Deep Learning-Based Skin Lesion Multi-class Classification with Global Average Pooling Improvement

Cancerous skin lesions are one of the deadliest diseases that have the ability in spreading across other body parts and organs. Conventionally, visual inspection and biopsy methods are widely used to detect skin cancers. However, these methods have some drawbacks, and the prediction is not highly accurate. This is where a dependable automatic recognition system for skin cancers comes into play. With the extensive usage of deep learning in various aspects of medical health, a novel computer-aided dermatologist tool has been suggested for the accurate identification and classification of skin lesions by deploying a novel deep convolutional neural network (DCNN) model that incorporates global average pooling along with preprocessing to discern the skin lesions. The proposed model is trained and tested on the HAM10000 dataset, which contains seven different classes of skin lesions as target classes. The black hat filtering technique has been applied to remove artifacts in the preprocessing stage along with the resampling techniques to balance the data. The performance of the proposed model is evaluated by comparing it with some of the transfer learning models such as ResNet50, VGG-16, MobileNetV2, and DenseNet121. The proposed model provides an accuracy of 97.20%, which is the highest among the previous state-of-art models for multi-class skin lesion classification. The efficacy of the proposed model is also validated by visualizing the results obtained using a graphical user interface (GUI).

Near Lossless Compression for 3D Radiological Images Using Optimal Multilinear Singular Value Decomposition (3D-VOI-OMLSVD)

Storage and transmission of high-compression 3D radiological images that create high-quality reconstruction upon decompression are critical necessities for effective and efficient teleradiology. To cater to this need, we propose a near lossless 3D image volume compression method based on optimal multilinear singular value decomposition called "3D-VOI-OMLSVD." The proposed strategy first eliminates any blank 2D image slices from the 3D image volume and uses the selective bounding volume (SBV) to identify and extract the volume of Interest (VOI). Following this, the VOI is decomposed with an optimal multilinear singular value decomposition (OMLSVD) to obtain the corresponding core tensor, factor matrices, and singular values that are compressed with adaptive binary range coder (ABRC), integrated as an entropy encoder. The compressed file can be transferred or transmitted and then decompressed in order to reconstruct the original image. The resultant decompressed VOI is acquired by reversing the above process and then fusing it with the background, using the bound volume coordinates associated with the compressed 3D image. The proposed method performance was tested on a variety of 3D radiological images with different imaging modalities and dimensions using quantitative evaluation metrics such as the compression rate (CR), bit rate (BR), peak signal to noise ratio (PSNR), and structural similarity index (SSIM). Furthermore, we also investigate the impact of VOI extraction on the model performance, before comparing it with two popular compression methods, namely JPEG and JPEG2000. Our proposed method, 3D-VOI-OMLSVD, displayed a high CR value, with a maximum of 37.31, and a low BR, with the lowest reported to be 0.21. The SSIM score was consistently high, with an average performance of 0.9868, while using < 1 second for decoding the image. We observe that with VOI extraction, the compression rate increases manifold, and bit rate drops significantly, and thus reduces the encoding and decoding time to a great extent. Compared to JPEG and JPEG2000, our method consistently performs better in terms of higher CR and lower BR. The results indicate that the proposed compression methodology performs consistently to create high-quality image compressions, and overall gives a better outcome when compared against two state-of-the-art and widely used methods, JPEG and JPEG2000.

Artificial intelligence in bronchopulmonary dysplasia- current research and unexplored frontiers

Provide an overview of bronchopulmonary dysplasia, its definitions, and their shortcomings. Explore the areas where machine learning may be used to further our understanding of bronchopulmonary dysplasia.

CellDrift: inferring perturbation responses in temporally sampled single-cell data

Cells and tissues respond to perturbations in multiple ways that can be sensitively reflected in the alterations of gene expression. Current approaches to finding and quantifying the effects of perturbations on cell-level responses over time disregard the temporal consistency of identifiable gene programs. To leverage the occurrence of these patterns for perturbation analyses, we developed CellDrift (https://github.com/KANG-BIOINFO/CellDrift), a generalized linear model-based functional data analysis method that is capable of identifying covarying temporal patterns of various cell types in response to perturbations. As compared to several other approaches, CellDrift demonstrated superior performance in the identification of temporally varied perturbation patterns and the ability to impute missing time points. We applied CellDrift to multiple longitudinal datasets, including COVID-19 disease progression and gastrointestinal tract development, and demonstrated its ability to identify specific gene programs associated with sequential biological processes, trajectories and outcomes.

Data Augmentation Using Generative Adversarial Networks for Multi-Class Segmentation of Lung Confocal IF Images

The human lung is a complex organ with high cellular heterogeneity, and its development and maintenance require interactive gene networks and dynamic cross-talk among multiple cell types. We focus on the confocal immunofluorescent (IF) images of lung tissues from the LungMAP database to reveal lung development. Using the current state-of-the-art deep learning-based model, the authors consider obtaining accurate multi-class segmentation of lung confocal IF images. One of the primary bottlenecks in using deep Convolutional Neural Network (CNN) models is the lack of availability of large-scale training or ground-truth segmentation labels. Then, we implement the multi-class segmentation with Generative Adversarial Network (GAN) models to expand the training dataset, improve overall segmentation accuracy, and discuss the effectiveness of created synthetic images in the segmentation of IF images. Consequently, experimental results indicated that 15.1% increased the accuracy of six-class segmentation using Mask R-CNN. In particular, the accuracy of our few data was mainly improved by using our proposed method. Therefore, the synthetic dataset can moderate the imbalanced data and be used for expanding the dataset.

COMPUTATIONAL 2D and 3D MEDICAL IMAGE DATA COMPRESSION MODELS

In this world of big data, the development and exploitation of medical technology is vastly increasing and especially in big biomedical imaging modalities available across medicine. At the same instant, acquisition, processing, storing and transmission of such huge medical data requires efficient and robust data compression models. Over the last two decades, numerous compression mechanisms, techniques and algorithms were proposed by many researchers. This work provides a detailed status of these existing computational compression methods for medical imaging data. Appropriate classification, performance metrics, practical issues and challenges in enhancing the two dimensional (2D) and three dimensional (3D) medical image compression arena are reviewed in detail.

DeepImmuno: deep learning-empowered prediction and generation of immunogenic peptides for T-cell immunity

Cytolytic T-cells play an essential role in the adaptive immune system by seeking out, binding and killing cells that present foreign antigens on their surface. An improved understanding of T-cell immunity will greatly aid in the development of new cancer immunotherapies and vaccines for life-threatening pathogens. Central to the design of such targeted therapies are computational methods to predict non-native peptides to elicit a T-cell response, however, we currently lack accurate immunogenicity inference methods. Another challenge is the ability to accurately simulate immunogenic peptides for specific human leukocyte antigen alleles, for both synthetic biological applications, and to augment real training datasets. Here, we propose a beta-binomial distribution approach to derive peptide immunogenic potential from sequence alone. We conducted systematic benchmarking of five traditional machine learning (ElasticNet, K-nearest neighbors, support vector machine, Random Forest and AdaBoost) and three deep learning models (convolutional neural network (CNN), Residual Net and graph neural network) using three independent prior validated immunogenic peptide collections (dengue virus, cancer neoantigen and SARS-CoV-2). We chose the CNN as the best prediction model, based on its adaptivity for small and large datasets and performance relative to existing methods. In addition to outperforming two highly used immunogenicity prediction algorithms, DeepImmuno-CNN correctly predicts which residues are most important for T-cell antigen recognition and predicts novel impacts of SARS-CoV-2 variants. Our independent generative adversarial network (GAN) approach, DeepImmuno-GAN, was further able to accurately simulate immunogenic peptides with physicochemical properties and immunogenicity predictions similar to that of real antigens. We provide DeepImmuno-CNN as source code and an easy-to-use web interface.

On a hybrid lossless compression technique for three-dimensional medical images

In the last two decades, incredible progress in various medical imaging modalities and sensing techniques have been made, leading to the proliferation of three-dimensional (3D) imagery. Byproduct of such great progress is the production of huge volume of medical images and this big data place a burden on automatic image processing methods for diagnostic assistance processes. Moreover, large amount of medical imaging data needs to be transmitted with no loss of information for the purpose of telemedicine, remote diagnosis etc. In this work, we consider a hybrid lossless compression technique with object-based features for three-dimensional (3D) medical images. Our approach utilizes two phases as follows: first we determine the volume of interest (VOI) for a given 3D medical imagery using selective bounding volume (SBV) method, and second the obtained VOI is encoded using a hybrid lossless algorithm using Lembel-Ziv-Welch Coding (LZW) followed by arithmetic coding (L to A). Experimental results show that our proposed 3D medical image compression method is comparable with other existing standard lossless encoding methods such as Huffman Coding, Run Length Coding, LZW, and Arithmetic Coding and obtains superior results overall.

Machine Learning for Detection of Correct Peripherally Inserted Central Catheter Tip Position from Radiology Reports in Infants

BACKGROUND

In critically ill infants, the position of a peripherally inserted central catheter (PICC) must be confirmed frequently, as the tip may move from its original position and run the risk of hyperosmolar vascular damage or extravasation into surrounding spaces. Automated detection of PICC tip position holds great promise for alerting bedside clinicians to noncentral PICCs.

OBJECTIVES

This research seeks to use natural language processing (NLP) and supervised machine learning (ML) techniques to predict PICC tip position based primarily on text analysis of radiograph reports from infants with an upper extremity PICC.

METHODS

Radiographs, containing a PICC line in infants under 6 months of age, were manually classified into 12 anatomical locations based on the radiologist's textual report of the PICC line's tip. After categorization, we performed a 70/30 train/test split and benchmarked the performance of seven different (neural network, support vector machine, the naïve Bayes, decision tree, random forest, AdaBoost, and K-nearest neighbors) supervised ML algorithms. After optimization, we calculated accuracy, precision, and recall of each algorithm's ability to correctly categorize the stated location of the PICC tip.

RESULTS

A total of 17,337 radiographs met criteria for inclusion and were labeled manually. Interrater agreement was 99.1%. Support vector machines and neural networks yielded accuracies as high as 98% in identifying PICC tips in central versus noncentral position (binary outcome) and accuracies as high as 95% when attempting to categorize the individual anatomical location (12-category outcome).

CONCLUSION

Our study shows that ML classifiers can automatically extract the anatomical location of PICC tips from radiology reports. Two ML classifiers, support vector machine (SVM) and a neural network, obtained top accuracies in both binary and multiple category predictions. Implementing these algorithms in a neonatal intensive care unit as a clinical decision support system may help clinicians address PICC line position.

POCASUM : Policy Categorizer and Summarizer Based on Text Mining and Machine Learning

Having control over your data is a right and a duty that every citizen has in our digital society. It is often that users skip entire policies of applications or websites to save time and energy without realizing the potential sticky points in these policies. Due to obscure language and verbose explanations majority of users of hypermedia do not bother to read them. Further, sometimes digital media companies do not spend enough effort in stating their policies clearly which often time can also be incomplete. A summarized version of these privacy policies that can be categorized into the useful information can help the users. To solve this problem, in this work we propose to use machine learning based models for policy categorizer that classifies the policy paragraphs under the attributes proposed like security, contact etc. By benchmarking different machine learning based classifier models, we show that artificial neural network model performs with higher accuracy on a challenging dataset of textual privacy policies. We thus show that machine learning can help summarize the relevant paragraphs under the various attributes so that the user can get the gist of that topic within a few lines.

Skin lesion segmentation method for dermoscopic images with convolutional neural networks and semantic segmentation

Melanoma skin cancer is one of the most dangerous forms of skin cancer because it grows fast and causes most of the skin cancer deaths. Hence, early detection is a very important task to treat melanoma. In this article, we propose a skin lesion segmentation method for dermoscopic images based on the U-Net architecture with VGG-16 encoder and the semantic segmentation. Base on the segmented skin lesion, diagnostic imaging systems can evaluate skin lesion features to classify them. The proposed method requires fewer resources for training, and it is suitable for computing systems without powerful GPUs, but the training accuracy is still high enough (above 95 %). In the experiments, we train the model on the ISIC dataset – a common dermoscopic image dataset. To assess the performance of the proposed skin lesion segmentation method, we evaluate the Sorensen-Dice and the Jaccard scores and compare to other deep learning-based skin lesion segmentation methods. Experimental results showed that skin lesion segmentation quality of the proposed method are better than ones of the compared methods.

In situ mapping identifies distinct vascular niches for myelopoiesis

In contrast to nearly all other tissues, the anatomy of cell differentiation in the bone marrow remains unknown. This is owing to a lack of strategies for examining myelopoiesis-the differentiation of myeloid progenitors into a large variety of innate immune cells-in situ in the bone marrow. Such strategies are required to understand differentiation and lineage-commitment decisions, and to define how spatial organizing cues inform tissue function. Here we develop approaches for imaging myelopoiesis in mice, and generate atlases showing the differentiation of granulocytes, monocytes and dendritic cells. The generation of granulocytes and dendritic cells-monocytes localizes to different blood-vessel structures known as sinusoids, and displays lineage-specific spatial and clonal architectures. Acute systemic infection with Listeria monocytogenes induces lineage-specific progenitor clusters to undergo increased self-renewal of progenitors, but the different lineages remain spatially separated. Monocyte-dendritic cell progenitors (MDPs) map with nonclassical monocytes and conventional dendritic cells; these localize to a subset of blood vessels expressing a major regulator of myelopoiesis, colony-stimulating factor 1 (CSF1, also known as M-CSF)¹. Specific deletion of Csf1 in endothelium disrupts the architecture around MDPs and their localization to sinusoids. Subsequently, there are fewer MDPs and their ability to differentiate is reduced, leading to a loss of nonclassical monocytes and dendritic cells during both homeostasis and infection. These data indicate that local cues produced by distinct blood vessels are responsible for the spatial organization of definitive blood cell differentiation.

Dynamic Increased Capacity Approach Steganography in Spatial Domain

Information security using image steganography is the process of concealing secret information within an image. The conventional methods are static approaches having fixed capacity in term of embedding rate. To solve the problem of static behavior and fixed capacity, we proposed a method that is dynamic approach and increased capacity for embedding rate. Novel algorithm can be used by the data storage industry to design new data storage devices. Other possible applications of this research work will be its usage in other areas such as Watermarking, Document Tracking Tool, Document Authentication Tool, and General Communication etc. Experimental results demonstrate that our proposed steganography algorithm produces the best performance among state-of-the-art algorithms in evaluation of subjective visual assessment as well as objective error metrics.

Melanoma Skin Cancer Detection Method Based on Adaptive Principal Curvature, Colour Normalisation and Feature Extraction with the ABCD Rule

According to statistics of the American Cancer Society, in 2015, there are about 91,270 American adults diagnosed with melanoma of the skin. For the European Union, there are over 90,000 new cases of melanoma annually. Although melanoma only accounts for about 1% of all skin cancers, it causes most of the skin cancer deaths. Melanoma is considered one of the fastest-growing forms of skin cancer, and hence the early detection is crucial, as early detection is helpful and can provide strong recommendations for specific and suitable treatment regimens. In this work, we propose a method to detect melanoma skin cancer with automatic image processing techniques. Our method includes three stages: pre-process images of skin lesions by adaptive principal curvature, segment skin lesions by the colour normalisation and extract features by the ABCD rule. We provide experimental results of the proposed method on the publicly available International Skin Imaging Collaboration (ISIC) skin lesions dataset. The acquired results on melanoma skin cancer detection indicates that the proposed method has high accuracy, and overall, a good performance: for the segmentation stage, the accuracy, Dice, Jaccard scores are 96.6%, 93.9% and 88.7%, respectively; and for the melanoma detection stage, the accuracy is up to 100% for a selected subset of the ISIC dataset.

Correction: OpinionML—Opinion Markup Language for Sentiment Representation. Symmetry 2019, 11, 545

The authors wish to make the following corrections to their paper [...]

Automatic body mass index detection using correlation of face visual cues

Body mass index (BMI) is used widely as an indicator in general health. Determination of BMI using non-intrusive measurements are of interest and recent advancements in the availability of digital imaging sensors have paved the way for performing quick and automatic measurements. In this work, we consider automatic computation of BMI using correlation features from face images. We show that using face detection based facial fiducial points analysis provides good BMI prediction. Experimental results on comparing the correlation coefficients of facial ratios along with the colour feature has higher significance in BMI of a person.

Choosing Mutation and Crossover Ratios for Genetic Algorithms—A Review with a New Dynamic Approach

Genetic algorithm (GA) is an artificial intelligence search method that uses the process of evolution and natural selection theory and is under the umbrella of evolutionary computing algorithm. It is an efficient tool for solving optimization problems. Integration among (GA) parameters is vital for successful (GA) search. Such parameters include mutation and crossover rates in addition to population that are important issues in (GA). However, each operator of GA has a special and different influence. The impact of these factors is influenced by their probabilities; it is difficult to predefine specific ratios for each parameter, particularly, mutation and crossover operators. This paper reviews various methods for choosing mutation and crossover ratios in GAs. Next, we define new deterministic control approaches for crossover and mutation rates, namely Dynamic Decreasing of high mutation ratio/dynamic increasing of low crossover ratio (DHM/ILC), and Dynamic Increasing of Low Mutation/Dynamic Decreasing of High Crossover (ILM/DHC). The dynamic nature of the proposed methods allows the ratios of both crossover and mutation operators to be changed linearly during the search progress, where (DHM/ILC) starts with 100% ratio for mutations, and 0% for crossovers. Both mutation and crossover ratios start to decrease and increase, respectively. By the end of the search process, the ratios will be 0% for mutations and 100% for crossovers. (ILM/DHC) worked the same but the other way around. The proposed approach was compared with two parameters tuning methods (predefined), namely fifty-fifty crossover/mutation ratios, and the most common approach that uses static ratios such as (0.03) mutation rates and (0.9) crossover rates. The experiments were conducted on ten Traveling Salesman Problems (TSP). The experiments showed the effectiveness of the proposed (DHM/ILC) when dealing with small population size, while the proposed (ILM/DHC) was found to be more effective when using large population size. In fact, both proposed dynamic methods outperformed the predefined methods compared in most cases tested.

Multiscale Structure Tensor for Improved Feature Extraction and Image Regularization

Regularization methods are used widely in image selective smoothing and edge preserving restoration of noisy images. Traditional methods utilize image gradients within regularization function for controlling the smoothing and can produce artifacts when noise levels are higher. In this paper, we consider a robust image adaptive exponent driven regularization for filtering noisy images with salient feature preservation. Our spatially adaptive variable exponent function depends on a continuous switch based on the eigenvalues of structure tensor which identifies noisy edges, and corners with higher accuracy. Structure tensor eigenvalues encode various image features and we consider a spatially varying continuous map which provides multiscale edge maps of natural images. By embedding the structure tensor-based exponent in a well-defined regularization model, we obtain denoising filters which are capable of obtaining good feature preserving image restoration. The GPU-based implementation computes the edge map in real time at 45-60 frames/s depending on the GPU card. Multiscale structure tensor-based spatially adaptive variable exponent provides reliable edge maps and compared with standard edge detectors it is robust under various noisy conditions. Moreover, filtering based on the multiscale variable exponent map method outperforms L0 sparse gradient-based image smoothing and related filters.

Effects of Distance Measure Choice on K-Nearest Neighbor Classifier Performance: A Review

The K-nearest neighbor (KNN) classifier is one of the simplest and most common classifiers, yet its performance competes with the most complex classifiers in the literature. The core of this classifier depends mainly on measuring the distance or similarity between the tested examples and the training examples. This raises a major question about which distance measures to be used for the KNN classifier among a large number of distance and similarity measures available? This review attempts to answer this question through evaluating the performance (measured by accuracy, precision, and recall) of the KNN using a large number of distance measures, tested on a number of real-world data sets, with and without adding different levels of noise. The experimental results show that the performance of KNN classifier depends significantly on the distance used, and the results showed large gaps between the performances of different distances. We found that a recently proposed nonconvex distance performed the best when applied on most data sets comparing with the other tested distances. In addition, the performance of the KNN with this top performing distance degraded only ∼20% while the noise level reaches 90%, this is true for most of the distances used as well. This means that the KNN classifier using any of the top 10 distances tolerates noise to a certain degree. Moreover, the results show that some distances are less affected by the added noise comparing with other distances.

Generation of fashionable clothes using generative adversarial networks

Purpose

There are various style options available when one buys clothes on online shopping websites, however the availability the new fashion trends or choices require further user interaction in generating fashionable clothes. The paper aims to discuss this issue.

Design/methodology/approach

Based on generative adversarial networks (GANs) from the deep learning paradigm, here the authors suggest model system that will take the latest fashion trends and the clothes bought by users as input and generate new clothes. The new set of clothes will be based on trending fashion but at the same time will have attributes of clothes where were bought by the consumer earlier.

Findings

In the proposed machine learning based approach, the clothes generated by the system will personalized for different types of consumers. This will help the manufacturing companies to come up with the designs, which will directly target the customer.

Research limitations/implications

The biggest limitation of the collected data set is that the clothes in the two domains do not belong to a specific category. For instance the vintage clothes data set has coats, dresses, skirts, etc. These different types of clothes are not segregated. Also there is no restriction on the number of images of each type of cloth. There can many images of dresses and only a few for the coats. This can affect the end results. The aim of the paper was to find whether new and desirable clothes can be created from two different domains or not. Analyzing the impact of “the number of images for each class of cloth” is something which is aim to work in future.

Practical implications

The authors believe such personalized experience can increase the sales of fashion stores and here provide the feasibility of such a clothes generation system.

Originality/value

Applying GANs from the deep learning models for generating fashionable clothes.

Analysis of a robust edge detection system in different color spaces using color and depth images

Edge detection is very important technique to reveal significant areas in the digital image, which could aids the feature extraction techniques. In fact it is possible to remove un-necessary parts from image, using edge detection. A lot of edge detection techniques has been made already, but we propose a robust evolutionary based system to extract the vital parts of the image. System is based on a lot of pre and post-processing techniques such as filters and morphological operations, and applying modified Ant Colony Optimization edge detection method to the image. The main goal is to test the system on different color spaces, and calculate the system’s performance. Another novel aspect of the research is using depth images along with color ones, which depth data is acquired by Kinect V.2 in validation part, to understand edge detection concept better in depth data. System is going to be tested with 10 benchmark test images for color and 5 images for depth format, and validate using 7 Image Quality Assessment factors such as Peak Signal-to-Noise Ratio, Mean Squared Error, Structural Similarity and more (mostly related to edges) for prove, in different color spaces and compared with other famous edge detection methods in same condition. Also for evaluating the robustness of the system, some types of noises such as Gaussian, Salt and pepper, Poisson and Speckle are added to images, to shows proposed system power in any condition. The goal is reaching to best edges possible and to do this, more computation is needed, which increases run time computation just a bit more. But with today’s systems this time is decreased to minimum, which is worth it to make such a system. Acquired results are so promising and satisfactory in compare with other methods available in validation section of the paper.

Video denoising with adaptive temporal averaging

Recently the proliferation of digital videos has increased exponentially due to availability of consumer cameras . Despite the improvement in the sensor technologies, one of the fundamental problems is that of noise affecting the video scenes. Recently, adaptive, pixel-wise, temporal averaging methods can advocate in denoising videos. In this work, we adapt the edge maps of frames within temporal averaging to guide the denoising away from the edges. This allows the filtering to remove noise in intermediate flat regions while respecting boundaries of objects better. The experimental results indicate that we can obtain improved video denoising results in comparison to other filtering methods.