI). Methods: In this study, we develop a 3D weighted multi-view convolutional neural network by fusing different views of MRI to detect ACL. The network is evaluated on two MRI datasets, the in-house MRI-ACL dataset and the publicly available MRNet-v1.0 dataset. In the MRI-ACL dataset, the retrospective study collects 100 cases, and four views per patient are included. There are 50 ACL patients and 50 normal patients, respectively. The MRNet-v1.0 dataset contains 1,250 cases with three views, of which 208 are ACL patients, and the rest are normal or other abnormal patients. Results: The area under the receiver operating characteristic curve (AUC) of the ACL diagnosis system is 97.00% and 92.86% at the optimal threshold for the MRI-ACL dataset and the MRNet-v1.0 dataset, respectively, indicating a high overall diagnostic accuracy. In comparison, the best AUC of the single-view diagnosis methods are 96.00% (MRI-ACL dataset) and 91.78% (MRNet-v1.0 dataset), and our method improves by about 1.00% and 1.08%. Furthermore, our method also improves by about 1.00% (MRI-ACL dataset) and 0.28% (MRNet-v1.0 dataset) compared with the multi-view network (i.e., MRNet). Conclusion: The presented 3D weighted multi-view network achieves superior AUC in diagnosing ACL, not only in the in-house MRI-ACL dataset but also in the publicly available MRNet-v1.0 dataset, which demonstrates its clinical applicability for the automatic detection of ACL.

Multi-view expressive graph neural networks for 3D CAD model classification

The creation of effective content-based retrieval systems for the 3D models of engineering components created by Mechanical Computer Aided Design (MCAD) systems has been a subject of academic investigation since the 1990 s. Recently some of the most promising results have been reported by researchers using Deep Neural Nets (DNN) to classify industrial parts represented by collections of images generated from different viewpoints. Known as Multi-View Convolutional Neural Network (MVCNN) these systems have extended the architectures developed for 2D images analysis to handle 3D data by using a series of pictures rendered from different viewpoints. In 2016 Monti et al. used Graph Neural Networks (GNN) to classify the superpixel images for the first time and reported results which suggested that the approach could produce good classification accuracy (an observation confirmed by the application of GNNs to 2D image datasets of common objects such as MNIST and Cifar). To investigate the potential for GNNs to reason about spatial adjacency relationships this paper reports, for the first time, the application of GNNs to classifications of 3D MCAD models of mechanical components. Viewing GNN as a convolution operator, parallel GNN can be applied to multiple views of a 3D shape in the same way as CNN is structured in a MVCNN. After outlining the architecture implemented to support MVGNNs the impact of various hyperparameters on the expressive power are explored. When optimised these hyperparameters (located in both intra-layer and inter-layer structures) combined with the multi-view architecture produced a classification accuracy superior to previous methods. The results also suggest that GNNs have the potential to produce fast, accurate classification systems for 3D MCAD data using significantly smaller datasets than those used for transfer learning in MVCNNs.

MORE: simultaneous multi-view 3D object recognition and pose estimation

Simultaneous object recognition and pose estimation are two key functionalities for robots to safely interact with humans as well as environments. Although both object recognition and pose estimation use visual input, most state of the art tackles them as two separate problems since the former needs a view-invariant representation, while object pose estimation necessitates a view-dependent description. Nowadays, multi-view convolutional neural network (MVCNN) approaches show state-of-the-art classification performance. Although MVCNN object recognition has been widely explored, there has been very little research on multi-view object pose estimation methods, and even less on addressing these two problems simultaneously. The pose of virtual cameras in MVCNN methods is often pre-defined in advance, leading to bound the application of such approaches. In this paper, we propose an approach capable of handling object recognition and pose estimation simultaneously. In particular, we develop a deep object-agnostic entropy estimation model, capable of predicting the best viewpoints of a given 3D object. The obtained views of the object are then fed to the network to simultaneously predict the pose and category label of the target object. Experimental results showed that the views obtained from such positions are descriptive enough to achieve a good accuracy score. Furthermore, we designed a real-life serve drink scenario to demonstrate how well the proposed approach worked in real robot tasks. Code is available online at: https://github.com/SubhadityaMukherjee/more_mvcnn.

DeePSC: A Deep Learning Model for Automated Diagnosis of Primary Sclerosing Cholangitis at Two-dimensional MR Cholangiopancreatography.

To develop, train, and validate a multiview deep convolutional neural network (DeePSC) for the automated diagnosis of primary sclerosing cholangitis (PSC) on two-dimensional MR cholangiopancreatography (MRCP) images. This retrospective study included two-dimensional MRCP datasets of 342 patients (45 years ± 14 [SD]; 207 male patients) with confirmed diagnosis of PSC and 264 controls (51 years ± 16; 150 male patients). MRCP images were separated into 3-T (n = 361) and 1.5-T (n = 398) datasets, of which 39 samples each were randomly chosen as unseen test sets. Additionally, 37 MRCP images obtained with a 3-T MRI scanner from a different manufacturer were included for external testing. A multiview convolutional neural network was developed, specialized in simultaneously processing the seven images taken at different rotational angles per MRCP examination. The final model, DeePSC, derived its classification per patient from the instance expressing the highest confidence in an ensemble of 20 individually trained multiview convolutional neural networks. Predictive performance on both test sets was compared with that of four licensed radiologists using the Welch t test. DeePSC achieved an accuracy of 80.5% ± 1.3 (sensitivity, 80.0% ± 1.9; specificity, 81.1% ± 2.7) on the 3-T and 82.6% ± 3.0 (sensitivity, 83.6% ± 1.8; specificity, 80.0% ± 8.9) on the 1.5-T test set and scored even higher on the external test set (accuracy, 92.4% ± 1.1; sensitivity, 100.0% ± 0.0; specificity, 83.5% ± 2.4). DeePSC outperformed radiologists in average prediction accuracy by 5.5 (P = .34, 3 T) and 10.1 (P = .13, 1.5 T) percentage points. Automated classification of PSC-compatible findings based on two-dimensional MRCP was achievable and demonstrated high accuracy on internal and external test sets.Keywords: Neural Networks, Deep Learning, Liver Disease, MRI, Primary Sclerosing Cholangitis, MR Cholangiopancreatography Supplemental material is available for this article. © RSNA, 2023.

MULTI-VIEW CNN FOR TOTAL LUNG VOLUME INFERENCE ON CARDIAC COMPUTED TOMOGRAPHY.

Total lung volume (TLV) at full inspiration is a parameter of significant interest in pulmonary physiology but requires computed tomography (CT) scanning of the full axial extent of the lung. There is a growing interest to infer TLV from cardiac CT scans, which are much more widely available in epidemiologic studies. In this study, we present an original approach to train a multi-view convolutional neural network (CNN) model to infer TLV from cardiac CT scans, which visualize about 2/3rd of the lung volume. Supervised learning is used, exploiting paired full-lung and cardiac CT scans in the Multi-Ethnic Study of Atherosclerosis (MESA). Our results show that our network outperforms existing regression models for TLV estimation, and achieves accuracy and reproducibility comparable to the scan-rescan reproducibility of TLV on full-lung CT.

Deep Learning for Drawing Numbering in Engineering Drawing Management: A Case Study for Refrigerated Compartment Product

Engineering drawing numbering (DN) is one of the most essential procedures for seamless platform integration towards intelligent manufacturing. In spite of this, it is difficult to handle the numbering work in an appropriate and effective manner. This is due to the unpredictability of the names of the manufactured parts and the ineffable relationship between the number and the shape of the parts. This paper proposes a method for numbering items based on historical numbering records based on deep learning. First, name-number (NN) duplexes are generated by retrieving the records. [Formula: see text]-means[Formula: see text] is then used to cluster these NN duplexes. Second, it involves looking up the names of the newly designed items using KNN in order to generate an initial numbering system. Third, a modified multi-view convolutional neural network (MVCNN) is utilized for numbering in situations where the same name is different from the previous number (SNDN). Finally, the most recent sequence numbers are appended to complete the numbering. When the system based on the proposed scheme for authentic engineering application is implemented on a refrigerated compartment, the correctness obtained is over 95%, and the efficiency is increased by 5–6 times.

IAACS: Image aesthetic assessment through color composition and space formation

BackgroundDetermining how an image is visually appealing is a complicated and subjective task. This motivates the use of a machine-learning model to evaluate image aesthetics automatically by matching the aesthetics of the general public. Although deep learning methods have successfully learned good visual features from images, correctly assessing the aesthetic quality of an image remains a challenge for deep learning. MethodsTo address this, we propose a novel multiview convolutional neural network to assess image aesthetics assessment through color composition and space formation (IAACS). Specifically, from different views of an image––including its key color components and their contributions, the image space formation, and the image itself––our network extracts the corresponding features through our proposed feature extraction module (FET) and the ImageNet weight-based classification model. ResultBy fusing the extracted features, our network produces an accurate prediction score distribution for image aesthetics. The experimental results show that we have achieved superior performance.

Tool-Wear-Estimation System in Milling Using Multi-View CNN Based on Reflected Infrared Images.

A novel method for tool wear estimation in milling using infrared (IR) laser vision and a deep-learning algorithm is proposed and demonstrated. The measurement device employs an IR line laser to irradiate the tool focal point at angles of -7.5°, 0.0°, and +7.5° to the vertical plane, and three cameras are placed at 45° intervals around the tool to collect the reflected IR light at different locations. For the processing materials and methods, a dry processing method was applied to a 100 mm × 100 mm × 40 mm SDK-11 workpiece through end milling and downward cutting using a TH308 insert. This device uses the diffused light reflected off the surface of a rotating tool roughened by flank wear, and a polarization filter is considered. As the measured tool wear images exhibit a low dynamic range of exposure, high dynamic range (HDR) images are obtained using an exposure fusion method. Finally, tool wear is estimated from the images using a multi-view convolutional neural network. As shown in the results of the estimated tool wear, a mean absolute error (MAE) of prediction error calculated was to be 9.5~35.21 μm. The proposed method can improve machining efficiency by reducing the downtime for tool wear measurement and by increasing tool life utilization.

DTiGNN: Learning drug-target embedding from a heterogeneous biological network based on a two-level attention-based graph neural network.

In vitro experiment-based drug-target interaction (DTI) exploration demands more human, financial and data resources. In silico approaches have been recommended for predicting DTIs to reduce time and cost. During the drug development process, one can analyze the therapeutic effect of the drug for a particular disease by identifying how the drug binds to the target for treating that disease. Hence, DTI plays a major role in drug discovery. Many computational methods have been developed for DTI prediction. However, the existing methods have limitations in terms of capturing the interactions via multiple semantics between drug and target nodes in a heterogeneous biological network (HBN). In this paper, we propose a DTiGNN framework for identifying unknown drug-target pairs. The DTiGNN first calculates the similarity between the drug and target from multiple perspectives. Then, the features of drugs and targets from each perspective are learned separately by using a novel method termed an information entropy-based random walk. Next, all of the learned features from different perspectives are integrated into a single drug and target similarity network by using a multi-view convolutional neural network. Using the integrated similarity networks, drug interactions, drug-disease associations, protein interactions and protein-disease association, the HBN is constructed. Next, a novel embedding algorithm called a meta-graph guided graph neural network is used to learn the embedding of drugs and targets. Then, a convolutional neural network is employed to infer new DTIs after balancing the sample using oversampling techniques. The DTiGNN is applied to various datasets, and the result shows better performance in terms of the area under receiver operating characteristic curve (AUC) and area under precision-recall curve (AUPR), with scores of 0.98 and 0.99, respectively. There are 23,739 newly predicted DTI pairs in total.

Spatial Pattern Learning: Dip Structure Constraint Multi-View Convolutional Neural Network for Pre-Stacked Seismic Inversion

Spatial Pattern Learning: Dip Structure Constraint Multi-View Convolutional Neural Network for Pre-Stacked Seismic Inversion

A multi-view convolutional neural network based on cross-connection and residual-wider

A multi-view convolutional neural network based on cross-connection and residual-wider

Lung Cancer Nodules Detection via an Adaptive Boosting Algorithm Based on Self-Normalized Multiview Convolutional Neural Network.

Lung cancer is the deadliest cancer killing almost 1.8 million people in 2020. The new cases are expanding alarmingly. Early lung cancer manifests itself in the form of nodules in the lungs. One of the most widely used techniques for both lung cancer early and noninvasive diagnosis is computed tomography (CT). However, the intensive workload of radiologists to read a large number of scans for nodules detection gives rise to issues like false detection and missed detection. To overcome these issues, we proposed an innovative strategy titled adaptive boosting self-normalized multiview convolution neural network (AdaBoost-SNMV-CNN) for lung cancer nodules detection across CT scans. In AdaBoost-SNMV-CNN, MV-CNN function as a baseline learner while the scaled exponential linear unit (SELU) activation function normalizes the layers by considering their neighbors' information and a special drop-out technique (α-dropout). The proposed method was trained and tested using the widely Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI) and Early Lung Cancer Action Program (ELCAP) datasets. AdaBoost-SNMV-CNN achieved an accuracy of 92%, sensitivity of 93%, and specificity of 92% for lung nodules detection on the LIDC-IDRI dataset. Meanwhile, on the ELCAP dataset, the accuracy for detecting lung nodules was 99%, sensitivity 100%, and specificity 98%. AdaBoost-SNMV-CNN outperformed the majority of the model in accuracy, sensitivity, and specificity. The multiviews confer the model's good generalization and learning ability for diverse features of lung nodules, the model architecture is simple, and has a minimal computational time of around 102 minutes. We believe that AdaBoost-SNMV-CNN has good accuracy for the detection of lung nodules and anticipate its potential application in the noninvasive clinical diagnosis of lung cancer. This model can be of good assistance to the radiologist and will be of interest to researchers involved in the designing and development of advanced systems for the detection of lung nodules to accomplish the goal of noninvasive diagnosis of lung cancer.

Multi‐view convolutional neural network‐based target classification in high‐resolution automotive radar sensor

In this study, a target classification method based on point cloud data in a high-resolution radar sensor is proposed. By using multiple antenna elements arranged in horizontal and vertical directions, pedestrians, cyclists and vehicles can be expressed as point cloud data in the three-dimensional (3D) space. To perform target classification using the spatial characteristics (i.e. length, height and width) of the target, the 3D point cloud data is orthogonally projected onto the xy, yz and zx planes, respectively, and three types of images are generated. Then, a multi-view convolutional neural network (CNN)-based target classifier using those three images as inputs is designed. To this end, a method for synthesising the detection results of three directions in series or in parallel is proposed. The proposed classifier can learn the spatial characteristics of the target by using the detection results of multiple viewpoints. Compared to the CNN-based classifier that uses only the detection result of a single plane as input, the proposed method shows 4.5%p higher classification accuracy in terms of the target with the lowest classification accuracy. In addition, the proposed multi-view CNN structure shows improved classification performance and shorter training time compared to the well-known deep learning methods for image classification.