Breast Cancer Histopathological Image Classification using Stochastic Dilated Residual Ghost Model

A new deep learning-based classification model called the Stochastic Dilated Residual Ghost (SDRG) was proposed in this work for categorizing histopathology images of breast cancer. The SDRG model used the proposed Multiscale Stochastic Dilated Convolution (MSDC) model, a ghost unit, stochastic upsampling, and downsampling units to categorize breast cancer accurately. This study addresses four primary issues: first, strain normalization was used to manage color divergence, data augmentation with several factors was used to handle the overfitting. The second challenge is extracting and enhancing tiny and low-level information such as edge, contour, and color accuracy; it is done by the proposed multiscale stochastic and dilation unit. The third contribution is to remove redundant or similar information from the convolution neural network using a ghost unit. According to the assessment findings, the SDRG model scored overall 95.65 percent accuracy rates in categorizing images with a precision of 99.17 percent, superior to state-of-the-art approaches.

Extreme Learning Machine-Based Age-Invariant Face Recognition With Deep Convolutional Descriptors

The principal intention of this paper is to study face recognition across age progression at two levels: feature extraction and classification. In other words, this work aims to prove the benefit of replacing the Softmax layer of the Deep-Convolutional Neural Networks (CNN) by Extreme Learning Machine (ELM) classifier based on deep features computed from fully-connected layer of pre-trained AlexNet CNN model, in a context of age-invariant face recognition. Experimental results indicate that the ELM classifier combined with feature extracted by the pre-trained AlexNet CNN model worked effectively for face recognition across age progression. As significant highest mean accuracy rates are always obtained using ELM classifier. These results are more significant, following a 95% confidence level hypothesis test.

Ultrasonic Elastography Combined with Human Papilloma Virus Detection Based on Intelligent Denoising Algorithm in Diagnosis of Cervical Intraepithelial Neoplasia

The aim of this research was to study the application of ultrasonic elastography combined with human papilloma virus (HPV) detection based on bilateral filter intelligent denoising algorithm in the diagnosis of cervical intraepithelial neoplasia (CIN) and provide a theoretical basis for clinical diagnosis and treatment of CIN. In this study, 100 patients with cervical lesions were selected as research objects and randomly divided into control group and experimental group, with 50 cases in each group. Patients in control group and experimental group were diagnosed by ultrasonic elastography combined with HPV detection. The experimental group used the optimized image map of bilateral filter intelligent denoising algorithm for denoising and optimization, while the control group did not use optimization, and the differences between them were analyzed and compared. The diagnostic effects of the two groups were compared. As a result, the three accuracy rates of the experimental group were 95%, 95%, and 98%, respectively; the three sensitivity rates were 96%, 92%, and 94%, respectively; and the three specificity rates were 99%, 97%, and 98%, respectively. In the control group, the three accuracy rates were 84%, 86%, and 84%, respectively; the three sensitivity rates were 88%, 84%, and 86%, respectively; and the three specificity rates were 81%, 83%, and 88%, respectively. The accuracy, sensitivity, and specificity of experiment group were significantly higher than those of control group, and the difference was statistically significant ( P < 0.05 ). In summary, the bilateral filter intelligent denoising algorithm has a good denoising effect on the ultrasonic elastography. The ultrasonic image processed by the algorithm combined with HPV detection has a better diagnosis of CIN.

Deep Learning and Machine Learning Techniques of Diagnosis Dermoscopy Images for Early Detection of Skin Diseases

With the increasing incidence of severe skin diseases, such as skin cancer, endoscopic medical imaging has become urgent for revealing the internal and hidden tissues under the skin. Diagnostic information to help doctors make an accurate diagnosis is provided by endoscopy devices. Nonetheless, most skin diseases have similar features, which make it challenging for dermatologists to diagnose patients accurately. Therefore, machine and deep learning techniques can have a critical role in diagnosing dermatoscopy images and in the accurate early detection of skin diseases. In this study, systems for the early detection of skin lesions were developed. The performance of the machine learning and deep learning was evaluated on two datasets (e.g., the International Skin Imaging Collaboration (ISIC 2018) and Pedro Hispano (PH2)). First, the proposed system was based on hybrid features that were extracted by three algorithms: local binary pattern (LBP), gray level co-occurrence matrix (GLCM), and wavelet transform (DWT). Such features were then integrated into a feature vector and classified using artificial neural network (ANN) and feedforward neural network (FFNN) classifiers. The FFNN and ANN classifiers achieved superior results compared to the other methods. Accuracy rates of 95.24% for diagnosing the ISIC 2018 dataset and 97.91% for diagnosing the PH2 dataset were achieved using the FFNN algorithm. Second, convolutional neural networks (CNNs) (e.g., ResNet-50 and AlexNet models) were applied to diagnose skin diseases using the transfer learning method. It was found that the ResNet-50 model fared better than AlexNet. Accuracy rates of 90% for diagnosing the ISIC 2018 dataset and 95.8% for the PH2 dataset were reached using the ResNet-50 model.

Multi-Focus Image Fusion Based on Convolution Neural Network for Parkinson’s Disease Image Classification

Parkinson’s disease (PD) is a common neurodegenerative disease that has a significant impact on people’s lives. Early diagnosis is imperative since proper treatment stops the disease’s progression. With the rapid development of CAD techniques, there have been numerous applications of computer-aided diagnostic (CAD) techniques in the diagnosis of PD. In recent years, image fusion has been applied in various fields and is valuable in medical diagnosis. This paper mainly adopts a multi-focus image fusion method primarily based on deep convolutional neural networks to fuse magnetic resonance images (MRI) and positron emission tomography (PET) neural photographs into multi-modal images. Additionally, the study selected Alexnet, Densenet, ResNeSt, and Efficientnet neural networks to classify the single-modal MRI dataset and the multi-modal dataset. The test accuracy rates of the single-modal MRI dataset are 83.31%, 87.76%, 86.37%, and 86.44% on the Alexnet, Densenet, ResNeSt, and Efficientnet, respectively. Moreover, the test accuracy rates of the multi-modal fusion dataset on the Alexnet, Densenet, ResNeSt, and Efficientnet are 90.52%, 97.19%, 94.15%, and 93.39%. As per all four networks discussed above, it can be concluded that the test results for the multi-modal dataset are better than those for the single-modal MRI dataset. The experimental results showed that the multi-focus image fusion method according to deep learning can enhance the accuracy of PD image classification.

Intelligent Malaysian Sign Language Translation System Using Convolutional-Based Attention Module with Residual Network

The deaf-mutes population always feels helpless when they are not understood by others and vice versa. This is a big humanitarian problem and needs localised solution. To solve this problem, this study implements a convolutional neural network (CNN), convolutional-based attention module (CBAM) to recognise Malaysian Sign Language (MSL) from images. Two different experiments were conducted for MSL signs, using CBAM-2DResNet (2-Dimensional Residual Network) implementing “Within Blocks” and “Before Classifier” methods. Various metrics such as the accuracy, loss, precision, recall, F1-score, confusion matrix, and training time are recorded to evaluate the models’ efficiency. The experimental results showed that CBAM-ResNet models achieved a good performance in MSL signs recognition tasks, with accuracy rates of over 90% through a little of variations. The CBAM-ResNet “Before Classifier” models are more efficient than “Within Blocks” CBAM-ResNet models. Thus, the best trained model of CBAM-2DResNet is chosen to develop a real-time sign recognition system for translating from sign language to text and from text to sign language in an easy way of communication between deaf-mutes and other people. All experiment results indicated that the “Before Classifier” of CBAMResNet models is more efficient in recognising MSL and it is worth for future research.

Creation and validation of the Picture-Set of Young Children’s Affective Facial Expressions (PSYCAFE)

The immediate detection and correct processing of affective facial expressions are one of the most important competences in social interaction and thus a main subject in emotion and affect research. Generally, studies in these research domains, use pictures of adults who display affective facial expressions as experimental stimuli. However, for studies investigating developmental psychology and attachment behaviour it is necessary to use age-matched stimuli, where it is children that display affective expressions. PSYCAFE represents a newly developed picture-set of children’s faces. It includes reference portraits of girls and boys aged 4 to 6 years averaged digitally from different individual pictures, that were categorized to six basic affects (fear, disgust, happiness, sadness, anger and surprise) plus a neutral facial expression by cluster analysis. This procedure led to deindividualized and affect prototypical portraits. Individual affect expressive portraits of adults from an already validated picture-set (KDEF) were used in a similar way to create affect prototypical images also of adults. The stimulus set has been validated on human observers and entail emotion recognition accuracy rates and scores for intensity, authenticity and likeability ratings of the specific affect displayed. Moreover, the stimuli have also been characterized by the iMotions Facial Expression Analysis Module, providing additional data on probability values representing the likelihood that the stimuli depict the expected affect. Finally, the validation data from human observers and iMotions are compared to data on facial mimicry of healthy adults in response to these portraits, measured by facial EMG (m. zygomaticus major and m. corrugator supercilii).

Multiplex polymerase chain reaction detection of Streptococcus pneumoniae and Haemophilus influenzae and their antibiotic resistance in patients with community-acquired pneumonia from southwest Iran

Background This study aimed to evaluate the occurrence of Streptococcus pneumoniae and Haemophilus influenzae in sputum of patients with community-acquired pneumonia (CAP) using culture and multiplex polymerase chain reaction (M-PCR) methods and to survey the antibiotic resistance patterns of aforesaid isolates. Result In total, 23.9 % (n = 22/92) of sputum samples showed positive results in the culture method. S. pneumoniae and H. influenzae were isolated from 15 (16.3 %) and 7 (7.6%) samples, respectively. Using M-PCR, 44 (47.8 %) samples were positive for S. pneumoniae and H. influenzae. Of these, S. pneumoniae and H. influenzae were detected in 33 (35.8%) and 11 (11.9%) of the sputum samples, respectively. The sensitivity, specificity, and accuracy rates of PCR in detection of S. pneumoniae in comparison with culture method were 100, 76.6, and 83.6%, respectively. While, the sensitivity, specificity, and accuracy rates of PCR in detection of H. influenzae in comparison with culture method were 100, 95.3, and 95.8%, respectively. Out of 11 isolates of H. influenzae, two strains confirmed as H. influenzae type b (Hib) and 3 isolates were type f. However, 6 isolates were non-typable. The co-trimoxazole and amoxicillin/clavulanate were the less effective antibiotics against S. pneumonia and H. influenzae, respectively. Ceftriaxone with 13.3% resistance rates was the most effective antibiotic against S. pneumoniae, while, clarithromycin, ceftriaxone, and gentamicin with resistance rates of 28.6% for each one were the most effective chemicals against H. influenzae isolates. Conclusion In this study, the prevalence of S. pneumoniae was more than H. influenzae using culture and M-PCR methods. The M-PCR provided better efficiency in detecting the bacterial agents in CAP patients compared to culture method. This method can improve the early detection of pathogens contributed to CAP. The drug resistant S. pneumoniae and H. influenzae indicated the need to develop a codified monitoring program to prevent further spread of these strains.

Language effects in early development of number writing and reading

Reading and writing multidigit numbers requires accurate switching between Arabic numbers and spoken number words. This is particularly challenging in languages with number-word inversion such as German (24 is pronounced as four-and-twenty), as reported by Zuber, Pixner, Moeller, and Nuerk (2009, https://doi.org/10.1016/j.jecp.2008.04.003). The current study aimed to replicate the qualitative error analysis by Zuber et al. and further extended their study: 1) A cross-linguistic (German, English) analysis enabled us to differentiate between language-dependent and more general transcoding challenges. 2) We investigated whether specific number structures influence accuracy rates. 3) To consider both transcoding directions (from Arabic numbers to number words and vice versa), we assessed performance for number reading in addition to number writing. 4) Our longitudinal design allowed us to investigate transcoding development between Grades 1 and 2. We assessed 170 German- and 264 English-speaking children. Children wrote and read the same set of 44 one-, two- and three-digit numbers, including the same number structures as Zuber et al. For German, we confirmed that a high amount of errors in number writing was inversion-related. For English, the percentage of inversion-related errors was very low. Accuracy rates were strongly related to number syntax. The impact of number structures was independent of transcoding direction or grade level and revealed cross-linguistic challenges of transcoding multidigit numbers. For instance, transcoding of three-digit numbers containing syntactic zeros (e.g., 109) was significantly more accurate than transcoding of items with lexical zeros (e.g., 190). Based on our findings, we suggest adaptations of current transcoding models.

DNS Firewall Based on Machine Learning

Nowadays there are many DNS firewall solutions to prevent users accessing malicious domains. These can provide real-time protection and block illegitimate communications, contributing to the cybersecurity posture of the organizations. Most of these solutions are based on known malicious domain lists that are being constantly updated. However, in this way, it is only possible to block malicious communications for known malicious domains, leaving out many others that are malicious but have not yet been updated in the blocklists. This work provides a study to implement a DNS firewall solution based on ML and so improve the detection of malicious domain requests on the fly. For this purpose, a dataset with 34 features and 90 k records was created based on real DNS logs. The data were enriched using OSINT sources. Exploratory analysis and data preparation steps were carried out, and the final dataset submitted to different Supervised ML algorithms to accurately and quickly classify if a domain request is malicious or not. The results show that the ML algorithms were able to classify the benign and malicious domains with accuracy rates between 89% and 96%, and with a classification time between 0.01 and 3.37 s. The contributions of this study are twofold. In terms of research, a dataset was made public and the methodology can be used by other researchers. In terms of solution, the work provides the baseline to implement an in band DNS firewall.