Learning-based Convolutional Neural Network Research Articles

A Novel Method to Inspect 3D Ball Joint Socket Products Using 2D Convolutional Neural Network with Spatial and Channel Attention.

Product defect inspections are extremely important for industrial manufacturing processes. It is necessary to develop a special inspection system for each industrial product due to their complexity and diversity. Even though high-precision 3D cameras are usually used to acquire data to inspect 3D objects, it is hard to use them in real-time defect inspection systems due to their high price and long processing time. To address these problems, we propose a product inspection system that uses five 2D cameras to capture all inspection parts of the product and a deep learning-based 2D convolutional neural network (CNN) with spatial and channel attention (SCA) mechanisms to efficiently inspect 3D ball joint socket products. Channel attention (CA) in our model detects the most relevant feature maps while spatial attention (SA) finds the most important regions in the extracted feature map of the target. To build the final SCA feature vector, we concatenated the learned feature vectors of CA and SA because they complement each other. Thus, our proposed CNN with SCA provides high inspection accuracy as well as it having the potential to detect small defects of the product. Our proposed model achieved 98% classification accuracy in the experiments and proved its efficiency on product inspection in real-time.

APPLICATION OF PRE-TRAINED REAL-WORLD SUPER RESOLUTION MODELS TO OPTICAL SATELLITE IMAGE

Abstract. The single image super-resolution (SISR) technique refers to improving the resolution over the original image. In recent years, we use deep learning-based convolutional neural networks to improve the spatial resolution of images more reasonably. To train such deep learning models, we use training samples consisting of the original HR images and LR images obtained by bicubic downsampling. However, this method of training data using downsampling has a negative impact when applying the trained model to real images. That is because the downsampling function that occurs in the real image is unknown, and the hypothetically created LR image does not represent the resolution degradation that can realistically occur. Therefore, SISR methods that use realistic degradation called real-world super-resolution (RWSR) have been proposed. In this paper, we investigate how such RWSR methods using realistic degradation affect the SISR performance of satellite images. The results of applying the trained model to optical satellite images show that the RWSR method is not the most effective way to handle optical satellite images when compared to the deep learning method without modeling the degradation. In particular, we showed that the effect of RWSR with not only upsampling but also noise and blur removal is significant in the visibility of optical satellite images. Moreover, pre-trained RWSR models can be an aid in visually deciphering ground objects.

Cyberbullying detection using deep transfer learning

Social networking platforms like Facebook, Twitter, and others have numerous advantages, but they have many dark sides also. One of the issues on these social platforms is cyberbullying. The impact of cyberbullying is immeasurable on the life of victims as it’s very subjective to how the person would tackle this. The message may be a bully for victims, but it may be normal for others. The ambiguities in cyberbullying messages create a big challenge to find the bully content. Some research has been reported to address this issue with textual posts. However, image-based cyberbullying detection is received less attention. This research aims to develop a model that helps to prevent image-based cyberbullying issues on social platforms. The deep learning-based convolutional neural network is initially used for model development. Later, transfer learning models are utilized in this research. The experimental outcomes of various settings of the hyper-parameters confirmed that the transfer learning-based model is the better choice for this problem. The proposed model achieved a satisfactory accuracy of 89% for the best case, indicating that the system detects most cyberbullying posts.

Detecting the presence of taurodont teeth on panoramic radiographs using a deep learning-based convolutional neural network algorithm.

Artificial intelligence (AI) techniques like convolutional neural network (CNN) are a promising breakthrough that can help clinicians analyze medical imaging, diagnose taurodontism, and make therapeutic decisions. The purpose of the study is to develop and evaluate the function of CNN-based AI model to diagnose teeth with taurodontism in panoramic radiography. 434 anonymized, mixed-sized panoramic radiography images over the age of 13years were used to develop automatic taurodont tooth segmentation models using a Pytorch implemented U-Net model. Datasets were split into train, validation, and test groups of both normal and masked images. The data augmentation method was applied to images of trainings and validation groups with vertical flip images, horizontal flip images, and both flip images. The Confusion Matrix was used to determine the model performance. Among the 43 test group images with 126 labels, there were 109 true positives, 29 false positives, and 17 false negatives. The sensitivity, precision, and F1-score values of taurodont tooth segmentation were 0.8650, 0.7898, and 0.8257, respectively. CNN's ability to identify taurodontism produced almost identical results to the labeled training data, and the CNN system achieved close to the expert level results in its ability to detect the taurodontism of teeth.

Traffic Sign Detection and Recognition Based on Convolutional Neural Network

As autonomous vehicles are developing and maturing the technology to implement the domestic autonomous vehicles. The critical technological problem for self-driving vehicles is traffic sign detection and recognition. A traffic sign recognition system is essential for an intelligent transportation system. The digital image processing techniques for object recognition and extraction of features from visual objects is a huge process and include many conversions and pre-processing steps. A deep learning-based convolutional neural network (CNN) model is one of the suitable approach for traffic sign detection and recognition. This model has overcome significant shortcomings of traditional visual object detection approaches. This paper proposed a traffic sign identification and detection system. The proposed design and strategy are implemented using the Tensorflow framework in google colab environment. The experiment is applied on the publicly available traffic sign data sets. The defined deep convolution neural network based model experimental results achieved 94.52% and 80.85% precision and recall respectively. Improving the seep of recognition and identifying appropriate features of traffic sign objects are addressed using deep learning-based encoders and transformers.

Effect of Kernel Size in Deep Learning-Based Convolutional Neural Networks for Image Classification

In recent years deep learning models are very popular for image classification. Convolution Neural Networks (CNNs) are commonly used for image classification and based on the architecture of these models there are various transfer learning models which are pre-trained on the ImageNet dataset. The accuracy of these models depends upon the various parameters, such as the number of layers, kernel size, image size, etc. In the current study, we analyze the effect of kernel size on the CNNs model for image classification. We consider the CGIAR wheat rust disease image dataset for experimentation. After performing various experiments, it is found that using a small kernel size leads to the reduction of several parameters of the model and also has a significant effect on the accuracy of the model.

Automated detection of posterior restorations in permanent teeth using artificial intelligence on intraoral photographs

ObjectivesIntraoral photographs might be considered the machine-readable equivalent of a clinical-based visual examination and can potentially be used to detect and categorize dental restorations. The first objective of this study was to develop a deep learning-based convolutional neural network (CNN) for automated detection and categorization of posterior composite, cement, amalgam, gold and ceramic restorations on clinical photographs. Second, this study aimed to determine the diagnostic accuracy for the developed CNN (test method) compared to that of an expert evaluation (reference standard). MethodsThe whole image set of 1761 images (483 of unrestored teeth, 570 of composite restorations, 213 of cements, 278 of amalgam restorations, 125 of gold restorations and 92 of ceramic restorations) was divided into a training set (N = 1407, 401, 447, 66, 231, 93, and 169, respectively) and a test set (N = 354, 82, 123, 26, 47, 32, and 44). The expert diagnoses served as a reference standard for cyclic training and repeated evaluation of the CNN (ResNeXt-101–32 × 8d), which was trained by using image augmentation and transfer learning. Statistical analysis included the calculation of contingency tables, areas under the receiver operating characteristic curve and saliency maps. ResultsAfter training was complete, the CNN was able to categorize restorations correctly with the following diagnostic accuracy values: 94.9% for unrestored teeth, 92.9% for composites, 98.3% for cements, 99.2% for amalgam restorations, 99.4% for gold restorations and 97.8% for ceramic restorations. ConclusionsIt was possible to categorize different types of posterior restorations on intraoral photographs automatically with a good diagnostic accuracy. Clinical significanceDental diagnostics might be supported by artificial intelligence-based algorithms in the future. However, further improvements are needed to increase accuracy and practicability.

Leukocytes identification using augmentation and transfer learning based convolution neural network

Most haematological diseases can be diagnosed using the morphological analysis of the microscopic blood image. The basic routine of the morphological analysis can be performed using the microscopic device which requires the skills and experiences of the haematologists. An inexperienced haematologist can lead to critical human errors. Therefore, this paper aims to propose an automated classification system used to classify different types of leukocytes based on the convolution neural network (CNN) algorithm. CNN has achieved robust performance in various fields especially in medical applications. A dataset of microscopic blood cells images of the conforming tags (basophil, eosinophil, erythroblast, lymphocyte, monocyte, neutrophil, and platelet) was used to train and test the proposed algorithm. The augmentation and deep transfer approaches were used to improve and enhance the performance of the CNN algorithm. The overall accuracy of the proposed classifier was 98% with Visual Geometry Group-19 (VGG-19). The obtained accuracy was higher than the state-of-art algorithms. To conclude that using the augmentation and deep transfer approaches with VGG-19 can obtain better classification results.

Empirical Analysis of Machine Learning Algorithms for Multiclass Prediction

With the emergence of big data and the interest in deriving valuable insights from ever-growing and ever-changing streams of data, machine learning has appeared as an effective data analytic technique as compared to traditional methodologies. Big data has become a source of incredible business value for almost every industry. In this context, machine learning plays an indispensable role of providing smart data analysis capabilities for uncovering hidden patterns. These patterns are later translated into automating certain aspects of the decision-making processes using machine learning classifiers. This paper presents a state-of-the-art comparative analysis of machine learning and deep learning-based classifiers for multiclass prediction. The experimental setup consisted of 11 datasets derived from different domains, publicly available at the repositories of UCI and Kaggle. The classifiers include Naïve Bayes (NB), decision trees (DTs), random forest (RF), gradient boosted decision trees (GBDTs), and deep learning-based convolutional neural networks (CNN). The results prove that the ensemble-based GBDTs outperform other algorithms in terms of accuracy, precision, and recall. RF and CNN show nearly similar performance on most datasets and outperform the traditional NB and DTs. On the other hand, NB shows the lowest performance as compared to other algorithms. It is worth mentioning that DTs show the lowest precision score on the Titanic dataset. One of the main reasons is that DTs suffer from overfitting and use a greedy approach for attribute relationship analysis.

Deep Learning-Based Electrocardiograph in Evaluating Radiofrequency Ablation for Rapid Arrhythmia.

This study is aimed at analyzing the important role of deep learning-based electrocardiograph (ECG) in the efficacy evaluation of radiofrequency ablation in the treatment of tachyarrhythmia. In this study, 158 patients with rapid arrhythmia treated by radiofrequency ablation were divided into effective treatment group (142 cases) and ineffective treatment group (16 cases). ECG examination was performed on all patients, and the indicators of ECG examination were quantified by the deep learning-based convolutional neural network model. The indicators of ECG examination of the effective treatment group and the ineffective treatment group were compared. The results showed that compared with the ineffective treatment group, the end-systolic volume (ESV), end-diastolic volume (EDV), end-systolic volume index (ESVI), and end-diastolic volume index (EDVI) of the effective treatment group were significantly decreased, and the left ventricular ejection fraction (LVEF) was significantly increased (P < 0.05). After radiofrequency ablation, the ventricular rate of patients in the effective treatment group was significantly lower than that of the ineffective treatment group at 12 h and 24 h after treatment (P < 0.05). In addition, compared with patients in the ineffective treatment group, the QT dispersion of the ECG in the effective treatment group was significantly higher (P < 0.05). The accuracy, specificity, and sensitivity of ECG in evaluating the therapeutic effect of patients with tachyarrhythmia were 86.81%, 84.29%, and 77.27%, respectively. The area under the curve was determined as 0.798 according to the receiver operating characteristic (ROC) curve of the subjects. In summary, indicators of ECG examination based on deep learning can provide auxiliary reference information for the efficacy evaluation of radiofrequency ablation in the treatment of tachyarrhythmia.

An automated diagnosis and classification of COVID-19 from chest CT images using a transfer learning-based convolutional neural network

Researchers have developed more intelligent, highly responsive, and efficient detection methods owing to the COVID-19 demands for more widespread diagnosis. The work done deals with developing an AI-based framework that can help radiologists and other healthcare professionals diagnose COVID-19 cases at a high level of accuracy. However, in the absence of publicly available CT datasets, the development of such AI tools can prove challenging. Therefore, an algorithm for performing automatic and accurate COVID-19 classification using Convolutional Neural Network (CNN), pre-trained model, and Sparrow search algorithm (SSA) on CT lung images was proposed. The pre-trained CNN models used are SeresNext50, SeresNext101, SeNet154, MobileNet, MobileNetV2, MobileNetV3Small, and MobileNetV3Large. In addition, the SSA will be used to optimize the different CNN and transfer learning(TL) hyperparameters to find the best configuration for the pre-trained model used and enhance its performance. Two datasets are used in the experiments. There are two classes in the first dataset, while three in the second. The authors combined two publicly available COVID-19 datasets as the first dataset, namely the COVID-19 Lung CT Scans and COVID-19 CT Scan Dataset. In total, 14,486 images were included in this study. The authors analyzed the Large COVID-19 CT scan slice dataset in the second dataset, which utilized 17,104 images. Compared to other pre-trained models on both classes datasets, MobileNetV3Large pre-trained is the best model. As far as the three-classes dataset is concerned, a model trained on SeNet154 is the best available. Results show that, when compared to other CNN models like LeNet-5 CNN, COVID faster R–CNN, Light CNN, Fuzzy + CNN, Dynamic CNN, CNN and Optimized CNN, the proposed Framework achieves the best accuracy of 99.74% (two classes) and 98% (three classes).

An efficient machine learning-based COVID-19 identification utilizing chest X-ray images

There is no well-known vaccine for coronavirus disease (COVID-19) with 100% efficiency. COVID-19 patients suffer from a lung infection, where lung-related problems can be effectively diagnosed with image techniques. The golden test for COVID-19 diagnosis is the RT-PCR test, which is costly, time-consuming and unavailable for various countries. Thus, machine learning-based tools are a viable solution. Here, we used a labelled chest X-ray of three categories, then performed data cleaning and augmentation to use the data in deep learning-based convolutional neural network (CNN) models. We compared the performance of different models that we gradually built and analyzed their accuracy. For that, we used 2905 chest X-ray scan samples. We were able to develop a model with the best accuracy of 97.44% for identifying COVID-19 using X-ray images. Thus, in this paper, we attested the feasibility of efficiently applying machine learning (ML) based models for medical image classification.

Inferring safety critical events from vehicle kinematics in naturalistic driving environment: Application of deep learning Algorithms

Advances in sensing technology has enabled the collection of countless terabytes of second-by-second kinematics data. Such data provides opportunities for real-time monitoring of driving behavior and identification of safety critical events (SCEs) including crashes and near crashes. The concept of volatility is relevant in this context, which identifies instability and erratic variations in driving behavior prior to involvement in SCEs. This study utilized vehicle kinematics from a large-scale naturalistic driving data to develop a deep learning approach based on 1D convolutional neural networks (CNN) for inferring SCEs. The data are unique in the sense that such accurate pre-crash data at high fidelity are not available in traditional crash repositories. This study contributes to the literature by providing a first attempt at predicting responses to SCEs by developing deep learning-based CNN architectures using novel driving volatility based kinematic thresholds for a sample of 9553 events. The key contribution lies in developing a volatility-based CNN input layout that is acceptable to CNN schemes and represents the motion kinematics such as speed, acceleration and volatility measures. Several 1D-CNN architectures were developed using layers, numbers of convolutions, layer patterns, and kernels. Shallow and deep architectures were tested, revealing higher accuracy of shallow architectures in detecting SCEs. The optimal number of epochs were identified using an early stopping method while the CNN performance was improved by increasing the number of epochs. The ensemble CNN had the highest predictive accuracy of 95.6% for detection of crashes and near crashes, which was 2.5% higher than the optimal CNN using 20% hold out test data. The ensemble CNN also outperformed classical machine learning models and model performance reported in past studies on detection of SCEs. These results have implications for identification of safety hotspots and providing real-time alerts and warnings in connected and highly automated vehicle environment including society of automotive engineers levels 3–5.

A transfer learning-based CNN and LSTM hybrid deep learning model to classify motor imagery EEG signals

In the Motor Imagery (MI)-based Brain Computer Interface (BCI), users' intention is converted into a control signal through processing a specific pattern in brain signals reflecting motor characteristics. There are such restrictions as the limited size of the existing datasets and low signal to noise ratio in the classification of MI Electroencephalogram (EEG) signals. Machine learning (ML) methods, particularly Deep Learning (DL), have overcome these limitations relatively. In this study, three hybrid models were proposed to classify the EEG signal in the MI-based BCI. The proposed hybrid models consist of the convolutional neural networks (CNN) and the Long-Short Term Memory (LSTM). In the first model, the CNN with different number of convolutional-pooling blocks (from shallow to deep CNN) was examined; a two-block CNN model not affected by the vanishing gradient descent and yet able to extract desirable features employed; the second and third models contained pre-trained CNNs conducing to the exploration of more complex features. The transfer learning strategy and data augmentation methods were applied to overcome the limited size of the datasets by transferring learning from one model to another. This was achieved by employing two powerful pre-trained convolutional neural networks namely ResNet-50 and Inception-v3. The continuous wavelet transform (CWT) was used to generate images for the CNN. The performance of the proposed models was evaluated on the BCI Competition IV dataset 2a. The mean accuracy vlaues of 86%, 90%, and 92%, and mean Kappa values of 81%, 86%, and 88% were obtained for the hybrid neural network with the customized CNN, the hybrid neural network with ResNet-50 and the hybrid neural network with Inception-v3, respectively. Despite the promising performance of the three proposed models, the hybrid neural network with Inception-v3 outperformed the two other models. The best obtained result in the present study improved the previous best result in the literature by 7% in terms of classification accuracy. From the findings, it can be concluded that transfer learning based on a pre-trained CNN in combination with LSTM is a novel method in MI-based BCI. The study also has implications for the discrimination of motor imagery tasks in each EEG recording channel and in different brain regions which can reduce computational time in future works by only selecting the most effective channels.

Breast lesions classifications of mammographic images using a deep convolutional neural network-based approach

Breast cancer is one of the worst illnesses, with a higher fatality rate among women globally. Breast cancer detection needs accurate mammography interpretation and analysis, which is challenging for radiologists owing to the intricate anatomy of the breast and low image quality. Advances in deep learning-based models have significantly improved breast lesions’ detection, localization, risk assessment, and categorization. This study proposes a novel deep learning-based convolutional neural network (ConvNet) that significantly reduces human error in diagnosing breast malignancy tissues. Our methodology is most effective in eliciting task-specific features, as feature learning is coupled with classification tasks to achieve higher performance in automatically classifying the suspicious regions in mammograms as benign and malignant. To evaluate the model’s validity, 322 raw mammogram images from Mammographic Image Analysis Society (MIAS) and 580 from Private datasets were obtained to extract in-depth features, the intensity of information, and the high likelihood of malignancy. Both datasets are magnificently improved through preprocessing, synthetic data augmentation, and transfer learning techniques to attain the distinctive combination of breast tumors. The experimental findings indicate that the proposed approach achieved remarkable training accuracy of 0.98, test accuracy of 0.97, high sensitivity of 0.99, and an AUC of 0.99 in classifying breast masses on mammograms. The developed model achieved promising performance that helps the clinician in the speedy computation of mammography, breast masses diagnosis, treatment planning, and follow-up of disease progression. Moreover, it has the immense potential over retrospective approaches in consistency feature extraction and precise lesions classification.

Deep Learning Based Convolutional Neural Network Structured New Image Classification Approach for Eye Disease Identification

A deep learning-based convolutional artificial neural networks structured a new image classification method approach was implemented in the study. Sample application was carried out with Diabetic Retinopathy disease. Obtaining information about the blood vessels and any abnormal patterns from the rest of the phonoscopic image and assessing the degree of retinopathy is the problem itself. To solve this problem developed methodology and algorithmic structure of this new approach is presented in the study. An approach called care model was used in this study different from the classical CNN structure. The care approach is based on the idea that the best solution will be taken from the new data obtained by rescale the available data according to total number of pixels before the average data pool is created and then CNN processes will continue. In the care model approach, all data is multiplied by the number of elements by the number of epoch time eight tensors. The purposed care model include VGG19 image classification model and developed mathematical model presented. Pre-trained model and all image dataset taken from kaggle and keras for implementation of case study. The purposed model provide train accuracy 87%, test accuracy 88%, precision 93% and recall 83%.

Deep learning-based convolutional neural network for intramodality brain MRI synthesis.

PurposeThe existence of multicontrast magnetic resonance (MR) images increases the level of clinical information available for the diagnosis and treatment of brain cancer patients. However, acquiring the complete set of multicontrast MR images is not always practically feasible. In this study, we developed a state‐of‐the‐art deep learning convolutional neural network (CNN) for image‐to‐image translation across three standards MRI contrasts for the brain.MethodsBRATS’2018 MRI dataset of 477 patients clinically diagnosed with glioma brain cancer was used in this study, with each patient having T1‐weighted (T1), T2‐weighted (T2), and FLAIR contrasts. It was randomly split into 64%, 16%, and 20% as training, validation, and test set, respectively. We developed a U‐Net model to learn the nonlinear mapping of a source image contrast to a target image contrast across three MRI contrasts. The model was trained and validated with 2D paired MR images using a mean‐squared error (MSE) cost function, Adam optimizer with 0.001 learning rate, and 120 epochs with a batch size of 32. The generated synthetic‐MR images were evaluated against the ground‐truth images by computing the MSE, mean absolute error (MAE), peak signal‐to‐noise ratio (PSNR), and structural similarity index (SSIM).ResultsThe generated synthetic‐MR images with our model were nearly indistinguishable from the real images on the testing dataset for all translations, except synthetic FLAIR images had slightly lower quality and exhibited loss of details. The range of average PSNR, MSE, MAE, and SSIM values over the six translations were 29.44–33.25 dB, 0.0005–0.0012, 0.0086–0.0149, and 0.932–0.946, respectively. Our results were as good as the best‐reported results by other deep learning models on BRATS datasets.ConclusionsOur U‐Net model exhibited that it can accurately perform image‐to‐image translation across brain MRI contrasts. It could hold great promise for clinical use for improved clinical decision‐making and better diagnosis of brain cancer patients due to the availability of multicontrast MRIs. This approach may be clinically relevant and setting a significant step to efficiently fill a gap of absent MR sequences without additional scanning.

Diagnosis of Active Pulmonary Tuberculosis and Community Acquired Pneumonia Using Convolution Neural Network Based on Transfer Learning

A convolutional neural network (CNN) model for the diagnosis of active pulmonary tuberculosis (APTB) and community-acquired pneumonia (CAP) using chest radiographs (CRs) was constructed and verified based on transfer learning. CRs of 1247 APTB cases, 1488 CAP cases and 1247 normal cases were collected. All CRs were randomly divided into training set (1992 cases), validation set (1194 cases) and test set (796 cases) by stratified sampling in 5:3:2 radio. After normalization of CRs, the convolution base of pre-trained CNN (VGG16) model on ImageNet dataset was used to extract features, and the grid search was used to determine the optimal classifier module, which was added to the convolution base for transfer learning. After the training, the model with the highest accuracy of the validation set was selected as the optimal model to verify in the test set and calculate the accuracy of the model. The accuracy of validation set in the 63rd epochs was the highest, which was 0.9430, and the corresponding Categorical crossentropy was 0.1742. The accuracy of the training set was 0.9428, and the Categorical crossentropy was 0.1545. When the optimal model was applied to the test set, the accuracy was 0.9447, and the Categorical crossentropy was 0.1929. The transfer learning-based CNN model has good classification performance in the diagnosis of APTB, CAP and normal patients using CRs.

Artificial Intelligence-Based Real-Time Pineapple Quality Classification Using Acoustic Spectroscopy

The pineapple is an essential fruit in Taiwan. Farmers separate pineapples into two types, according to the percentages of water in the pineapples. One is the “drum sound pineapple” and the other is the “meat sound pineapple”. As there is more water in the meat sound pineapple, the meat sound pineapple more easily rots and is more challenging to store than the drum sound pineapple. Thus, farmers need to filter out the meat sound pineapple, so that they can sell pineapples overseas. The classification, based on striking the pineapple fruit with rigid objects (e.g., plastic rulers) is most commonly used by farmers due to the negligibly low costs and availability. However, it is a time-consuming job, so we propose a method to automatically classify pineapples in this work. Using embedded onboard computing processors, servo, and an ultrasonic sensor, we built a hitting machine and combined it with a conveyor to automatically separate pineapples. To classify pineapples, we proposed a method related to acoustic spectrogram spectroscopy, which uses acoustic data to generate spectrograms. In the acoustic data collection step, we used the hitting machine mentioned before and collected many groups of data with different factors; some groups also included the noise in the farm. With these differences, we tested our deep learning-based convolutional neural network (CNN) performances. The best accuracy of the developed CNN model is 0.97 for data Group V. The proposed hitting machine and the CNN model can assist in the classification of pineapple fruits with high accuracy and time efficiency.

InSiNet: a deep convolutional approach to skin cancer detection and segmentation

Cancer is among the common causes of death around the world. Skin cancer is one of the most lethal types of cancer. Early diagnosis and treatment are vital in skin cancer. In addition to traditional methods, method such as deep learning is frequently used to diagnose and classify the disease. Expert experience plays a major role in diagnosing skin cancer. Therefore, for more reliable results in the diagnosis of skin lesions, deep learning algorithms can help in the correct diagnosis. In this study, we propose InSiNet, a deep learning-based convolutional neural network to detect benign and malignant lesions. The performance of the method is tested on International Skin Imaging Collaboration HAM10000 images (ISIC 2018), ISIC 2019, and ISIC 2020, under the same conditions. The computation time and accuracy comparison analysis was performed between the proposed algorithm and other machine learning techniques (GoogleNet, DenseNet-201, ResNet152V2, EfficientNetB0, RBF-support vector machine, logistic regression, and random forest). The results show that the developed InSiNet architecture outperforms the other methods achieving an accuracy of 94.59%, 91.89%, and 90.54% in ISIC 2018, 2019, and 2020 datasets, respectively. Since the deep learning algorithms eliminate the human factor during diagnosis, they can give reliable results in addition to traditional methods.