Deep Convolutional Neural Network Algorithm Research Articles

Embedded artificial intelligence system using deep learning and raspberrypi for the detection and classification of melanoma

<div lang="EN-US"><span>Melanoma is a kind of skin cancer that originates in melanocytes responsible for producing melanin, it can be a severe and potentially deadly form of cancer because it can metastasize to other regions of the body if not detected and treated early. To facilitate this process, Recently, various computer-assisted low-cost, reliable, and accurate diagnostic systems have been proposed based on artificial intelligence (AI) algorithms, particularly deep learning techniques. This work proposed an innovative and intelligent system that combines the internet of things (IoT) with a Raspberry Pi connected to a camera and a deep learning model based on the deep convolutional neural network (CNN) algorithm for real-time detection and classification of melanoma cancer lesions. The key stages of our model before serializing to the Raspberry Pi: Firstly, the preprocessing part contains data cleaning, data transformation (normalization), and data augmentation to reduce overfitting when training. Then, the deep CNN algorithm is used to extract the features part. Finally, the classification part with applied Sigmoid Activation Function. The experimental results indicate the efficiency of our proposed classification system as we achieved an accuracy rate of 92%, a precision of 91%, a sensitivity of 91%, and an area under the curve- receiver operating characteristics (AUC-ROC) of 0.9133.</span></div>

Prediction of Diabetic Retinopathy using Deep Learning with Preprocessing

INTRODUCTION: When Diabetic Retinopathy (DR) is not identified promptly; it frequently results in sight impairment. To properly diagnose and treat DR, preprocessing of picture methods and precise prediction models are essential. With the help of numerous well-liked filters and a Deep CNN (Convolutional Neural Network) model, the comprehensive method for DR image preparation and prognosis presented in this research is described. Using the filters that focus boundaries and contours in the ocular pictures is the first step in the initial processing stage. This procedure tries to find anomalies linked to DR. By the usage of filters, the excellence of pictures can be developed and minimize disturbances, preserving critical information. The Deep CNN algorithm has been trained to generate forecasts on the cleaned retinal pictures following the phase of preprocessing. The filters efficiently eliminate interference without sacrificing vital data. Convolutional type layers, pooling type layers, and fully associated layers are used in the CNN framework, which was created especially for image categorization tasks, to acquire data and understand the relationships associated with DR.
 OBJECTIVES: Using image preprocessing techniques such as the Sobel, Wiener, Gaussian, and non-local mean filters is a promising approach for DR analysis. Then, predicting using a CNN completes the approach. These preprocessing filters enhance the images and prepare them for further examination. The pre-processed images are fed into a CNN model. The model extracts significant information from the images by identifying complex patterns. DR or classification may be predicted by the CNN model through training on a labeled dataset.
 METHODS: The Method Preprocessing is employed for enhancing the clarity and difference of retina fundus picture by removing noise and fluctuation. The preprocessing stage is utilized for the normalization of the pictures and non-uniform brightness adjustment in addition to contrast augmentation and noise mitigation to remove noises and improve the rate of precision of the subsequent processing stages.
 RESULTS: To improve image quality and reduce noise, preprocessing techniques including Sobel, Wiener, Gaussian, and non-local mean filters are frequently employed in image processing jobs. For a particular task, the non-local mean filter produces superior results; for enhanced performance, it may be advantageous to combine it with a CNN. Before supplying the processed images to the CNN for prediction, the non-local mean filter can assist reduce noise and improve image details.
 CONCLUSION: A promising method for DR analysis entails the use of image preprocessing methods such as the Sobel, Wiener, Gaussian, and non-local mean filters, followed by prediction using a CNN. These preprocessing filters improve the photos and get them ready for analysis. After being pre-processed, the photos are sent into a CNN model, which uses its capacity to discover intricate patterns to draw out important elements from the images. The CNN model may predict DR or classification by training it on a labeled dataset. The development of computer-aided diagnosis systems for DR is facilitated by the integration of CNN prediction with image preprocessing filters. This strategy may increase the effectiveness of healthcare workers, boost patient outcomes, and lessen the burden of DR.

Study on the Application of Improved Deep Convolutional Neural Network Algorithm in Broken Information Recovery

Abstract This study on the fusion of deep convolutional neural network (CNN) and extended short-term memory network (LSTM) aims to improve the efficiency and accuracy of broken information recovery. The challenges faced by traditional information recovery techniques are addressed through improved algorithms. The research methodology includes constructing CNN models to automatically extract features and combining LSTM networks to process complex time-series data. We conducted a detailed experimental evaluation of the CNN-LSTM fusion algorithm, including recovery of different types of corrupted data, and compared it with other algorithms. The results show that the CNN-LSTM fusion algorithm has the highest structural similarity (0.9545) and the most minor normalized mean square error (0.0016) for recovering broken video information, outperforming the methods using CNN or LSTM alone. The fusion algorithm dramatically reduces computation time and resource consumption for processing complex datasets. The combination of CNN and LSTM significantly improves the performance of broken information recovery, especially in processing video and audio data, and provides new ideas for future information processing techniques.

Moving scene object tracking method based on deep convolutional neural network

The effect of target tracking is not ideal when facing various complex tracking scenarios such as non-rigid deformation of target, frequent occlusion, clutter of target background and interference of similar objects. In this paper, the feature based on deep convolutional neural network is used for target tracking in moving scenes, and a sliding window target segmentation method is proposed to study the impact of data normalization and data set expansion on the final result. In order to select more distinguishing features, principal component analysis is used to process the features of Deep Convolution Neural Network (DCNN), and the features of different network layers of DCNN are compared. The feature coding algorithm is studied, and the extracted DCNN features are encoded by Fisher Vectors algorithm, and compared with the locality-constrained linear encoding technique. Experiments show that the feature based on deep convolutional neural network in this paper can obtain higher accuracy than the traditional feature fusion method. According to the result analysis, the tracking accuracy of deep convolutional neural network algorithm is improved under the condition of illumination variation. In the case of local occlusion, the tracking accuracy is also improved.

Au-Ag OHCs-based SERS sensor coupled with deep learning CNN algorithm to quantify thiram and pymetrozine in tea.

Pesticide residue detection in food has become increasingly important. Herein, surface-enhanced Raman scattering (SERS) coupled with an intelligent algorithm was developed for the rapid and sensitive detection of pesticide residues in tea. By employing octahedral Cu2O templates, Au-Ag octahedral hollow cages (Au-Ag OHCs) were developed, which improved the surface plasma effect via rough edges and hollow inner structure, amplifying the Raman signals of pesticide molecules. Afterward, convolutional neural network (CNN), partial least squares (PLS), and extreme learning machine (ELM) algorithms were applied for the quantitative prediction of thiram and pymetrozine. CNN algorithms performed optimally for thiram and pymetrozine, with correlation values of 0.995 and 0.977 and detection limits (LOD) of 0.286 and 29ppb, respectively. Accordingly, no significant difference (Pgreater than0.05) was observed between the developed approach and HPLC in detecting tea samples. Hence, the proposed Au-Ag OHCs-based SERS technique could be utilized for quantifying thiram and pymetrozine in tea.

Deep Learning-based Assessment of Facial Asymmetry Using U-Net Deep Convolutional Neural Network Algorithm.

This study aimed to evaluate the diagnostic performance of a deep convolutional neural network (DCNN)-based computer-assisted diagnosis (CAD) system to detect facial asymmetry on posteroanterior (PA) cephalograms and compare the results of the DCNN with those made by the orthodontist. PA cephalograms of 1020 patients with orthodontics were used to train the DCNN-based CAD systems for autoassessment of facial asymmetry, the degree of menton deviation, and the coordinates of its regarding landmarks. Twenty-five PA cephalograms were used to test the performance of the DCNN in analyzing facial asymmetry. The diagnostic performance of the DCNN-based CAD system was assessed using independent t -tests and Bland-Altman plots. Comparison between the DCNN-based CAD system and conventional analysis confirmed no significant differences. Bland-Altman plots showed good agreement for all the measurements. The DCNN-based CAD system might offer a clinically acceptable diagnostic evaluation of facial asymmetry on PA cephalograms.

Clinically Oriented CBCT Periapical Lesion Evaluation via 3D CNN Algorithm

Apical periodontitis (AP) is one of the most prevalent disorders in dentistry. However, it can be underdiagnosed in asymptomatic patients. In addition, the perioperative evaluation of 3-dimensional (3D) lesion volume is of great clinical relevance, but the required slice-by-slice manual delineation method is time- and labor-intensive. Here, for quickly and accurately detecting and segmenting periapical lesions (PALs) associated with AP on cone beam computed tomography (CBCT) images, we proposed and geographically validated a novel 3D deep convolutional neural network algorithm, named PAL-Net. On the internal 5-fold cross-validation set, our PAL-Net achieved an area under the receiver operating characteristic curve (AUC) of 0.98. The algorithm also improved the diagnostic performance of dentists with varying levels of experience, as evidenced by their enhanced average AUC values (junior dentists: 0.89–0.94; senior dentists: 0.91–0.93), and significantly reduced the diagnostic time (junior dentists: 69.3 min faster; senior dentists: 32.4 min faster). Moreover, our PAL-Net achieved an average Dice similarity coefficient over 0.87 (0.85–0.88), which is superior or comparable to that of other existing state-of-the-art PAL segmentation algorithms. Furthermore, we validated the generalizability of the PAL-Net system using multiple external data sets from Central, East, and North China, showing that our PAL-Net has strong robustness. Our PAL-Net can help improve the diagnostic performance and speed of dentists working from CBCT images, provide clinically relevant volume information to dentists, and can potentially be applied in dental clinics, especially without expert-level dentists or radiologists.

Semantic Segmentation of Portuguese Agri-Forestry Using High-Resolution Orthophotos

The Montado ecosystem is an important agri-forestry system in Portugal, occupying about 8% of the total area of the country. However, this biodiverse ecosystem is threatened due to factors such as shrub encroachment. In this context, the development of tools for characterizing and monitoring Montado areas is crucial for their conservation. In this study, we developed a deep convolutional neural network algorithm based on the U-net architecture to identify regions with trees, shrubs, grass, bare soil, or other areas in Montado areas using high-resolution RGB and near-infrared orthophotos (with a spatial resolution of 25 cm) from seven experimental sites in the Alentejo region of Portugal (six used for training/validation and one for testing). To optimize the model’s performance, we performed hyperparameter tuning, which included adjusting the number of filters, dropout rate, and batch size. The best model achieved an overall classification performance of 0.88 and a mean intersection of the union of 0.81 on the test set, indicating high accuracy and reliability of the model in identifying and delineating land cover classes in the Montado ecosystem. The developed model is a powerful tool for identifying the status of the Montado ecosystem regarding shrub encroachment and facilitating better future management.

Convolutional-neural-network-based radiographs evaluation assisting in early diagnosis of the periodontal bone loss via periapical radiograph

Background/PurposeThe preciseness of detecting periodontal bone loss is examiners dependent, and this leads to low reliability. The need for automated assistance systems on dental radiographic images has been increased. To the best of our knowledge, no studies have quantitatively and automatically staged periodontitis using dental periapical radiographs. The purpose of this study was to evaluate periodontal bone loss and periodontitis stage on dental periapical radiographs using deep convolutional neural networks (CNNs). Materials and methods336 periapical radiographic images (teeth: 390) between January 2017 and December 2019 were collected and de-identified. All periapical radiographic image datasets were divided into training dataset (n = 82, teeth: 123) and test dataset (n = 336, teeth: 390). For creating an optimal deep CNN algorithm model, the training datasets were directly used for the segmentation and individual tooth detection. To evaluate the diagnostic power, we calculated the degree of alveolar bone loss deviation between our proposed method and ground truth, the Pearson correlation coefficients (PCC), and the diagnostic accuracy of the proposed method in the test datasets. ResultsThe periodontal bone loss degree deviation between our proposed method and the ground truth drawn by the three periodontists was 6.5 %. In addition, the overall PCC value of our proposed system and the periodontists’ diagnoses was 0.828 (P < 0.01). The total diagnostic accuracy of our proposed method was 72.8 %. The diagnostic accuracy was highest for stage III (97.0 %). ConclusionThis tool helps with diagnosis and prevents omission, and this may be especially helpful for inexperienced younger doctors and doctors in underdeveloped countries. It could also dramatically reduce the workload of clinicians and timely access to periodontist care for people requiring advanced periodontal treatment.

THU676 Real-time Assessment Of The Beneficial Role Of Computer-Aided Diagnosis In The Diagnosis Of Thyroid Nodules On Ultrasound

Abstract Disclosure: Y. Kim: None. S. Shin: None. E. Lee: None. D. Kim: None. J. Kwak: None. Objective: Computer-aided Diagnosis (CAD) has been applied in various medical fields. SERA (SEveRance Artificial intelligence program) is a deep convolutional neural network algorithm. We conducted this study to evaluate whether CAD-SERA helps diagnose the malignancy when the ultrasound was used by physicians with low levels of experience and to compare with the experienced radiologist. Methods: In real-time, an inexperienced physician and a radiologist simultaneously assessed the same thyroid nodules to determine malignancy and performed CAD. The diagnosis was changed if it was necessary to correct it by referring to the CAD results, and this was compared with the surgical pathology or biopsy pathology. Results: We evaluated 191 thyroid nodules in 179 patients. Area Under the Receiver Operating Characteristics (AUROC) was analyzed with the diagnoses with/without CAD assistance and pathology results. The AUROC of the inexperienced physician was 0.716, and when assisted by CAD that increased to 0.740 (Accuracy 73.82 -&amp;gt; 76.44%). In the case of the radiologist, AUROC without CAD assist was 0.868 and 0.880 with the assist of CAD (Accuracy 84.29 -&amp;gt; 85.86%). Conclusion: CAD improves diagnostic performance in the diagnosis of thyroid nodules in various experienced physicians in ultrasound. In particular, the extent of this is greater in physicians with less experience in ultrasound. Presentation: Thursday, June 15, 2023

Deep Convolutional Neural Network Algorithm for Prediction of the Mechanical Properties of Friction Stir Welded Copper Joints from its Microstructures

Convolutional Neural Network (CNN) is a special type of Artificial Neural Network which takes input in the form of an image. Like Artificial Neural Network they consist of weights that are estimated during training, neurons (activation functions), and an objective (loss function). CNN is finding various applications in image recognition, semantic segmentation, object detection, and localization. The present work deals with the prediction of the welding efficiency of the Friction Stir Welded joints on the basis of microstructure images by carrying out training on 3000 microstructure images and further testing on 300 microstructure images. The obtained results showed an accuracy of 80 % on the validation dataset.

Two-Stage Channel Estimation for mmWave Massive MIMO Systems Based on ResNet-UNet

For millimeter wave massive multiple-input multiple-output systems, the transceiver usually adopts a hybrid precoding structure to reduce complexity and cost, which poses great challenges to the acquisition of channel state information, especially in the case of low signal-to-noise ratio regime. In this article, residual network (ResNet) is employed to address this problem. Firstly, we design a two-stage channel estimation structure to improve the accuracy of channel estimation. Then, we take ResNet as the basic network and integrate UNet structure to build ResNet-UNet model to solve the model degradation problem. Moreover, we use noise2noise algorithm to train the neural network in order to implement the channel estimation in the case that a clean pilot cannot be obtained. Numerical results show that compared with the traditional channel estimation algorithms and deep convolutional neural network algorithm, the proposed approach has higher accuracy and robustness, and achieves performance close to the denoising algorithm using clean targets that is very difficult to be implemented in practical situations.

Generalization Analysis of CNNs for Classification on Spheres.

Deep learning based on deep convolutional neural networks (CNNs) is extremely efficient in solving classification problems in speech recognition, computer vision, and many other fields. But there is no enough theoretical understanding about this topic, especially the generalization ability of the induced CNN algorithms. In this article, we develop some generalization analysis of a deep CNN algorithm for binary classification with data on spheres. An essential property of the classification problem is the lack of continuity or high smoothness of the target function associated with a convex loss function such as the hinge loss. This motivates us to consider the approximation of functions in the Lp space with 1≤ p ≤ ∞. We provide rates of Lp -approximation when the approximated function lies in a Sobolev space and then present generalization bounds and learning rates for the excess misclassification error of the deep CNN classification algorithm. Our novel analysis is based on efficient cubature formulae on spheres and other tools from spherical analysis and approximation theory.

A novel alpine land cover classification strategy based on a deep convolutional neural network and multi-source remote sensing data in Google Earth Engine

ABSTRACT Alpine land cover (ALC) is facing many challenges with climatic change, biodiversity reduction and other cascading ecosystem damage triggered by natural and anthropogenic interference. Although several global land cover products and thematic maps are already available, their mapping accuracy of alpine and montane regions remains unsatisfactory due to the data acquisition, methodology, and workflow design constraints. Therefore, in this paper, a deep convolutional neural network (DCNN) in Google Earth Engine (GEE) was developed to map the ALC types of the Yarlung Zangbo river basin (YZRB) in the Tibetan plateau using multi-source remote sensing data. The DCNN algorithm was offline trained using automatically generating samples and online deployed in the GEE for a large-scale ALC mapping. Moreover, a set of fine land cover classification system (containing 14 ALC types) was also established in accordance with the natural situation of the YZRB. The overall accuracy and kappa were 86.24% and 0.8156, which were higher than traditional classification algorithms. The spatial distribution of ALC types was analyzed in different gradient zones, and a clear altitudinal characteristic was noticed. The terrain of the YZRB from upper-stream to down-stream with an elevation dramatically decreases, and corresponding to vertical zonal changes from glacier and permanent snow/ice, barren gravel land, alpine desert steppe, alpine steppe, alpine meadow, shrubs, to tree cover. The product can provide valuable land cover information to support alpine ecosystem conservation.

Analysis of Line and Tube Detection Performance of a Chest X-ray Deep Learning Model to Evaluate Hidden Stratification.

This retrospective case-control study evaluated the diagnostic performance of a commercially available chest radiography deep convolutional neural network (DCNN) in identifying the presence and position of central venous catheters, enteric tubes, and endotracheal tubes, in addition to a subgroup analysis of different types of lines/tubes. A held-out test dataset of 2568 studies was sourced from community radiology clinics and hospitals in Australia and the USA, and was then ground-truth labelled for the presence, position, and type of line or tube from the consensus of a thoracic specialist radiologist and an intensive care clinician. DCNN model performance for identifying and assessing the positioning of central venous catheters, enteric tubes, and endotracheal tubes over the entire dataset, as well as within each subgroup, was evaluated. The area under the receiver operating characteristic curve (AUC) was assessed. The DCNN algorithm displayed high performance in detecting the presence of lines and tubes in the test dataset with AUCs > 0.99, and good position classification performance over a subpopulation of ground truth positive cases with AUCs of 0.86-0.91. The subgroup analysis showed that model performance was robust across the various subtypes of lines or tubes, although position classification performance of peripherally inserted central catheters was relatively lower. Our findings indicated that the DCNN algorithm performed well in the detection and position classification of lines and tubes, supporting its use as an assistant for clinicians. Further work is required to evaluate performance in rarer scenarios, as well as in less common subgroups.

Emotion classification for musical data using deep learning techniques

This research is done based on the identification and thorough analyzing musical data that is extracted by the various method. This extracted information can be utilized in the deep learning algorithm to identify the emotion, based on the hidden features of the dataset. Deep learning-based convolutional neural network (CNN) and long short-term memory-gated recurrent unit (LSTM-GRU) models were developed to predict the information from the musical information. The musical dataset is extracted using the fast Fourier transform (FFT) models. The three deep learning models were developed in this work the first model was based on the information of extracted information such as zero-crossing rate, and spectral roll-off. Another model was developed on the information of Mel frequencybased cepstral coefficient (MFCC) features, the deep and wide CNN algorithm with LSTM-GRU bidirectional model was developed. The third model was developed on the extracted information from Mel-spectrographs and untied these graphs based on two-dimensional (2D) data information to the 2D CNN model alongside LSTM models. Proposed model performance on the information from Mel-spectrographs is compared on the F1 score, precision, and classification report of the models. Which shows better accuracy with improved F1 and recall values as compared with existing approaches.

Retracted: Optimization of Machine Online Translation System Based on Deep Convolution Neural Network Algorithm.

[This retracts the article DOI: 10.1155/2021/7388825.].

Deep convolutional neural network algorithm for the automatic segmentation of oral potentially malignant disorders and oral cancers.

This study aimed to develop an algorithm to automatically segment the oral potentially malignant diseases (OPMDs) and oral cancers (OCs) of all oral subsites with various deep convolutional neural network applications. A total of 510 intraoral images of OPMDs and OCs were collected over 3 years (2006-2009). All images were confirmed both with patient records and histopathological reports. Following the labeling of the lesions the dataset was arbitrarily split, using random sampling in Python as the study dataset, validation dataset, and test dataset. Pixels were classified as the OPMDs and OCs with the OPMD/OC label and the rest as the background. U-Net architecture was used and the model with the best validation loss was chosen for the testing among the trained 500 epochs. Dice similarity coefficient (DSC) score was noted. The intra-observer ICC was found to be 0.994 while the inter-observer reliability was 0.989. The calculated DSC and validation accuracy across all clinical images were 0.697 and 0.805, respectively. Our algorithm did not maintain an excellent DSC due to multiple reasons for the detection of both OC and OPMDs in oral cavity sites. A better standardization for both 2D and 3D imaging (such as patient positioning) and a bigger dataset are required to improve the quality of such studies. This is the first study which aimed to segment OPMDs and OCs in all subsites of oral cavity which is crucial not only for the early diagnosis but also for higher survival rates.

Face Recognition Technique using YOLO V5 Algorithm

In today’s date real world application like human-machine interaction, security surveillance face recognition has made its great importance. For face recognition the steps to be followed are data collection, preprocessing, Feature Extraction, Training Evaluation and finally testing. One of the best Algorithms used for face recognition is Viola-Jones Algorithm. Viola Jones Algorithm is highly accepted because of its fast processing time and high detection rate. The other detection Algorithms which can be used are HOG Algorithm (Histogram Oriented Gradient), Deep Learning CNN (Convolution Neural Network) Algorithm, Haar cascade Algorithm and MTCNN Algorithm. In this Paper we will discuss about all this Algorithms and compare the detection rate of facial points among various methods for the datasets. YOLO V5 algorithm is another algorithm which can be used for face recognition technique. Face recognition can be achieved by combining the YOLO V5 algorithm with additional technique such as deep face recognition models like face net, which can recognize and compare facial features to identify individuals.YOLOV5 can identify facial features such as eyes, mouth, and nose, making it useful for a variety of face recognition applications.

Evaluation of ensemble strategy on the development of multiple view ankle fracture detection algorithm.

To identify the feasibility and efficiency of deep convolutional neural networks (DCNNs) in the detection of ankle fractures and to explore ensemble strategies that applied multiple projections of radiographs.Ankle radiographs (AXRs) are the primary tool used to diagnose ankle fractures. Applying DCNN algorithms on AXRs can potentially improve the diagnostic accuracy and efficiency of detecting ankle fractures. A DCNN was trained using a trauma image registry, including 3102 AXRs. We separately trained the DCNN on anteroposterior (AP) and lateral (Lat) AXRs. Different ensemble methods, such as "sum-up," "severance-OR," and "severance-Both," were evaluated to incorporate the results of the model using different projections of view. The AP/Lat model's individual sensitivity, specificity, positive-predictive value, accuracy, and F1 score were 79%/84%, 90%/86%, 88%/86%, 83%/85%, and 0.816/0.850, respectively. Furthermore, the area under the receiver operating characteristic curve (AUROC) of the AP/Lat model was 0.890/0.894 (95% CI: 0.826-0.954/0.831-0.953). The sum-up method generated balanced results by applying both models and obtained an AUROC of 0.917 (95% CI: 0.863-0.972) with 87% accuracy. The severance-OR method resulted in a better sensitivity of 90%, and the severance-Both method obtained a high specificity of 94%. Ankle fracture in the AXR could be identified by the trained DCNN algorithm. The selection of ensemble methods can depend on the clinical situation which might help clinicians detect ankle fractures efficiently without interrupting the current clinical pathway. This study demonstrated different ensemble strategies of AI algorithms on multiple view AXRs to optimize the performance in various clinical needs.