Deep Convolutional Neural Network Approach Research Articles

Segmentation and Classification of Glaucoma Using U-Net with Deep Learning Model.

Glaucoma is the second most common cause for blindness around the world and the third most common in Europe and the USA. Around 78 million people are presently living with glaucoma (2020). It is expected that 111.8 million people will have glaucoma by the year 2040. 90% of glaucoma is undetected in developing nations. It is essential to develop a glaucoma detection system for early diagnosis. In this research, early prediction of glaucoma using deep learning technique is proposed. In this proposed deep learning model, the ORIGA dataset is used for the evaluation of glaucoma images. The U-Net architecture based on deep learning algorithm is implemented for optic cup segmentation and a pretrained transfer learning model; DenseNet-201 is used for feature extraction along with deep convolution neural network (DCNN). The DCNN approach is used for the classification, where the final results will be representing whether the glaucoma infected or not. The primary objective of this research is to detect the glaucoma using the retinal fundus images, which can be useful to determine if the patient was affected by glaucoma or not. The result of this model can be positive or negative based on the outcome detected as infected by glaucoma or not. The model is evaluated using parameters such as accuracy, precision, recall, specificity, and F-measure. Also, a comparative analysis is conducted for the validation of the model proposed. The output is compared to other current deep learning models used for CNN classification, such as VGG-19, Inception ResNet, ResNet 152v2, and DenseNet-169. The proposed model achieved 98.82% accuracy in training and 96.90% in testing. Overall, the performance of the proposed model is better in all the analysis.

Quantification of uptake in pelvis F-18 FLT PET-CT images using a 3D localization and segmentation CNN.

The purpose of this work was to develop and validate a deep convolutional neural network (CNN) approach for the automated pelvis segmentation in computed tomography (CT) scans to enable the quantification of active pelvic bone marrow by means of Fluorothymidine F-18 (FLT) tracer uptake measurement in positron emission tomography (PET) scans. This quantification is a critical step in calculating bone marrow dose for radiopharmaceutical therapy clinical applications as well as external beam radiationdoses. An approach for the combined localization and segmentation of the pelvis in CT volumes of varying sizes, ranging from full-body to pelvis CT scans, was developed that utilizes a novel CNN architecture in combination with a random sampling strategy. The method was validated on 34 planning CT scans and 106 full-body FLT PET-CT scans using a cross-validation strategy. Specifically, two different training and CNN application options were studied, quantitatively assessed, and statisticallycompared. The proposed method was able to successfully locate and segment the pelvis in all test cases. On all data sets, an average Dice coefficient of 0.9396 0.0182 or better was achieved. The relative tracer uptake measurement error ranged between 0.065% and 0.204%. The proposed approach is time-efficient and shows a reduction in runtime of up to 95% compared to a standard U-Net-based approach without a localizationcomponent. The proposed method enables the efficient calculation of FLT uptake in the pelvis. Thus, it represents a valuable tool to facilitate bone marrow preserving adaptive radiation therapy and radiopharmaceutical dose calculation. Furthermore, the method can be adapted to process other bone structures as well asorgans.

Design and implementation of intelligent patient in-house monitoring system based on efficient XGBoost-CNN approach.

Because of the scarcity of caregivers and the high cost of medical devices, it is difficult to keep track of the aging population and provide assistance. To avoid deterioration of health issues, continuous monitoring of personal health should be done prior to the intervention. If a problem is discovered, the IoT platform collects and presents the caretaker with graphical data. The death rates of older patients are reduced when projections are made ahead of time. Patients can die as a result of minor abnormalities in their ECG. The cardiac dysrhythmia/irregular heart rate is classified with several multilayer parameters using a deep convolutional neural network (CNN) approach in this paper. The key benefit of utilizing this CNN approach is that it can handle databases that have been purposefully oversampled. Using the XGBoost approach, these are oversampled to deal with difficulties like minority class and imbalance. XGBoost is a decision tree-based ensemble learning algorithm that uses a gradient boosting framework. It uses an artificial neural network and predicts the unstructured data in a structured manner. This CNN-based supervised learning model is tested and simulated on a real-time elderly heart patient IoT dataset. The proposed methodology has a recall value of 100%, an F1-Score of 94.8%, a precision of 98%, and an accuracy of 98%, which is higher than existing approaches like decision trees, random forests, and Support Vector Machine. The results reveal that the proposed model outperforms state-of-the-art methodologies and improves elderly heart disease patient monitoring with a low error rate.

DIAT-μSAT: Small Aerial Targets’ Micro-Doppler Signatures and Their Classification Using CNN

Protective measures against small unmanned aerial vehicles (UAVs) are vital from a national security perspective. As a result, the importance of surveillance systems that automatically identify and classify low radar cross section (RCS) aerial targets increases. In this work, an indigenously developed continuous wave (CW) (X-band: 10 GHz) radar is used to build a diversified “DIAT- <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\mu $ </tex-math></inline-formula> SAT” dataset comprising 4849 micro-Doppler signature images of five different small aerial targets. We also proposed a transfer learning-based deep convolutional neural network (DCNN) approach for classifying low RCS aerial targets. We demonstrated the classification accuracy of 95% and 97%, with VGG16 and VGG19 as feature extractors, respectively, with minimal false-negative and -positive results. The open-field experimental classes covered in this work are: 1) a two-blade rotor; 2) a three-short-blade rotor; 3) a three-long-blade rotor; 4) a quadcopter; 5) a bionic bird; and 6) a two-blade-rotor and bionic bird. We also observed a good classification accuracy (>97%) when more than one target is operated simultaneously.

Melanoma Skin Cancer Detection Using Recent Deep Learning Models.

Melanoma is considered as one of the world's deadly cancers. This type of skin cancer will spread to other areas of the body if not detected at an early stage. Convolutional Neural Network (CNN) based classifiers are currently considered one of the most effective melanoma detection techniques. This study presents the use of recent deep CNN approaches to detect melanoma skin cancer and investigate suspicious lesions. Tests were conducted using a set of more than 36,000 images extracted from multiple datasets. The obtained results show that the best performing deep learning approach achieves high scores with an accuracy and Area Under Curve (AUC) above 99%.

Classification of Breast Cancer Lesions in Ultrasound Images by Using Attention Layer and Loss Ensemble in Deep Convolutional Neural Networks.

The reliable classification of benign and malignant lesions in breast ultrasound images can provide an effective and relatively low-cost method for the early diagnosis of breast cancer. The accuracy of the diagnosis is, however, highly dependent on the quality of the ultrasound systems and the experience of the users (radiologists). The use of deep convolutional neural network approaches has provided solutions for the efficient analysis of breast ultrasound images. In this study, we propose a new framework for the classification of breast cancer lesions with an attention module in a modified VGG16 architecture. The adopted attention mechanism enhances the feature discrimination between the background and targeted lesions in ultrasound. We also propose a new ensembled loss function, which is a combination of binary cross-entropy and the logarithm of the hyperbolic cosine loss, to improve the model discrepancy between classified lesions and their labels. This combined loss function optimizes the network more quickly. The proposed model outperformed other modified VGG16 architectures, with an accuracy of 93%, and also, the results are competitive with those of other state-of-the-art frameworks for the classification of breast cancer lesions. Our experimental results show that the choice of loss function is highly important and plays a key role in breast lesion classification tasks. Additionally, by adding an attention block, we could improve the performance of the model.

Deep learning network optimization and hyperparameter tuning for seismic lithofacies classification

Deep learning is increasingly being applied in many aspects of seismic processing and interpretation. Here, we look at a deep convolutional neural network approach to multiclass seismic lithofacies characterization using well logs and seismic data. In particular, we focus on network performance and hyperparameter tuning. Several hyperparameter tuning approaches are compared, including true and directed random search methods such as very fast simulated annealing and Bayesian hyperparameter optimization. The results show that improvements in predictive capability are possible by using automatic optimization compared with manual parameter selection. In addition to evaluating the prediction accuracy's sensitivity to hyperparameters, we test various types of data representations. The choice of input seismic data can significantly impact the overall accuracy and computation speed of the optimized networks for the classification challenge under consideration. This is validated on a 3D synthetic seismic lithofacies example with acoustic and lithologic properties based on real well data and structure from an onshore oil field.

A Hybrid Deep Convolutional Neural Network Approach for Predicting the Traffic Congestion Index

Traffic congestion is one of the most important issues in large cities, and the overall travel speed is an important factor that reflects the traffic status on road networks. This study proposes a hybrid deep convolutional neural network (CNN) method that uses gradient descent optimization algorithms and pooling operations for predicting the short-term traffic congestion index in urban networks based on probe vehicles. First, the input data are collected by the probe vehicles to calculate the traffic congestion index (output label). Then, a CNN that uses gradient descent optimization algorithms and pooling operations is applied to enhance its performance. Finally, the proposed model is chosen on the basis of the R-squared (R2) and root mean square error (RMSE) values. In the best-case scenario, the proposed model achieved an R2 value of 98.7%. In addition, the experiments showed that the proposed model significantly outperforms other algorithms, namely the ordinary least squares (OLS), k-nearest neighbors (KNN), random forest (RF), recurrent neural network (RNN), artificial neural network (ANN), and convolutional long short-term memory (ConvLSTM), in predicting traffic congestion index. Furthermore, using the proposed method, the time-series changes in the traffic congestion status can be reliably visualized for the entire urban network.

Investigation of Deep Convolutional Neural Network (CNN) approaches’ accuracy for the detection of COVID-19

Abstract— the world those days focuses on protecting human health and combating the irruption of coronavirus patients (COVID-19). As results of its extra ordinarily contagious infection that have caused a disturbance in everyone's lives in various ways. For early screening, Reverse Transcription Protein Chain Reaction (RT-PCR) test is used to examine the onset of the patients by detecting the RNA material of the virus among the patients’ samples. Recent results indicate that the applying of X-ray images and X-radiation (CT) improves the detection accuracy of this disease. However, the classification task of medical images is tough due to several factors such as lack of dataset for COVID-19, and difficulty in identifying type of infection. Recent research works have been proposed for COVID-19 detection that has been applied on specific datasets. Thus, it is vital to validate their performance on various datasets with different imaging disease conditions. The paper presents a comparison study between top performer CNN models that recorded the very best detection accuracy in image detection and classification: COVID-Net, VGG16, ResNet, Bayesian, DenseNet, and DarkNet. Such CNN approaches can assist medical staff in the early detection of infection. Additionally, we improved dataset in terms of quality, clarity, and quantity using augmentation technique. The quantitative results show that Darknet and COVID-net yield high detection accuracy when applied on CT and X-ray dataset. We validated our results by training the models on multiple different datasets, using CPU and GPU with various bach sizes and optimizers.

Automated accurate emotion recognition system using rhythm-specific deep convolutional neural network technique with multi-channel EEG signals

Emotion is interpreted as a psycho-physiological process, and it is associated with personality, behavior, motivation, and character of a person. The objective of affective computing is to recognize different types of emotions for human-computer interaction (HCI) applications. The spatiotemporal brain electrical activity is measured using multi-channel electroencephalogram (EEG) signals. Automated emotion recognition using multi-channel EEG signals is an exciting research topic in cognitive neuroscience and affective computing. This paper proposes the rhythm-specific multi-channel convolutional neural network (CNN) based approach for automated emotion recognition using multi-channel EEG signals. The delta (δ), theta (θ), alpha (α), beta (β), and gamma (γ) rhythms of EEG signal for each channel are evaluated using band-pass filters. The EEG rhythms from the selected channels coupled with deep CNN are used for emotion classification tasks such as low-valence (LV) vs. high valence (HV), low-arousal (LA) vs. high-arousal (HA), and low-dominance (LD) vs. high dominance (HD) respectively. The deep CNN architecture considered in the proposed work has eight convolutions, three average pooling, four batch-normalization, three spatial drop-outs, two drop-outs, one global average pooling and, three dense layers. We have validated our developed model using three publicly available databases: DEAP, DREAMER, and DASPS. The results reveal that the proposed multivariate deep CNN approach coupled with β-rhythm has obtained the accuracy values of 98.91%, 98.45%, and 98.69% for LV vs. HV, LA vs. HA, and LD vs. HD emotion classification strategies, respectively using DEAP database with 10-fold cross-validation (CV) scheme. Similarly, the accuracy values of 98.56%, 98.82%, and 98.99% are obtained for LV vs. HV, LA vs. HA, and LD vs. HD classification schemes, respectively, using deep CNN and θ-rhythm. The proposed multi-channel rhythm-specific deep CNN classification model has obtained the average accuracy value of 57.14% using α-rhythm and trial-specific CV using DASPS database. Moreover, for 8-quadrant based emotion classification strategy, the deep CNN based classifier has obtained an overall accuracy value of 24.37% using γ-rhythms of multi-channel EEG signals. Our developed deep CNN model can be used for real-time automated emotion recognition applications.

Artificial intelligence improves the accuracy of residents in the diagnosis of hip fractures: a multicenter study

BackgroundLess experienced clinicians sometimes make misdiagnosis of hip fractures. We developed computer-aided diagnosis (CAD) system for hip fractures on plain X-rays using a deep learning model trained on a large dataset. In this study, we examined whether the accuracy of the diagnosis of hip fracture of the residents could be improved by using this system.MethodsA deep convolutional neural network approach was used for machine learning. Pytorch 1.3 and Fast.ai 1.0 were applied as frameworks, and an EfficientNet-B4 model (a pre-trained ImageNet model) was used. We handled the 5295 X-rays from the patients with femoral neck fracture or femoral trochanteric fracture from 2009 to 2019. We excluded cases in which the bilateral hips were not included within an image range, and cases of femoral shaft fracture and periprosthetic fracture. Finally, we included 5242 AP pelvic X-rays from 4851 cases. We divided these 5242 images into two images per image, and prepared 5242 images including fracture site and 5242 images without fracture site. Thus, a total of 10,484 images were used for machine learning. The accuracy, sensitivity, specificity, F-value, and area under the curve (AUC) were assessed. Gradient-weighted class activation mapping (Grad-CAM) was used to conceptualize the basis for the diagnosis of the fracture by the deep learning algorithm. Secondly, we conducted a controlled experiment with clinicians. Thirty-one residents;young doctors within 2 years of graduation from medical school who rotate through various specialties, were tested using 300 hip fracture images that were randomly extracted from the dataset. We evaluated the diagnostic accuracy with and without the use of the CAD system for each of the 300 images.ResultsThe accuracy, sensitivity, specificity, F-value, and AUC were 96.1, 95.2, 96.9%, 0.961, and 0.99, respectively, with the correct diagnostic basis generated by Grad-CAM. In the controlled experiment, the diagnostic accuracy of the residents significantly improved when they used the CAD system.ConclusionsWe developed a newly CAD system with a deep learning algorithm from a relatively large dataset from multiple institutions. Our system achieved high diagnostic performance. Our system improved the diagnostic accuracy of residents for hip fractures.Level of evidenceLevel III, Foundational evidence, before-after study. Clinical relevance: high

DSANet: Dilated spatial attention for real-time semantic segmentation in urban street scenes

Efficient and accurate semantic segmentation is particularly important in scene understanding for autonomous driving. Although Deep Convolutional Neural Networks(DCNNs) approaches have made a significant improvement for semantic segmentation. However, state-of-the-art models such as Deeplab and PSPNet have complex architectures and high computation complexity. Thus, it is inefficient for realtime applications. On the other hand, many works compromise the performance to obtain real-time inference speed which is critical for developing a light network model with high segmentation accuracy. In this paper, we present a computationally efficient network named DSANet, which follows a two-branch strategy to tackle the problem of real-time semantic segmentation in urban scenes. We first design a Semantic Encoding Branch, which employs channel split and shuffle to reduce the computation and maintain higher segmentation accuracy. Also, we propose a dual attention module consisting of dilated spatial attention and channel attention to make full use of the multi-level feature maps simultaneously, which helps predict the pixel-wise labels in each stage. Meanwhile, Spatial Encoding Network is used to enhance semantic information and preserve the spatial details. To better combine context information and spatial information, we introduce a Simple Feature Fusion Module. We evaluated our model with state-of-the-art semantic image semantic segmentation methods using two challenging datasets. The proposed method achieves an accuracy of 69.9% mean IoU and 71.3% mean IoU at speed of 75.3 fps and 34.08 fps on CamVid and Cityscapes test datasets respectively.

AI-driven deep CNN approach for multi-label pathology classification using chest X-Rays.

Artificial intelligence (AI) has played a significant role in image analysis and feature extraction, applied to detect and diagnose a wide range of chest-related diseases. Although several researchers have used current state-of-the-art approaches and have produced impressive chest-related clinical outcomes, specific techniques may not contribute many advantages if one type of disease is detected without the rest being identified. Those who tried to identify multiple chest-related diseases were ineffective due to insufficient data and the available data not being balanced. This research provides a significant contribution to the healthcare industry and the research community by proposing a synthetic data augmentation in three deep Convolutional Neural Networks (CNNs) architectures for the detection of 14 chest-related diseases. The employed models are DenseNet121, InceptionResNetV2, and ResNet152V2; after training and validation, an average ROC-AUC score of 0.80 was obtained competitive as compared to the previous models that were trained for multi-class classification to detect anomalies in x-ray images. This research illustrates how the proposed model practices state-of-the-art deep neural networks to classify 14 chest-related diseases with better accuracy.

Automatic colonic polyp detection using integration of modified deep residual convolutional neural network and ensemble learning approaches

Background and ObjectiveThe increased incidence of colorectal cancer (CRC) and its mortality rate have attracted interest in the use of artificial intelligence (AI) based computer-aided diagnosis (CAD) tools to detect polyps at an early stage. Although these CAD tools have thus far achieved a good accuracy level to detect polyps, they still have room to improve further (e.g. sensitivity). Therefore, a new CAD tool is developed in this study to detect colonic polyps accurately. MethodsIn this paper, we propose a novel approach to distinguish colonic polyps by integrating several techniques, including a modified deep residual network, principal component analysis and AdaBoost ensemble learning. A powerful deep residual network architecture, ResNet-50, was investigated to reduce the computational time by altering its architecture. To keep the interference to a minimum, median filter, image thresholding, contrast enhancement, and normalisation techniques were exploited on the endoscopic images to train the classification model. Three publicly available datasets, i.e., Kvasir, ETIS-LaribPolypDB, and CVC-ClinicDB, were merged to train the model, which included images with and without polyps. ResultsThe proposed approach trained with a combination of three datasets achieved Matthews Correlation Coefficient (MCC) of 0.9819 with accuracy, sensitivity, precision, and specificity of 99.10%, 98.82%, 99.37%, and 99.38%, respectively. ConclusionsThese results show that our method could repeatedly classify endoscopic images automatically and could be used to effectively develop computer-aided diagnostic tools for early CRC detection.

Multi-classification of alzheimer disease on magnetic resonance images (MRI) using deep convolutional neural network (DCNN) approaches

Multi-classification of alzheimer disease on magnetic resonance images (MRI) using deep convolutional neural network (DCNN) approaches

Integration of deep convolutional neural networks and mathematical morphology-based postclassification framework for urban slum mapping

We propose the convolutional neural networks approach for detecting urban slums from very high resolution (VHR) satellite images. Slums are becoming an inevitable and growing phenomenon in cities of the global south, whose locations are inappropriate in official statistics and maps. Thus the automatic detection and identification of slums provides vibrant information to decision-makers for formulating pro-poor policies in urban planning. However, field surveys are used as the conventional methods for slum detection, which are expensive and inefficient. The challenge is to find an automatic approach for identifying slums from VHR imagery. Although numerous studies focused on detecting slums from satellite data, only limited number captured their differences. Due to the unique spectral signatures of urban slums, it could not be simply classified as other urban (buildings, vegetation, and roads) features. We explore the potential of the dilated kernel-based deep convolutional neural network (DK-DCNN) approach to the learning of discriminatory spatial features and the automatic detection of slums from other features. However, the result obtained by the proposed DK-DCNN achieves high accuracy. The open area of informal settlements and the roofing structures of formal settlements are misclassified as slums. Morphological spatial pattern analysis, based on mathematical morphology, is used as a postprocessing method to enhance the classification accuracy. The four distinct very high-resolution satellite images captured by WorldView-2 Sensor (1.84 m) of Madurai and Tiruppur city, South India, have shown the performance of the proposed method to distinguish urban slums from other features by producing higher accuracy than any other approach.

A deep-learning semantic segmentation approach to fully automated MRI-based left-ventricular deformation analysis in cardiotoxicity

Left-ventricular (LV) strain measurements with the Displacement Encoding with Stimulated Echoes (DENSE) MRI sequence provide accurate estimates of cardiotoxicity damage related to breast cancer chemotherapy. This study investigated an automated LV chamber quantification tool via segmentation with a supervised deep convolutional neural network (DCNN) before strain analysis with DENSE images. Segmentation for chamber quantification analysis was conducted with a custom DeepLabV3+ DCNN with ResNet-50 backbone on 42 female breast cancer datasets (22 training-sets, eight validation-sets and 12 independent test-sets). Parameters such as LV end-diastolic diameter (LVEDD) and ejection fraction (LVEF) were quantified, and myocardial strains analyzed with the Radial Point Interpolation Method (RPIM). Myocardial classification was validated against ground-truth with sensitivity-specificity analysis, the metrics of Dice, average perpendicular distance (APD) and Hausdorff-distance. Following segmentation, validation was conducted with the Cronbach's Alpha (C-Alpha) intraclass correlation coefficient between LV chamber quantification results with DENSE and Steady State Free Precession (SSFP) acquisitions and a vendor tool-based method to segment the DENSE data, and similarly for myocardial strain analysis in the chambers. The results of myocardial classification from segmentation of the DENSE data were accuracy = 97%, Dice = 0.89 and APD = 2.4 mm in the test-set. The C-Alpha correlations from comparing chamber quantification results between the segmented DENSE and SSFP data and vendor tool-based method were 0.97 for LVEF (56 ± 7% vs 55 ± 7% vs 55 ± 6%, p = 0.6) and 0.77 for LVEDD (4.6 ± 0.4 cm vs 4.5 ± 0.3 cm vs 4.5 ± 0.3 cm, p = 0.8). The validation metrics against ground-truth and equivalent parameters obtained from the SSFP segmentation and vendor tool-based comparisons show that the DCNN approach is applicable for automated LV chamber quantification and subsequent strain analysis in cardiotoxicity.

Cross-cohort generalizability of deep and conventional machine learning for MRI-based diagnosis and prediction of Alzheimer’s disease

This work validates the generalizability of MRI-based classification of Alzheimer’s disease (AD) patients and controls (CN) to an external data set and to the task of prediction of conversion to AD in individuals with mild cognitive impairment (MCI).We used a conventional support vector machine (SVM) and a deep convolutional neural network (CNN) approach based on structural MRI scans that underwent either minimal pre-processing or more extensive pre-processing into modulated gray matter (GM) maps. Classifiers were optimized and evaluated using cross-validation in the Alzheimer’s Disease Neuroimaging Initiative (ADNI; 334 AD, 520 CN). Trained classifiers were subsequently applied to predict conversion to AD in ADNI MCI patients (231 converters, 628 non-converters) and in the independent Health-RI Parelsnoer Neurodegenerative Diseases Biobank data set. From this multi-center study representing a tertiary memory clinic population, we included 199 AD patients, 139 participants with subjective cognitive decline, 48 MCI patients converting to dementia, and 91 MCI patients who did not convert to dementia.AD-CN classification based on modulated GM maps resulted in a similar area-under-the-curve (AUC) for SVM (0.940; 95%CI: 0.924–0.955) and CNN (0.933; 95%CI: 0.918–0.948). Application to conversion prediction in MCI yielded significantly higher performance for SVM (AUC = 0.756; 95%CI: 0.720-0.788) than for CNN (AUC = 0.742; 95%CI: 0.709-0.776) (p<0.01 for McNemar’s test). In external validation, performance was slightly decreased. For AD-CN, it again gave similar AUCs for SVM (0.896; 95%CI: 0.855–0.932) and CNN (0.876; 95%CI: 0.836–0.913). For prediction in MCI, performances decreased for both SVM (AUC = 0.665; 95%CI: 0.576-0.760) and CNN (AUC = 0.702; 95%CI: 0.624-0.786). Both with SVM and CNN, classification based on modulated GM maps significantly outperformed classification based on minimally processed images (p=0.01).Deep and conventional classifiers performed equally well for AD classification and their performance decreased only slightly when applied to the external cohort. We expect that this work on external validation contributes towards translation of machine learning to clinical practice.

A Novel Region-Based Image Registration Method for Multisource Remote Sensing Images Via CNN

The comprehensive utilization of images from various satellite sensors can significantly increase the performance of remote sensing applications and has, therefore, attracted extensive research attention. One of the essential challenges that research encounters comes from multisource image registration. This article proposes a novel region-based image registration method for multisource images. The proposed method exploits the region features of input images, which provide more consistent and common information of the multisource data. The image region features are extracted based on image semantic segmentation using the deep convolutional neural network approach. The final registration result is a pixel-level output corresponding to the input images. The proposed registration scheme overcomes the limits of traditional feature extraction methods (e.g., point feature) adopted in previous registration schemes. Results indicate that the proposed method has good performance for the multisource remote sensing image registration and can serve as a building block for the fusion of multisource images.

Automated multi-class classification of skin lesions through deep convolutional neural network with dermoscopic images.

As an analytic tool in medicine, deep learning has gained great attention and opened new ways for disease diagnosis. Recent studies validate the effectiveness of deep learning algorithms for binary classification of skin lesions (i.e., melanomas and nevi classes) with dermoscopic images. Nonetheless, those binary classification methods cannot be applied to the general clinical situation of skin cancer screening in which multi-class classification must be taken into account. The main objective of this research is to develop, implement, and calibrate an advanced deep learning model in the context of automated multi-class classification of skin lesions. The proposed Deep Convolutional Neural Network (DCNN) model is carefully designed with several layers, and multiple filter sizes, but fewer filters and parameters to improve efficacy and performance. Dermoscopic images are acquired from the International Skin Imaging Collaboration databases (ISIC-17, ISIC-18, and ISIC-19) for experiments. The experimental results of the proposed DCNN approach are presented in terms of precision, sensitivity, specificity, and other metrics. Specifically, it attains 94 % precision, 93 % sensitivity, and 91 % specificity in ISIC-17. It is demonstrated by the experimental results that this proposed DCNN approach outperforms state-of-the-art algorithms, exhibiting 0.964 area under the receiver operating characteristics (AUROC) in ISIC-17 for the classification of skin lesions and can be used to assist dermatologists in classifying skin lesions. As a result, this proposed approach provides a novel and feasible way for automating and expediting the skin lesion classification task as well as saving effort, time, and human life.