Automatic detection of breast lesions in automated 3D breast ultrasound with cross-organ transfer learning

Background Deep convolutional neural networks have garnered considerable attention in numerous machine learning applications,particularly in visual recognition tasks such as image and video analyses.There is a growing interest in applying this technology to diverse applications in medical image analysis.Automated three dimensional Breast Ultrasound is a vital tool for detecting breast cancer,and computer-assisted diagnosis software,developed based on deep learning,can effectively assist radiologists in diagnosis.However,the network model is prone to overfitting during training,owing to challenges such as insufficient training data.This study attempts to solve the problem caused by small datasets and improve model detection performance.Methods We propose a breast cancer detection framework based on deep learning(a transfer learning method based on cross-organ cancer detection)and a contrastive learning method based on breast imaging reporting and data systems(BI-RADS).Results When using cross organ transfer learning and BIRADS based contrastive learning,the average sensitivity of the model increased by a maximum of 16.05%.Conclusion Our experiments have demonstrated that the parameters and experiences of cross-organ cancer detection can be mutually referenced,and contrastive learning method based on BI-RADS can improve the detection performance of the model.

Review of Artificial Intelligence for Oil and Gas Exploration: Convolutional Neural Network Approaches and the U-Net 3D Model

Deep learning, especially through convolutional neural networks (CNN) such as the U-Net 3D model, has revolutionized fault identification from seismic data, representing a significant leap over traditional methods. Our review traces the evolution of CNN, emphasizing the adaptation and capabilities of the U-Net 3D model in automating seismic fault delineation with unprecedented accuracy. We find: 1) The transition from basic neural networks to sophisticated CNN has enabled remarkable advancements in image recognition, which are directly applicable to analyzing seismic data. The U-Net 3D model, with its innovative architecture, exemplifies this progress by providing a method for detailed and accurate fault detection with reduced manual interpretation bias. 2) The U-Net 3D model has demonstrated its superiority over traditional fault identification methods in several key areas: it has enhanced interpretation accuracy, increased operational efficiency, and reduced the subjectivity of manual methods. 3) Despite these achievements, challenges such as the need for effective data preprocessing, acquisition of high-quality annotated datasets, and achieving model generalization across different geological conditions remain. Future research should therefore focus on developing more complex network architectures and innovative training strategies to refine fault identification performance further. Our findings confirm the transformative potential of deep learning, particularly CNN like the U-Net 3D model, in geosciences, advocating for its broader integration to revolutionize geological exploration and seismic analysis.

A Survey on Deep Learning-Based 2D Human Pose Estimation Models

In this article,a comprehensive survey of deep learning-based(DLbased)human pose estimation(HPE)that can help researchers in the domain of computer vision is presented.HPE is among the fastest-growing research domains of computer vision and is used in solving several problems for human endeavours.After the detailed introduction,three different human body modes followed by the main stages of HPE and two pipelines of twodimensional(2D)HPE are presented.The details of the four components of HPE are also presented.The keypoints output format of two popular 2D HPE datasets and the most cited DL-based HPE articles from the year of breakthrough are both shown in tabular form.This study intends to highlight the limitations of published reviews and surveys respecting presenting a systematic review of the current DL-based solution to the 2D HPE model.Furthermore,a detailed and meaningful survey that will guide new and existing researchers on DL-based 2D HPE models is achieved.Finally,some future research directions in the field of HPE,such as limited data on disabled persons and multi-training DL-based models,are revealed to encourage researchers and promote the growth of HPE research.

Real-Time Multi-Feature Approximation Model-Based Efficient Brain Tumor Classification Using Deep Learning Convolution Neural Network Model

The deep learning models are identified as having a significant impact on various problems.The same can be adapted to the problem of brain tumor classification.However,several deep learning models are presented earlier,but they need better classification accuracy.An efficient Multi-Feature Approximation Based Convolution Neural Network(CNN)model(MFACNN)is proposed to handle this issue.The method reads the input 3D Magnetic Resonance Imaging(MRI)images and applies Gabor filters at multiple levels.The noise-removed image has been equalized for its quality by using histogram equalization.Further,the features like white mass,grey mass,texture,and shape are extracted from the images.Extracted features are trained with deep learning Convolution Neural Network(CNN).The network has been designed with a single convolution layer towards dimensionality reduction.The texture features obtained from the brain image have been transformed into a multi-dimensional feature matrix,which has been transformed into a single-dimensional feature vector at the convolution layer.The neurons of the intermediate layer are designed to measure White Mass Texture Support(WMTS),GrayMass Texture Support(GMTS),WhiteMass Covariance Support(WMCS),GrayMass Covariance Support(GMCS),and Class Texture Adhesive Support(CTAS).In the test phase,the neurons at the intermediate layer compute the support as mentioned above values towards various classes of images.Based on that,the method adds a Multi-Variate Feature Similarity Measure(MVFSM).Based on the importance ofMVFSM,the process finds the class of brain image given and produces an efficient result.

Intelligent 3D garment system of the human body based on deep spiking neural network

Background Intelligent garments,a burgeoning class of wearable devices,have extensive applications in domains such as sports training and medical rehabilitation.Nonetheless,existing research in the smart wearables domain predominantly emphasizes sensor functionality and quantity,often skipping crucial aspects related to user experience and interaction.Methods To address this gap,this study introduces a novel real-time 3D interactive system based on intelligent garments.The system utilizes lightweight sensor modules to collect human motion data and introduces a dual-stream fusion network based on pulsed neural units to classify and recognize human movements,thereby achieving real-time interaction between users and sensors.Additionally,the system incorporates 3D human visualization functionality,which visualizes sensor data and recognizes human actions as 3D models in real time,providing accurate and comprehensive visual feedback to help users better understand and analyze the details and features of human motion.This system has significant potential for applications in motion detection,medical monitoring,virtual reality,and other fields.The accurate classification of human actions contributes to the development of personalized training plans and injury prevention strategies.Conclusions This study has substantial implications in the domains of intelligent garments,human motion monitoring,and digital twin visualization.The advancement of this system is expected to propel the progress of wearable technology and foster a deeper comprehension of human motion.

Integrating deep learning and logging data analytics for lithofacies classification and 3D modeling of tight sandstone reservoirs

The lithofacies classification is essential for oil and gas reservoir exploration and development.The traditional method of lithofacies classification is based on"core calibration logging"and the experience of geologists.This approach has strong subjectivity,low efficiency,and high uncertainty.This uncertainty may be one of the key factors affecting the results of 3 D modeling of tight sandstone reservoirs.In recent years,deep learning,which is a cutting-edge artificial intelligence technology,has attracted attention from various fields.However,the study of deep-learning techniques in the field of lithofacies classification has not been sufficient.Therefore,this paper proposes a novel hybrid deep-learning model based on the efficient data feature-extraction ability of convolutional neural networks(CNN)and the excellent ability to describe time-dependent features of long short-term memory networks(LSTM)to conduct lithological facies-classification experiments.The results of a series of experiments show that the hybrid CNN-LSTM model had an average accuracy of 87.3%and the best classification effect compared to the CNN,LSTM or the three commonly used machine learning models(Support vector machine,random forest,and gradient boosting decision tree).In addition,the borderline synthetic minority oversampling technique(BSMOTE)is introduced to address the class-imbalance issue of raw data.The results show that processed data balance can significantly improve the accuracy of lithofacies classification.Beside that,based on the fine lithofacies constraints,the sequential indicator simulation method is used to establish a three-dimensional lithofacies model,which completes the fine description of the spatial distribution of tight sandstone reservoirs in the study area.According to this comprehensive analysis,the proposed CNN-LSTM model,which eliminates class imbalance,can be effectively applied to lithofacies classification,and is expected to improve the reality of the geological model for the tight sandstone reservoirs.

A Deep Learning Approach to Mesh Segmentation

In the shape analysis community,decomposing a 3D shape intomeaningful parts has become a topic of interest.3D model segmentation is largely used in tasks such as shape deformation,shape partial matching,skeleton extraction,shape correspondence,shape annotation and texture mapping.Numerous approaches have attempted to provide better segmentation solutions;however,the majority of the previous techniques used handcrafted features,which are usually focused on a particular attribute of 3Dobjects and so are difficult to generalize.In this paper,we propose a three-stage approach for using Multi-view recurrent neural network to automatically segment a 3D shape into visually meaningful sub-meshes.The first stage involves normalizing and scaling a 3D model to fit within the unit sphere and rendering the object into different views.Contrasting viewpoints,on the other hand,might not have been associated,and a 3D region could correlate into totally distinct outcomes depending on the viewpoint.To address this,we ran each view through(shared weights)CNN and Bolster block in order to create a probability boundary map.The Bolster block simulates the area relationships between different views,which helps to improve and refine the data.In stage two,the feature maps generated in the previous step are correlated using a Recurrent Neural network to obtain compatible fine detail responses for each view.Finally,a layer that is fully connected is used to return coherent edges,which are then back project to 3D objects to produce the final segmentation.Experiments on the Princeton Segmentation Benchmark dataset show that our proposed method is effective for mesh segmentation tasks.

Risk pre-assessment method for regional drilling engineering based on deep learning and multi-source data

Accurately predicting downhole risk before drilling in new exploration areas is one of the difficulties.Using intelligent algorithms to explore the complex relationship between multi-source data and downhole risk is a hot research topic and frontier in this field.However,due to the small number and uneven distribution of drilled wells in new exploration areas and the lack of sample data related to risk,the training model has insufficient generalization ability,and thus the prediction is not effective.In this paper,a drilling risk profile(depth domain)rich in geological and engineering information is constructed by introducing a quantitative evaluation method for drilling risk of drilled wells,which can provide sufficient risk sample data for model training and thus solve the small sample problem.For the problem of uneven distribution of drilling wells in new exploration areas,the concept of virtual wells and their deployment methods were proposed.Besides,two methods for calculating rock mechanical parameters of virtual wells were proposed,and the accuracy and applicability of the two methods are analyzed.The LSTM deep learning model was optimized to tap the quantitative relationship between drilling risk profiles and multi-source data(e.g.,seismic,logging,and rock mechanical parameters).The model was validated to have an average relative error of 9.19%.The quantitative prediction of the drilling risk profile of the virtual well was achieved using the trained LSTM model and the calculation of the relevant parameters of the virtual well.Finally,based on the sequential Gaussian simulation method and the risk distribution of drilled and virtual wells,a regional 3D drilling risk model was constructed.The analysis of real cases shows that the addition of virtual wells can significantly improve the identification of regional drilling risks and the prediction accuracy of pre-drill drilling risks in unexplored areas can be improved by up to 21%compared with the 3D risk model constructed based on drilled wells only.

A 3D attention U-Net network and its application in geological model parameterization

To solve the problems of convolutional neural network–principal component analysis(CNN-PCA)in fine description and generalization of complex reservoir geological features,a 3D attention U-Net network was proposed not using a trained C3D video motion analysis model to extract the style of a 3D model,and applied to complement the details of geologic model lost in the dimension reduction of PCA method in this study.The 3D attention U-Net network was applied to a complex river channel sandstone reservoir to test its effects.The results show that compared with CNN-PCA method,the 3D attention U-Net network could better complement the details of geological model lost in the PCA dimension reduction,better reflect the fluid flow features in the original geologic model,and improve history matching results.

A Systematic Literature Review of Deep Learning Algorithms for Segmentation of the COVID-19 Infection

Coronavirus has infected more than 753 million people,ranging in severity from one person to another,where more than six million infected people died worldwide.Computer-aided diagnostic(CAD)with artificial intelligence(AI)showed outstanding performance in effectively diagnosing this virus in real-time.Computed tomography is a complementary diagnostic tool to clarify the damage of COVID-19 in the lungs even before symptoms appear in patients.This paper conducts a systematic literature review of deep learning methods for classifying the segmentation of COVID-19 infection in the lungs.We used the methodology of systematic reviews and meta-analyses(PRISMA)flow method.This research aims to systematically analyze the supervised deep learning methods,open resource datasets,data augmentation methods,and loss functions used for various segment shapes of COVID-19 infection from computerized tomography(CT)chest images.We have selected 56 primary studies relevant to the topic of the paper.We have compared different aspects of the algorithms used to segment infected areas in the CT images.Limitations to deep learning in the segmentation of infected areas still need to be developed to predict smaller regions of infection at the beginning of their appearance.

Deep learning enhanced NIR-Ⅱ volumetric imaging of whole mice vasculature

Fluorescence imaging through the second near-infrared window(NIR-Ⅱ,1000–1700 nm) allows in-depth imaging.However, current imaging systems use wide-field illumination and can only provide low-contrast 2D information, without depth resolution. Here, we systematically apply a light-sheet illumination, a time-gated detection, and a deep-learning algorithm to yield high-contrast high-resolution volumetric images. To achieve a large Fo V(field of view) and minimize the scattering effect, we generate a light sheet as thin as 100.5 μm with a Rayleigh length of 8 mm to yield an axial resolution of 220 μm. To further suppress the background, we time-gate to only detect long lifetime luminescence achieving a high contrast of up to 0.45 Icontrast. To enhance the resolution, we develop an algorithm based on profile protrusions detection and a deep neural network and distinguish vasculature from a low-contrast area of 0.07 Icontrast to resolve the 100μm small vessels. The system can rapidly scan a volume of view of 75 × 55 × 20 mm3and collect 750 images within 6mins. By adding a scattering-based modality to acquire the 3D surface profile of the mice skin, we reveal the whole volumetric vasculature network with clear depth resolution within more than 1 mm from the skin. High-contrast large-scale 3D animal imaging helps us expand a new dimension in NIR-Ⅱ imaging.

Recognition of mortar pumpability via computer vision and deep learning

The mortar pumpability is essential in the construction industry,which requires much labor to estimate manually and always causes material waste.This paper proposes an effective method by combining a 3-dimensional convolutional neural network(3D CNN)with a 2-dimensional convolutional long short-term memory network(ConvLSTM2D)to automatically classify the mortar pumpability.Experiment results show that the proposed model has an accuracy rate of 100%with a fast convergence speed,based on the dataset organized by collecting the corresponding mortar image sequences.This work demonstrates the feasibility of using computer vision and deep learning for mortar pumpability classification.

Application of Opening and Closing Morphology in Deep Learning-Based Brain Image Registration

In order to improve the registration accuracy of brain magnetic resonance images(MRI),some deep learning registration methods use segmentation images for training model.How-ever,the segmentation values are constant for each label,which leads to the gradient variation con-centrating on the boundary.Thus,the dense deformation field(DDF)is gathered on the boundary and there even appears folding phenomenon.In order to fully leverage the label information,the morphological opening and closing information maps are introduced to enlarge the non-zero gradi-ent regions and improve the accuracy of DDF estimation.The opening information maps supervise the registration model to focus on smaller,narrow brain regions.The closing information maps supervise the registration model to pay more attention to the complex boundary region.Then,opening and closing morphology networks(OC_Net)are designed to automatically generate open-ing and closing information maps to realize the end-to-end training process.Finally,a new registra-tion architecture,VM_(seg+oc),is proposed by combining OC_Net and VoxelMorph.Experimental results show that the registration accuracy of VM_(seg+oc) is significantly improved on LPBA40 and OASIS1 datasets.Especially,VM_(seg+oc) can well improve registration accuracy in smaller brain regions and narrow regions.

3D Reconstruction for Motion Blurred Images Using Deep Learning-Based Intelligent Systems

The 3D reconstruction using deep learning-based intelligent systems can provide great help for measuring an individual’s height and shape quickly and accurately through 2D motion-blurred images.Generally,during the acquisition of images in real-time,motion blur,caused by camera shaking or human motion,appears.Deep learning-based intelligent control applied in vision can help us solve the problem.To this end,we propose a 3D reconstruction method for motion-blurred images using deep learning.First,we develop a BF-WGAN algorithm that combines the bilateral filtering(BF)denoising theory with a Wasserstein generative adversarial network(WGAN)to remove motion blur.The bilateral filter denoising algorithm is used to remove the noise and to retain the details of the blurred image.Then,the blurred image and the corresponding sharp image are input into the WGAN.This algorithm distinguishes the motion-blurred image from the corresponding sharp image according to the WGAN loss and perceptual loss functions.Next,we use the deblurred images generated by the BFWGAN algorithm for 3D reconstruction.We propose a threshold optimization random sample consensus(TO-RANSAC)algorithm that can remove the wrong relationship between two views in the 3D reconstructed model relatively accurately.Compared with the traditional RANSAC algorithm,the TO-RANSAC algorithm can adjust the threshold adaptively,which improves the accuracy of the 3D reconstruction results.The experimental results show that our BF-WGAN algorithm has a better deblurring effect and higher efficiency than do other representative algorithms.In addition,the TO-RANSAC algorithm yields a calculation accuracy considerably higher than that of the traditional RANSAC algorithm.

Deep-Learning-Empowered 3D Reconstruction for Dehazed Images in IoT-Enhanced Smart Cities

With increasingly more smart cameras deployed in infrastructure and commercial buildings,3D reconstruction can quickly obtain cities’information and improve the efficiency of government services.Images collected in outdoor hazy environments are prone to color distortion and low contrast;thus,the desired visual effect cannot be achieved and the difficulty of target detection is increased.Artificial intelligence(AI)solutions provide great help for dehazy images,which can automatically identify patterns or monitor the environment.Therefore,we propose a 3D reconstruction method of dehazed images for smart cities based on deep learning.First,we propose a fine transmission image deep convolutional regression network(FT-DCRN)dehazing algorithm that uses fine transmission image and atmospheric light value to compute dehazed image.The DCRN is used to obtain the coarse transmission image,which can not only expand the receptive field of the network but also retain the features to maintain the nonlinearity of the overall network.The fine transmission image is obtained by refining the coarse transmission image using a guided filter.The atmospheric light value is estimated according to the position and brightness of the pixels in the original hazy image.Second,we use the dehazed images generated by the FT-DCRN dehazing algorithm for 3D reconstruction.An advanced relaxed iterative fine matching based on the structure from motion(ARI-SFM)algorithm is proposed.The ARISFM algorithm,which obtains the fine matching corner pairs and reduces the number of iterations,establishes an accurate one-to-one matching corner relationship.The experimental results show that our FT-DCRN dehazing algorithm improves the accuracy compared to other representative algorithms.In addition,the ARI-SFM algorithm guarantees the precision and improves the efficiency.

Improved Lightweight Deep Learning Algorithm in 3D Reconstruction

The three-dimensional(3D)reconstruction technology based on structured light has been widely used in the field of industrial measurement due to its many advantages.Aiming at the problems of high mismatch rate and poor real-time performance caused by factors such as system jitter and noise,a lightweight stripe image feature extraction algorithm based on You Only Look Once v4(YOLOv4)network is proposed.First,Mobilenetv3 is used as the backbone network to effectively extract features,and then the Mish activation function and Complete Intersection over Union(CIoU)loss function are used to calculate the improved target frame regression loss,which effectively improves the accuracy and real-time performance of feature detection.Simulation experiment results show that the model size after the improved algorithm is only 52 MB,the mean average accuracy(mAP)of fringe image data reconstruction reaches 82.11%,and the 3D point cloud restoration rate reaches 90.1%.Compared with the existing model,it has obvious advantages and can satisfy the accuracy and real-time requirements of reconstruction tasks in resource-constrained equipment.

Applying Deep Learning Models to Mouse Behavior Recognition

In many animal-related studies, a high-performance animal behavior recognition system can help researchers reduce or get rid of the limitation of human assessments and make the experiments easier to reproduce. Recently, although deep learning models are holding state-of-the-art performances in human action recognition tasks, these models are not well-studied in applying to animal behavior recognition tasks. One reason is the lack of extensive datasets which are required to train these deep models for good performances. In this research, we investigated two current state-of-the-art deep learning models in human action recognition tasks, the I3D model and the R(2 + 1)D model, in solving a mouse behavior recognition task. We compared their performances with other models from previous researches and the results showed that the deep learning models that pre-trained using human action datasets then fine-tuned using the mouse behavior dataset can outperform other models from previous researches. It also shows promises of applying these deep learning models to other animal behavior recognition tasks without any significant modification in the models’ architecture, all we need to do is collecting proper datasets for the tasks and fine-tuning the pre-trained models using the collected data.

Deep Reinforcement Learning Based Unmanned Aerial Vehicle (UAV) Control Using 3D Hand Gestures

The evident change in the design of the autopilot system produced massive help for the aviation industry and it required frequent upgrades.Reinforcement learning delivers appropriate outcomes when considering a continuous environment where the controlling Unmanned Aerial Vehicle(UAV)required maximum accuracy.In this paper,we designed a hybrid framework,which is based on Reinforcement Learning and Deep Learning where the traditional electronic flight controller is replaced by using 3D hand gestures.The algorithm is designed to take the input from 3D hand gestures and integrate with the Deep Deterministic Policy Gradient(DDPG)to receive the best reward and take actions according to 3D hand gestures input.The UAV consist of a Jetson Nano embedded testbed,Global Positioning System(GPS)sensor module,and Intel depth camera.The collision avoidance system based on the polar mask segmentation technique detects the obstacles and decides the best path according to the designed reward function.The analysis of the results has been observed providing best accuracy and computational time using novel design framework when compared with traditional Proportional Integral Derivatives(PID)flight controller.There are six reward functions estimated for 2500,5000,7500,and 10000 episodes of training,which have been normalized between 0 to−4000.The best observation has been captured on 2500 episodes where the rewards are calculated for maximum value.The achieved training accuracy of polar mask segmentation for collision avoidance is 86.36%.

3D Instance Segmentation Using Deep Learning on RGB-D Indoor Data

3D object recognition is a challenging task for intelligent and robot systems in industrial and home indoor environments.It is critical for such systems to recognize and segment the 3D object instances that they encounter on a frequent basis.The computer vision,graphics,and machine learning fields have all given it a lot of attention.Traditionally,3D segmentation was done with hand-crafted features and designed approaches that didn’t achieve acceptable performance and couldn’t be generalized to large-scale data.Deep learning approaches have lately become the preferred method for 3D segmentation challenges by their great success in 2D computer vision.However,the task of instance segmentation is currently less explored.In this paper,we propose a novel approach for efficient 3D instance segmentation using red green blue and depth(RGB-D)data based on deep learning.The 2D region based convolutional neural networks(Mask R-CNN)deep learning model with point based rending module is adapted to integrate with depth information to recognize and segment 3D instances of objects.In order to generate 3D point cloud coordinates(x,y,z),segmented 2D pixels(u,v)of recognized object regions in the RGB image are merged into(u,v)points of the depth image.Moreover,we conducted an experiment and analysis to compare our proposed method from various points of view and distances.The experimentation shows the proposed 3D object recognition and instance segmentation are sufficiently beneficial to support object handling in robotic and intelligent systems.

Deep Learning-Based 3D Instance and Semantic Segmentation: A Review

The process of segmenting point cloud data into several homogeneous areas with points in the same region having the same attributes is known as 3D segmentation.Segmentation is challenging with point cloud data due to substantial redundancy,fluctuating sample density and lack of apparent organization.The research area has a wide range of robotics applications,including intelligent vehicles,autonomous mapping and navigation.A number of researchers have introduced various methodologies and algorithms.Deep learning has been successfully used to a spectrum of 2D vision domains as a prevailing A.I.methods.However,due to the specific problems of processing point clouds with deep neural networks,deep learning on point clouds is still in its initial stages.This study examines many strategies that have been presented to 3D instance and semantic segmentation and gives a complete assessment of current developments in deep learning-based 3D segmentation.In these approaches’benefits,draw backs,and design mechanisms are studied and addressed.This study evaluates the impact of various segmentation algorithms on competitiveness on various publicly accessible datasets,as well as the most often used pipelines,their advantages and limits,insightful findings and intriguing future research directions.