Search

Recently years, convolutional neural networks (CNNs) have proven to be powerful tools for a broad range of computer vision tasks. However, training a CNN from scratch is difficult because it requires a large amount of labeled training data, which remains a challenge in medical imaging domain. To this end, deep transfer learning (TL) technique is widely used for many medical image tasks. In this paper, we propose a novel multisource transfer learning CNN model for lymph node detection. The mechanism behind it is straightforward. Point‐wise (1 × 1) convolution is used to fuse multisource transfer learning knowledge. Concretely, we view the transferred features as priori domain knowledge and 1 × 1 convolutional operation is implemented after pre‐trained convolution layers to adaptively combine the transfer information for target task. In order to learn non‐linear transferred features and prevent over‐fitting, we present an encode process for the pre‐trained convolution kernels. At last, based on convolutional factorization technique, we train the proposed CNN model and the encoder process jointly, which improves the feasibility of our approach. The effectiveness of the proposed method is verified on lymph node (LN) dataset: 388 mediastinal LNs labeled by radiologists in 90 patient CT scans, and 595 abdominal LNs in 86 patient CT scans for LN detection. Our method demonstrates sensitivities of about 85%/71% at 3 FP/vol. and 92%/85% at 6 FP/vol. for mediastinum and abdomen respectively, which compares favorably to previous methods. [ABSTRACT FROM AUTHOR]

The cataract is the most common cause of severe vision impairment or blindness worldwide. A periodical diagnosis is recommended in order to prevent cataract severity, where screening might be feasibly ensured through fundus images. In this paper, we propose a CAD system to efficiently grade the cataract from fundus images. For such a need, an ensemble learning framework is put forward where the knowledge of three convolutional deep neural networks is stacked in order to perform an efficient cataract prediction. The main contributions of this work are given as follows: (1) Preprocessing and data augmentation of fundus images are carried out to ensure the robustness of the cataract grading; (2) The well‐known DL architectures (Inception‐V3, MobileNet‐V2 and NasNet‐Mobile) are fine‐tuned and learned as base classifiers; (3) An Extreme Learning Machine (ELM) is performed as a meta classifier to stack the predictions of base classifiers. The evaluation is conducted using a dataset of 590 fundus images selected from two public databases. The suggested framework achieves 94.07% accuracy, 94.37% sensitivity, 93.62% specificity, 95.71% precision and 95.04% F‐measure for cataract grading. The experimentation proves that the proposed framework successfully grades fundus images into cataract severity. Moreover, stacking ensemble learning allows achieving a performance that significantly surpasses the ones realized by each DL architecture, applied separately. [ABSTRACT FROM AUTHOR]

Skin cancer is a common type of malignant tumor that poses a serious threat to patients' lives and health, especially melanoma. It may spread to other body parts, resulting in serious complications and death. In the medical field, accurate identification of skin lesion images is crucial for diagnosing different diseases. However, due to the similarity between different skin lesions, it brings some challenges to medical diagnosis. In this paper, a novel Ensemble Learning Model (EL‐DLOA) based on deep learning and optimization algorithms is proposed, which uses four different deep neural network architectures to generate confidence levels for classes, and optimization algorithms are used to integrate these confidence levels to make the final predictions. To ensure the model's accuracy and reliability, it is first trained using three different learning rates to find the best classification performance of the model. Then, a new search method based on the grey wolf optimization algorithm is proposed to enhance the grey wolf search efficiency. The method improves the search mechanism by changing the grey wolf's individual position through random perturbation or adaptive mutation, which solves the problem that the grey wolf algorithm is easy to fall into local optimum. Finally, four different ensemble strategies are used to reduce individual model bias in the classification process. The proposed model is trained and evaluated using the publicly available dataset HAM10000. The experimental results show that the improved grey wolf optimization algorithm effectively avoids the premature convergence problem and improves the search combination efficiency. Furthermore, in the ensemble methods, the adaptive weight average ensemble strategy effectively improves the classification performance, yielding accuracy, precision, recall, and F1 scores of 0.888, 0.837, 0.897, and 0.862, respectively. These metrics show varying degrees of improvement over the best performing single model. In general, the results indicate that the proposed method achieves high accuracy and practicality in skin lesion classification. Our model shows excellent performance in comparison with other existing models, which makes it significant for research and application in dermatology diagnosis. [ABSTRACT FROM AUTHOR]

Glaucomatous optic neuropathy is the preeminent cause of incurable vision impairment and blindness across the world. Manual interpretation of the pathological structures in fundus images is time‐consuming and requires the expertise of a competent specialist. With the development of deep learning approaches, automated glaucoma diagnosis is easy and effective for larger screening. Convolutional neural networks, in particular, have emerged as a promising choice for glaucoma detection from fundus images due to their remarkable success in image classification. Transferring the optimized weights from a pre‐trained model expedites and simplifies the training process of deep neural network. In this paper, a deep ensemble model using the stacking ensemble learning technique is developed to attain the optimum performance for the classification of glaucomatous and normal images. Thirteen pre‐trained models such as Alexnet, Googlenet, VGG‐16, VGG‐19, Squeezenet, Resnet‐18, Resnet‐50, Resnet‐101, Efficientnet‐b0, Mobilenet‐v2, Densenet‐201, Inception‐v3, and Xception are implemented. Their performance is compared in 65 different configurations, comprising 13 CNN architectures and five various classification approaches. A two‐stage ensemble selection technique is proposed to select the optimal configurations. Selected configurations are pooled using a probability averaging technique. The final classification is performed using an SVM classifier. In this work, publicly available databases are modified (such as: DRISHTI‐GS1‐R, ORIGA‐R, RIM‐ONE2‐R, LAG‐R, and ACRIMA‐R) based on oversampling data‐level technique for validating the performance of deep ensemble model. Ensembling the best configurations reports an overall classification accuracy of 93.4%, 79.6%, 91.3%, 99.5%, and 99.6% in DRISHTI‐GS1‐R, ORIGA‐R, RIM‐ONE2‐R, ACRIMA‐R, and LAG‐R databases, respectively. [ABSTRACT FROM AUTHOR]

The syndrome called COVID‐19 which was firstly spread in Wuhan, China has already been declared a globally "Pandemic." To stymie the further spread of the virus at an early stage, detection needs to be done. Artificial Intelligence‐based deep learning models have gained much popularity in the detection of many diseases within the confines of biomedical sciences. In this paper, a deep neural network‐based "LiteCovidNet" model is proposed that detects COVID‐19 cases as the binary class (COVID‐19, Normal) and the multi‐class (COVID‐19, Normal, Pneumonia) bifurcated based on chest X‐ray images of the infected persons. An accuracy of 100% and 98.82% is achieved for binary and multi‐class classification respectively which is competitive performance as compared to the other recent related studies. Hence, our methodology can be used by health professionals to validate the detection of COVID‐19 infected patients at an early stage with convenient cost and better accuracy. [ABSTRACT FROM AUTHOR]

Cancer grade is an indicator of the aggressiveness of cancer. It is used for prognosis and treatment decisions. Conventionally cancer grading is performed manually by experienced pathologists via microscopic examination of pathology slides. Among the three factors involved in breast cancer grading (mitosis count, nuclear atypia, and tubule formation), mitotic cell counting is the most challenging task for pathologists. It is possible to automate this task by applying computational algorithms on pathology slides images. Lack of sufficiently large datasets and class imbalance between mitotic and non‐mitotic cells in slide images are the two major challenges in developing effective deep learning‐based methods for mitosis detection. In this paper, we propose a new approach and a method based on that to address these challenges. The high training data requirement of the advanced deep neural network is met by combining two datasets from different sources after a color‐normalization process. Class imbalance is addressed by the augmentation of the mitotic samples in a context‐preserving manner. Finally, a customized convolutional neural network classifier is used to classify the candidate cells into the target classes. We have used the publicly available datasets MITOS‐ATYPIA and MITOS for the experiments. Our method outperforms most of the recent methods that are based on independent datasets and at the same time offers adaptability to the combination of datasets from different sources. [ABSTRACT FROM AUTHOR]

This research paper shows an effective deformable complex 3D image reconstruction and image synthesis technique by consolidating needed high‐level features from convolutional Neural Network (CNN) system. By recognize inherent deep feature representations in image patches for morphological changes in medicinal imaging information discovery. Various performance measurements, High Frequency Error Norm (HFEN), Mean Squared Error MSE, peak Signal‐to‐noise‐ratio (PSNR), Structural Similarity Index (SSI), are utilized to inspect different dataset. As presented in the paper outcomes, the proposed method can accomplish predominant performance compared with other cutting‐edge techniques with either low or high‐level features in terms of the synthesis and reconstruction rate. The proposed deep learning algorithm has a training time of 5 seconds with 0.97 SSI and 0.15 HFEN. In all investigations, the outcome shows that the proposed image synthesis and reconstruction framework reliably exhibited progressively precise outcomes when contrasted with best in class. [ABSTRACT FROM AUTHOR]

Ultrasonography AKA diagnostic sonography is a noninvasive imaging technique that allows the analysis of an organic structure, thanks to the ultrasonic waves. It is a valuable diagnosis method and is also seen as the evidence‐based diagnostic method for thyroid nodules. The diagnosis, however, is visually made by the practitioner. The automatic discrimination of benign and malignant nodules would be very useful to report Thyroid Imaging Reporting. In this paper, we propose a fine‐tuning approach based on deep learning using a Convolutional Neural Network model named resNet‐50. This approach allows improving the effectiveness of the classification of thyroid nodules in ultrasound images. Experiments have been conducted on 814 ultrasound images and the results show that our proposed approach dramatically improves the accuracy of the classification of thyroid nodules and outperforms The VGG‐19 model. [ABSTRACT FROM AUTHOR]

Visual interpretation of chest X‐rays (CXRs) is tedious and prone to error. Significant amount of time is spent by the radiologist in differentiating normal from abnormal CXRs and in identifying the location and type of abnormalities. An assistance tool for automatically classifying normal and different types of abnormal CXRs can facilitate the diagnosis and potentially save time costs. In this paper, a novel hybrid model having concatenation of Visual Geometry Group (VGG19) network and Entropy features as a modified deep convolutional neural network (DCNN) architecture, called VEntNet, is proposed for the automated multi‐class categorization of CXR images into normal, coronavirus disease (COVID), tuberculosis (TB), viral pneumonia, and bacterial pneumonia. The VEntNet model implemented consists of deep features extraction from convolutional layers of VGG19 network which are then concatenated with hand‐crafted entropy features extracted from CXRs. The concatenated features are then fed to the fully connected (FC) layers for performing multi‐class categorization using Softmax activation function. The performance of proposed VEntNet model is compared with other DCNNs with and without the hybrid approach for categorization of closely related lung pathologies and normal CXR images. Our proposed VEntNet achieved accuracies of 98.78% and 90.96%, respectively, for four and five‐class classification of CXRs. Thus, it is demonstrated that among the different DCNNs, our VEntNet outperformed in four‐class CXR categorization tasks. The proposed model can potentially save time by facilitating the screening of CXRs to identify those with abnormalities present as well as to categorize the abnormalities. [ABSTRACT FROM AUTHOR]

Today, all scientific advancements related to medical image processing aim to develop a unique computational model. The latter will mimic the way humans interpret images. In the present paper, we propose a formal approach biologically inspired by the human natural vision system's mechanisms. To that end, we use the spiking neural network model for edge detection in brain MRI images. The optimal results provided by this last step increase performance, and facilitate the process of anomaly detection. For that, we have developed a tool called Edge and Anomaly Detection of Brain MRI Images in Distributed Environment (EADBMIDE). It is tested on an MRI brain tumour dataset, which shows the effectiveness of the proposed methods. Each stage in this tool is compared separately with similar approaches in the literature. The obtained results show a significant improvement, making this a recommended tool for edge and anomaly detection methods in MRI images. [ABSTRACT FROM AUTHOR]

The application of deep transfer learning techniques has been successful in developing accurate systems for brain tumour classification on large‐scale medical image databases. For small databases, feature learning by deep neural networks is not robust. The systems based on domain‐specific hand‐crafted features have limited accuracy. In this paper, the authors focus on developing accurate models that could be trained effectively using a smaller number of data samples. A siamese neural network (SNN) is designed to extract features from brain magnetic resonance imaging (MRI) images. The SNN is realised using a 3‐layer, fully connected neural network. The designed SNN has lesser complexity and fewer parameters than deep transfer‐learned convolutional neural networks (CNN). A nearest neighbourhood analysis, using Euclidean and Mahalanobis distances, is conducted on the SNN encoded feature space. The encoded feature space is two dimensional, such that the neighbourhood analysis is computationally less intensive. For the neighbourhood analysis, a k‐nearest neighbour (k‐NN) model is utilised. The proposed method is evaluated using three publicly available datasets, namely, Radiopaedia, Harvard and Figshare repositories. The respective classification accuracy on cross‐validation is 92.6%, 98.5% and 92.6%. Other metrics used for the performance evaluation include F‐score, Specificity and balanced accuracy. The underlying network architecture and the design choice of network layers allow the implementation of the SNN in environments with low computational resources. The SNN features are found to be more effective than the hand‐designed features, and the deep transfer learned features for the stated problem. [ABSTRACT FROM AUTHOR]

Breast cancer is caused by the abnormal and rapid growth of breast cells. An early diagnosis can ensure an easier and effective treatment. A mass in the breast is a significant early sign of breast cancer, even though differentiating the cancerous mass's tissue from normal tissue for diagnosis is a difficult task for radiologists. The development of computer‐aided detection systems in recent years has led to nondestructive and efficient cancer diagnostic techniques. This paper proposes a comprehensive method to locate the cancerous region in the mammogram image. This method employs image noise reduction, optimal image segmentation based on the convolutional neural network, a grasshopper optimization algorithm, and optimized feature extraction and feature selection based on the grasshopper optimization algorithm, thereby improving precision and decreasing the computational cost. This method was applied to the Mammographic Image Analysis Society Digital Mammogram Database and Digital Database for Screening Mammography breast cancer databases and the simulation results were compared with 10 different state‐of‐the‐art methods to analyze the proposed system's efficiency. Final results showed that the proposed method had 96% Sensitivity, 93% Specificity, 85% PPV, 97% NPV, 92% accuracy, and better efficiency than other traditional methods in terms of Sensitivity, Specificity, PPV, NPV, and Accuracy. [ABSTRACT FROM AUTHOR]

This paper presents an intelligent system for gastrointestinal polyp detection in endoscopic video. Video endoscopy is a popular diagnostic modality in assessing the gastrointestinal polyps. But the accuracy of diagnosis mostly depends on doctors' experience that is crucial to detect polyps in many cases. Computer‐aided polyp detection is promising to reduce the miss detection rate of polyp and thus improve the accuracy of diagnosis results. The proposed method illustrates an automatic system based on a new color feature extraction scheme as a support for gastrointestinal polyp detection. The scheme is the combination of color empirical mode decomposition features and convolutional neural network features extracted from video frames. The features are fed into a linear support vector machine to train the classifier. Experiments on standard public databases show that the proposed scheme outperforms the previous conventional methods, gaining accuracy of 99.53%, sensitivity of 99.91%, and specificity of 99.15%. [ABSTRACT FROM AUTHOR]

Imaging based sensitive clinical diagnosis is critically depending on image quality. In this article, the problem of enhancing fundus images is addressed by a novel fusion technique. The proposed approach utilizes the representation capability of wavelet transform and the learning ability of artificial neural networks. In this approach, input images are decomposed into wavelet transform followed by appropriate feature extraction for training of neural networks to obtain fused image. To ensure homogeneity, it employs consistency verification for minimizing the fusion artifacts. The visual and quantitative performance of the proposed approach is assessed using a number of experiments performed on the standard datasets of DRIVE and DRION‐DB. The experimental results demonstrate that the proposed fusion technique offers high average structural similarity of "0.99." The proposed approach outperforms state‐of‐the‐art techniques which validates its effectiveness. The developed approach might be applied by the clinical diagnosis system for fundus related diseases. [ABSTRACT FROM AUTHOR]

Accurately classify teeth category is important in further dental diagnosis. Analyzing huge dental data, that is, identifying the teeth category, is often a hard task. Current automatic methods are based on computer vision and deep learning approaches. In this study, we aimed to classify the teeth category into four classes: incisor, canine, premolar, and molar. Cone beam computed tomography was used to collect the data. We proposed a seven‐layer deep convolutional neural network with global average pooling to identify teeth category. Data augmentation method was used to enlarge the size of training dataset. The results showed the sensitivities of incisor, canine, premolar, and molar teeth are 88%, 86%, 84%, and 90%, respectively. The average sensitivity is 87.0%. We validated max pooling gives better results than average pooling. Our method is better than three state‐of‐the‐art approaches. [ABSTRACT FROM AUTHOR]

ABSTRACT In recent decades, region growing methods in image segmentation plays a vital role in medical image processing. Nonetheless, the method needs more advancement to cope up with the images of current acquisition devices. This paper attempts to solve the problem of maintaining diversity among wide image specifications by optimizing the threshold. In order to accomplish this, we introduce a hybrid framework of Artificial Bee Colony and Genetic Algorithm in a region growing variant, in which gradient and intensity levels are used for segmentation. Eventually, the proposed work is subjected to classify the tumor and non-tumor images, followed by the segmentation of tumor region in MRI images. Classification methodologies such as feed forward back propagation neural network, radial basis neural network, support vector machine with quadratic programming and adaptive neuro-fuzzy inference system are considered for experimental investigation in which support vector machine with quadratic programming is found to be dominant than other methodologies. Proposed region growing method outperforms well on the classified image, when compared with the region growing variant and standard region growing method. The results are demonstrated with the aid of wide set of performance measures. © 2014 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 24, 129-137, 2014 [ABSTRACT FROM AUTHOR]

Deep learning is frequently used to classify medical images. Surgeons may know the type of tumor before doing surgery on a patient. Transfer learning was used to alleviate the overfitting issue of deep networks in classification since the training samples, such as a brain MRI dataset, were insufficient. To overcome this issue, We introduce a new deep‐learning methodology for the categorization of MRI brain tumor images. This method combines a unique data augmentation model with modified AlexNet and network‐based deep transfer learning. We used Lipschitz‐based data augmentation on a dataset, and the output of the augmentation model was fed into a modified AlexNet that uses network‐based deep transfer learning to extract features from a dataset. The proposed model is trained and tested using the BraTS 2020 and Figshare datasets. The proposed model's performance is assessed using sensitivity, specificity, accuracy, precision, F1‐score, and MCC. The proposed model yields superior results. [ABSTRACT FROM AUTHOR]

Classification of brain hemorrhage computed tomography (CT) images provides a better diagnostic implementation for emergency patients. Attentively, each brain CT image must be examined by doctors. This situation is time‐consuming, exhausting, and sometimes leads to making errors. Hence, we aim to find the best algorithm owing to a requirement for automatic classification of CT images to detect brain hemorrhage. In this study, we developed OzNet hybrid algorithm, which is a novel convolution neural networks (CNN) algorithm. Although OzNet achieves high classification performance, we combine it with Neighborhood Component Analysis (NCA) and many classifiers: Artificial neural networks (ANN), Adaboost, Bagging, Decision Tree, K‐Nearest Neighbor (K‐NN), Linear Discriminant Analysis (LDA), Naïve Bayes and Support Vector Machines (SVM). In addition, Oznet is utilized for feature extraction, where 4096 features are extracted from the fully connected layer. These features are reduced to have significant and informative features with minimum loss by NCA. Eventually, we use these classifiers to classify these significant features. Finally, experimental results display that OzNet‐NCA‐ANN excellent classifier model and achieves 100% accuracy with created Dataset 2 from Brain Hemorrhage CT images. [ABSTRACT FROM AUTHOR]

Skin cancer detection through dermoscopy images has remained challenging due to higher inter‐class uniformity and intra‐class diversity. Deep convolutional neural networks (CNNs) have recently obtained remarkable attention for automated skin cancer classification; however, most of these methods extract features from the global image of high resolution. One of the major drawbacks of these methods is the downscaling of input images to a low resolution, which leads to information loss. Moreover, the lack of a vast number of dermoscopy images is a concern. To overcome these issues and improve the classification accuracy, we propose a novel method using patch‐based local deep feature extraction. In the proposed method, the features are extracted from different patches of a dermoscopy image using a pre‐trained CNN model and are fused to preserve fine details. The kernel principal component analysis is then employed to select the prominent features, and a feed‐forward neural network is finally used to detect skin cancer. The approach is validated using two benchmark datasets: ISIC 2016 and ISIC 2017. The experimental results show that the suggested method achieves promising results in comparison with state‐of‐the‐art approaches. Moreover, a comparative analysis is made among contemporary pre‐trained CNN models. [ABSTRACT FROM AUTHOR]

Several deep learning techniques are utilized for classification of the masses in mammogram images. But the existing method doesnot provide sufficient accuracy. for breast masses classification in mammogram images. In this manuscript, an efficient breast cancer image classification framework utilizing the deep belief network (DBN) through chaotic krill herd optimization (CKHO) algorithm for classification of masses in mammogram images is proposed. Initially the input mammogram images are pre‐processed by altered phase preserving dynamic range compression (APPDRC) method for removing the unwanted noise and artifacts. Then these pre‐processed images are assumed with DBN for classifying that mass in the mammogram images into normal, benign, and malignant lesions. Generally, DBN does not reveal any acceptance of optimization techniques for computing optimal parameters that guarantee an accurate classification. Therefore in this work, proposed CKHO algorithm is employed for optimizing weight parameters of the self‐attention convolutional neural network (SACNN). The simulation process is performed under MATLAB platform. Finally, the proposed DBN with chaotic krill herd optimization algorithm (DBN‐CKHO) attains high accuracy 44.5%, 33.42%, 55.23%, 62.35%, and 43.42% when compared with the existing method such as extreme learning machine classifier with moth flame optimization (ELMC‐MFO), Kernel extreme learning machine classifier with Chaotic salp swarm algorithm (KELMC‐CSSA), Extreme learning machine classifier with fruit fly optimization algorithm (ELMC‐FOA), Kernel extreme learning machine classifier with grasshopper optimization algorithm (KELMC‐GOA) and deep neural network with non‐dominated sorting genetic algorithm‐based classification approach. [ABSTRACT FROM AUTHOR]

Interstitial lung diseases (ILDs) are adverse disorders, damaging the lung tissues, thus making timely diagnosis imperative. To counter the scarcity of publicly available high‐resolution computed tomography (HRCT) data, architecture employing HRCT and x‐ray data have been proposed for diagnosing ILDs. A model is first trained to diagnose three ILDs and a healthy lung from x‐ray data and then with a small amount of HRCT data of the same four classes. We introduce an EfficientNet+AlexNet model and a custom deep convolutional neural network and compare their performances with different weight initialization at the start of x‐ray image training. The EfficientNet+AlexNet model initialized with ImageNet weights performed best on the x‐ray dataset and was later used for domain adaptation. We also compare our model's performance to a single pre‐trained EfficientNetB0 model (trained on the same HRCT data). Our model gave an accuracy of 97.4% on the testing dataset, a notable increase in the performance compared to the recently proposed methodologies. The experimental results and graphical plots depict the superiority of domain adaptation and the potentials of weights that are a starting point for training the models. [ABSTRACT FROM AUTHOR]

Breast cancer is detected in one out of eight females worldwide. Principally biomedical image processing techniques work with images captured by a microscope and then analyzed with the help of different algorithms and methods. Instead of microscopic image diagnosis, machine learning algorithms are now incorporated to detect and diagnose therapeutic imagery. Computer‐aided mechanisms are used for better efficiency and reliability compared with manual pathological detection systems. Machine learning algorithms detect tumors by extracting features through a convolutional neural network (CNN) and then classifying them using a fully connected network. As Machine learning does not require prior expertise, it is profoundly used in biomedical imaging. This article has customized a convolutional neural network by mathematical modeling of a proposed activation function. We have obtained an appreciable prediction accuracy of up to 99%, along with a precision of 0.97. [ABSTRACT FROM AUTHOR]

In this study, we present a novel automatic segmentation method using a neural network model named GAN‐segNet, which can not only identify brain tumors from MRI images but also accurately delineate intratumor regions. Since brain tumors with varying shapes and sizes can appear anywhere in the brain and image quality and contrast of MRI could be inadequate, automatic segmentation remains challenging despite its importance in the clinical workflow. The proposed GAN‐segNet is an innovative modification of the Generative Adversarial Network (GAN) and can efficiently and accurately segment brain tumors. One key innovation of our GAN model is an autoencoder learning representation of input data that were added to the generative network of the above‐mentioned GAN. By doing so, information extracted through convolution operations can be meaningfully regularized. As a result, the scales of extracted features can be controlled by the added autoencoder to preserve detail. Additionally, we propose an innovative loss function based on the concept of focal loss to effectively mitigate the impact of label imbalance. The above‐mentioned combination enables the proposed GAN‐segNet model to improve the segmentation of small intratumor region(s). We demonstrate the proposed method using MRI data available from a public database, that is, Brain Tumor Segmentation Challenge 2018 database (BRATS 2018). Using the proposed GAN‐segNet model, the average Dice scores were 0.8280, 0.9022, and 0.814 for segmenting enhancing tumor core, whole tumor, and tumor core, respectively. Furthermore, positive predictive values for segmenting enhanced tumor core, whole tumor, and tumor core were 0.8496, 0.9270, and 0.8610, respectively. [ABSTRACT FROM AUTHOR]

Alzheimer's disease is a progressive neurodegenerative fatal disease characterized by a decrease in mental functions. Although there is no definitive treatment for the disease, there are some treatment methods that delay the course of the disease in case of early diagnosis. Therefore, early diagnosis and classification of the disease are important to determine the most appropriate treatment. The most commonly used method for imaging the brain with a high soft‐tissue resolution is magnetic resonance imaging (MRI). Brain MRI help in the diagnosis of Alzheimer's disease with some specific imaging findings. In this study, we aimed to classify Alzheimer's disease in brain MRI using machine learning architectures. An mRMR‐based hybrid CNN was proposed in the study. First, features of MRI in Darknet53, InceptionV3, and Resnet101 models were extracted. These extracted features were concatenated. Then the obtained features were optimized using the mRMR method. SVM and KNN classifiers were used to classify the optimized features. The accuracy value obtained in the proposed model was 99.1%. [ABSTRACT FROM AUTHOR]

Image restoration is aimed to recover the original scene from its degraded version. This paper presents a new method for image restoration. In this technique, an evaluation function which combines a scaled residual with space-variant regularization is established and minimized using a Hopfield network to obtain a restored image from a noise corrupted and blurred image. Simulation results demonstrate that the proposed evaluation function leads to a more efficient restoration process which offers a fast convergence and improved restored image quality. © 2003 Wiley Periodicals, Inc. Int J Imaging Syst Technol 12, 247–253, 2002; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/ima.10034 [ABSTRACT FROM AUTHOR]

This paper explores a novel neural network-based nonlinear filter that has the ability to remove mixed noises and sharpen the edges in noise-corrupted digital images. The noise is assumed to be a mixture of both Gaussian and impulse types. Initially, a nonlinear filter is used to reduce the noise. The smoothed image is then combined with the output of an edge detector using a synthesizer to provide the effect of noise reducing and edge sharpening. The smoother and synthesizer are designed by using layered neural networks. Simulation results show that the proposed filter can effectively remove the mixed Guassian and impulsive noises and sharpen the edges. It can adapt itself to the various noise environments by learning during the training process. © 2002 Wiley Periodicals, Inc. Int J Imaging Syst Technol 12, 56–62, 2002; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/ima.10009 [ABSTRACT FROM AUTHOR]

A new neural network algorithm based on the counter-propagation network (CPN) architecture, named MVL-CPN, is proposed in this paper for bidirectional mapping and recognition of multiple-valued patterns. The MVL-CPN is capable of performing a mathematical mapping of a set of multiple-valued vector pairs by self-organization. The use of MVL-CPN reduces considerably the number of nodes required for the input layers as well as the number of synaptic weights compared to the binary CPN. The training of the network is stable because all synaptic weights are monotonically nonincreasing. The bidirectional mapping and associative recall features of the MVL-CPN are tested by using various sets of quaternary patterns. It is observed that the MVL-CPN can converge within three or four iterations. The high-speed convergence characteristics of the network can lead to the possibility of using this architecture for real-time applications. An important advantage of the proposed type of neural network is that it can be implemented in VLSI with reduced number of neurons and synaptic weights when compared to a larger binary network needed for the same application. © 2000 John Wiley & Sons, Inc. Int J Imaging Syst Technol 11, 125–129, 2000 [ABSTRACT FROM AUTHOR]

This paper proposes a new method for reducing the number of colors in an image. The proposed approach uses both the image color components and local image characteristics to feed a Kohonen self-organized feature map (SOFM) neural network. After training, the neurons of the output competition layer define the proper color classes. The final image has the dominant image colors and its texture approaches the image local characteristics used. To speed up the entire algorithm and reduce memory requirements, a fractal scanning subsampling technique can be used. The method is applicable to all types of color images and can be easily extended to accommodate any type of spatial characteristics. Several experimental and comparative results are presented. © 1999 John Wiley & Sons, Inc. Int J Imaging Syst Technol 10, 404–409, 1999 [ABSTRACT FROM AUTHOR]

This paper presents a method for guiding an autonomous underwater vehicle (AUV) during sea bottom inspection missions. The vehicle is equipped with several sensors (optical, sonar, acoustic) and is able to detect and follow a pipeline placed on the sea bottom. Neural networks and geometric reasoning methods are integrated to perform a real-time identification of pipeline borders in a complex underwater environment. Different scenarios characterized by both obstacles and/or artifacts (due to reflections of artificial light sources used by the vehicle to illuminate the scene) have been considered. Results focus on pipeline detection accuracy and on AUV missions in the absence or presence of down stream and/or obstacles. © 1999 John Wiley & Sons, Inc. Int J Imaging Syst Technol 10, 385–396, 1999 [ABSTRACT FROM AUTHOR]

Diabetic retinopathy (DR) accounts in eye‐related disorders due to accumulated damage to small retinal blood vessels. Automated diagnostic systems are effective in early detection and diagnosis of severe eye complications by assisting the ophthalmologists. Deep learning‐based techniques have emerged as an advancement over conventional techniques based on hand‐crafted features. The authors have proposed a Quadrant‐based automated DR grading system in this work using Inception‐V3 deep neural network to extract small lesions present in retinal fundus images. The grading efficiency of the proposed architecture is improved utilizing image enhancement and optical disc removal pipeline along with data augmentation stage. The proposed system yields accuracy of 93.33% with minimized cross‐entropy loss of 0.291. Capability of proposed system is demonstrated experimentally to provide efficient DR diagnosis. The diagnosis ability of the proposed architecture is demonstrated by state‐of‐the‐art comparison with other mainstream convolution neural network models and a maximum improvement of 14.33% is observed. [ABSTRACT FROM AUTHOR]

The brain tumor detection is a highly complicated but significant task. The early detection of a brain tumor can increase the survival rate of an individual by providing proper treatment. This work proposes a computer‐aided diagnostic method for brain tumor detection using fractional wavelet transform (FrDWT) with different values of alpha (α) ranging from (0.1‐1), histogram‐based various local feature descriptors, feature selectors, and two classification methods, that is, support vector machine (SVM) as well as artificial neural network (ANN). The brain MR images dataset is taken from BraTS 2015, e‐health laboratory, and Harvard Medical School. The FrDWT and the local feature descriptors used are combined to extract features. Some of the features are selected using Eigenvector centrality and Laplacian Score techniques. The selected features are trained and classified by the two classifiers, SVM and ANN. It is a type of binary classification, so the labels provided to the classifier are named "normal" and "abnormal." The performance is estimated using parameters like accuracy, sensitivity, precision, specificity, and F1 score. The results of FrDWT are compared with conventional discrete wavelet transform (DWT), and it is observed that FrDWT outperforms DWT at alpha (α) values lower than 0.5. [ABSTRACT FROM AUTHOR]

Computer Assisted Diagnosis (CAD) is an effective method to detect lung cancer from computed tomography (CT) scans. The development of artificial neural network makes CAD more accurate in detecting pathological changes. Due to the complexity of the lung environment, the existing neural network training still requires large datasets, excessive time, and memory space. To meet the challenge, we analysis 3D volumes as serialized 2D slices and present a new neural network structure lightweight convolutional neural network (CNN)‐long short‐term memory (LSTM) for lung nodule classification. Our network contains two main components: (a) optimized lightweight CNN layers with tiny parameter space for extracting visual features of serialized 2D images, and (b) LSTM network for learning relevant information among 2D images. In all experiments, we compared the training results of several models and our model achieved an accuracy of 91.78% for lung nodule classification with an AUC of 93%. We used fewer samples and memory space to train the model, and we achieved faster convergence. Finally, we analyzed and discussed the feasibility of migrating this framework to mobile devices. The framework can also be applied to cope with the small amount of training data and the development of mobile health device in future. [ABSTRACT FROM AUTHOR]

Background: Lung carcinoma is the leading cause of 1.76 million deaths worldwide. GLOBOCAN 2018 report says lung cancer occupies the first position in terms of incidence and mortality rate. Reasons include limited access to timely diagnosis and treatment. Objective: This research work presents the viability of using convolutional neural network (CNN) for lung carcinoma detection. The proposed network automatically detects the lung carcinomas tissues through transfer learning without the difficulty of specifying features for image classification. Subjects and methods: The study involves lung CT images of 12 male and 4 female subjects, aging between 35 and 77 years. These images are obtained in Bitmap image format with a resolution of 512 × 512. Two cases namely healthy and carcinoma are taken for study. Carcinoma cases include poorly differentiated carcinoma, moderately differentiated carcinoma. The training data consists of 800 lung CT slices, validation set consists of 100 CT images, and test data consist of 100 images, respectively. Results: Experimental results demonstrate the VGG16 and VGG 19 network implementation with the area under the receiver operating characteristics of 0.930 and 0.90, respectively. VGG19 compete well with a sensitivity and specificity of 80% and 100% compared to VGG16 with 98% and 88%, respectively. Conclusion: Hence, the implementation of VGG16 and VGG19 with good accuracy proves that CNN used for lung carcinoma detection leading to timely diagnosis and treatment may decrease the mortality rate. [ABSTRACT FROM AUTHOR]

Manual detection of small uncalcified pulmonary nodules (diameter <4 mm) in thoracic computed tomography (CT) scans is a tedious and error‐prone task. Automatic detection of disperse micronodules is, thus, highly desirable for improved characterization of the fatal and incurable occupational pulmonary diseases. Here, we present a novel computer‐assisted detection (CAD) scheme specifically dedicated to detect micronodules. The proposed scheme consists of a candidate‐screening module and a false positive (FP) reduction module. The candidate‐screening module is initiated by a lung segmentation algorithm and is followed by a combination of 2D/3D features‐based thresholding parameters to identify plausible micronodules. The FP reduction module employs a 3D convolutional neural network (CNN) to classify each identified candidate. It automatically encodes the discriminative representations by exploiting the volumetric information of each candidate. A set of 872 micro‐nodules in 598 CT scans marked by at least two radiologists are extracted from the Lung Image Database Consortium and Image Database Resource Initiative to test our CAD scheme. The CAD scheme achieves a detection sensitivity of 86.7% (756/872) with only 8 FPs/scan and an AUC of 0.98. Our proposed CAD scheme efficiently identifies micronodules in thoracic scans with only a small number of FPs. Our experimental results provide evidence that the automatically generated features by the 3D CNN are highly discriminant, thus making it a well‐suited FP reduction module of a CAD scheme. [ABSTRACT FROM AUTHOR]

Bone age assessment based on hand X‐ray imaging is important in pediatry medicine. At present, prediction of bone age is mainly performed by the manual comparison with the existing atlas. To develop an automatic regression framework based on deep learning with high performance and efficiency. A landmark‐based multi‐region convolutional neural networks for automatic bone age assessment based on left hand X‐ray images was proposed. The deep alignment network localized multiple landmarks distributed over the hand, and cropped the local regions to establish the multi‐region ensemble convolutional neural networks with different sub‐network combinations. The modified loss function and the optimized bone sub‐regions were applied to train the networks. The experiments on Digital Hand Atlas Database revealed that the mean absolute error of bone age assessment was 0.52 ± 0.25 years. It is the first study to predict bone age using deep learning methods throughout the entire process including image preprocessing, landmark localization and bone age predication. The proposed method outperformed most of the existing state‐of‐the‐art deep learning methods and achieved good results compared with the expert's experience. It can improve the efficiency of the medical doctors while minimizing the subjective errors. [ABSTRACT FROM AUTHOR]

Computer‐aided diagnosis (CAD) is a computerized way of detecting tumors in MR images. Magnetic resonance imaging (MRI) has been generally used in the diagnosis and detection of pancreatic tumors. In a medical imaging system, soft tissue contrast and noninvasiveness are clear preferences of MRI. Inaccurate detection of tumor and long time consumption are the disadvantages of MRI. Computerized classifiers can greatly renew the diagnosis activity, in terms of both accuracy and time necessity by normal and abnormal images, automatically. This article presents an intelligent, automatic, accurate, and robust method to classify human pancreas MRI images as normal or abnormal in terms of pancreatic tumor. It represents the response of artificial neural network (ANN) and support vector machine (SVM) techniques for pancreatic tumor classification. For this, we extract features from MR images of pancreas using the GLCM method and select the best features using JAFER algorithm. These features are analyzed by five classification techniques: ANN BP, ANN RBF, SVM Linear, SVM Poly, and SVM RBF. We compare the results with benchmark data set of MR brain images. The analytical outcome presents that the two best features used to classify the MR images using ANN BP technique have 98% classification accuracy. [ABSTRACT FROM AUTHOR]

The abnormal development of cells in brain leads to the formation of tumors in brain. In this article, image fusion based brain tumor detection and segmentation methodology is proposed using convolutional neural networks (CNN). This proposed methodology consists of image fusion, feature extraction, classification, and segmentation. Discrete wavelet transform (DWT) is used for image fusion and enhanced brain image is obtained by fusing the coefficients of the DWT transform. Further, Grey Level Co-occurrence Matrix features are extracted and fed to the CNN classifier for glioma image classifications. Then, morphological operations with closing and opening functions are used to segment the tumor region in classified glioma brain image. [ABSTRACT FROM AUTHOR]

ABSTRACT To find a better way to screen early lung cancer, motivated by the great success of deep learning, we empirically investigate the challenge of classifying lung nodules in computed tomography (CT) in an end-to-end manner. Multi-view convolutional neural networks (MV-CNN) are proposed in this article for lung nodule classification. Unlike the traditional CNNs, a MV-CNN takes multiple views of each entered nodule. We carry out a binary classification (benign and malignant) and a ternary classification (benign, primary malignant, and metastatic malignant) using the Lung Image Database Consortium and Image Database Resource Initiative database. The results show that, for binary or ternary classifications, the multiview strategy produces higher accuracy than the single view method, even for cases that are over-fitted. Our model achieves an error rate of 5.41 and 13.91% for binary and ternary classifications, respectively. Finally, the receiver operating characteristic curve and t-distributed stochastic neighbor embedding algorithm are used to analyze the models. The results reveal that the deep features learned by the model proposed in this article have a higher separability than features from the image space and the multiview strategies; therefore, researchers can get better representation. © 2017 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 27, 12-22, 2017 [ABSTRACT FROM AUTHOR]

In this article, an efficient and novel approach for video data association is developed. This new method is formulated as a search across the hypotheses space defined by the possible association among tracks and detections, carried out for each frame of a video sequence. The full data association problem in visual tracking is formulated as a combinatorial hypotheses search with a heuristic evaluation function taking into account structural and specific information such as distance, shape, color, etc. To guarantee real-time performance, a time limit is set for the search process explore alternative solutions. This time limit defines the upper bound of the number of evaluations depending on search algorithm efficiency. Estimation distribution algorithms are proposed as an efficient evolutionary computation technique to search in this hypothesis space. Finally, an exhaustive comparison of the performance of alternative algorithms is carried out considering complex representative situations in real video sets. © 2009 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 19, 208–220, 2009 [ABSTRACT FROM AUTHOR]

This article describes the application of a neural network to the segmentation of remote sensing images of multispectral SPOT and fully polarimetric SAR data. The structure of the network is a modified multilayer perception and is trained by the Kalman filter theory. The internal activity of the network is a nonlinear function, while the function at output layer is linearized through the use of a polynomial basis function, thus allowing us employ the theory of Kalman filtering as the learning rule. The network is therefore called the dynamic learning (DL) neural network. It is found that, when applied to SPOT and SAR data, the DL neural network gives a good segmentation results, while the learning rate is very promising compared to the standard backpropagation network and other fast-learning networks. In particular, for polarimetric SAR data, optimum polarizations for discriminating between different terrains are automatically built in through the use of the Kalman filter technique. The suitability and effectiveness of the proposed DL neural network to the segmentation of remote sensing images is demonstrated. [ABSTRACT FROM AUTHOR]