Deep learning based classification of breast tumors with shear-wave elastography

Deep learning (also known as deep structured learning, hierarchical learning, or deep machine learning) is a branch of machine learning based on a set of algorithms that attempt to model high-level abstractions in data by using a deep graph with multiple processing layers, composed of multiple linear and nonlinear transformations. Deep learning has been characterized as a class of machine learning algorithms with the following characteristics [257]: • They use a cascade of many layers of nonlinear processing units for feature extraction and transformation. Each successive layer uses the output from the previous layer as input. The algorithms may be supervised or unsupervised and applications include pattern analysis (unsupervised) and classification (supervised). • They are based on the (unsupervised) learning of multiple levels of features or representations of the data. Higher-level features are derived from lower-level features to form a hierarchical representation. • They are part of the broader machine learning field of learning representations of data. • They learn multiple levels of representations that correspond to different levels of abstraction; the levels form a hierarchy of concepts. These definitions have in common: multiple layers of nonlinear processing units and the supervised or unsupervised learning of feature representations in each layer, with the layers forming a hierarchy from low-level to high-level features. Various deep learning architectures such as deep neural networks, convolutional deep neural networks, deep belief networks (DBN), and recurrent neural networks have been applied to fields like computer vision, automatic speech recognition, natural language processing, audio recognition, and bioinformatics where they have been shown to produce state-of-the-art results on various tasks. In this chapter we start in Section 7.1 with an introduction, giving a brief history of this field, the relevant literature, and its applications. Then we study some basic concepts of deep learning such as convolutional neural networks, recurrent neural networks, backpropagation algorithm, restricted Boltzmann machines, and deep learning networks in Section 7.2. Then we illustrate three examples for Apache Spark implementation for mobile big data (MBD), user moving pattern extraction, and combination with nonparametric Bayesian learning, respectively, in Sections 7.3 through 7.5. Finally, we have summary in Section 7.6.

Steering angle prediction plays a crucial role in the control of Autonomous Vehicles (AVs) and has garnered the interest of researchers, manufacturers, and insurance companies within the automotive industry. Various Deep Learning (DL) architectures have been utilized to forecast the steering angle of AVs across different scenarios. An examination focusing on steering angle prediction through deep learning algorithms can assist seasoned researchers in pinpointing areas that necessitate further advancement. Additionally, newcomers in the field can utilize this study as a foundation. This paper offers an extensive analysis of the recent progress achieved in DL architectures concerning the steering angle prediction of AVs. A comprehensive taxonomy outlining the application of DL in steering angle prediction of AVs has been developed. The survey provides a succinct synthesis, summary, and analysis of research findings. It is evident that Convolutional Neural Network (CNN) is the preferred choice among researchers for predicting the steering angle of autonomous vehicles, compared to other DL architectures. Furthermore, existing research challenges have been identified. The primary obstacle encountered in DL-based steering angle prediction of AVs is the scarcity of real-world datasets, leading researchers to heavily rely on data generated from simulated environments. Lastly, potential alternative approaches to address the identified research challenges have been suggested, indicating promising avenues for future research endeavours.

Tumor-infiltrating lymphocytes (TIL) are important immunological components in response to cancers. Patients with higher numbers of TIL in breast cancerous tissues, comprising T- cytotoxic and T - helper cells along with B- and rare natural killer (NK) cells, have more favorable clinical outcomes. To analyze the rate of the expressed surface biomarker proteins of CD20-B cells and CD56- NK cells on the infiltrative lymphocytic subpopulations in a group of breast tumorous tissues (invasive and benign) from female patients in Iraq and explore the relations to the grade of the invasive breast cancerous tissues. One hundred and 75 archived breast tissues were enrolled in this retrospective research: 100 archived breast from female patients with invasive breast cancers (BC) [20 well differentiated BC tissues; 48 moderately differentiated BC and 32 poorly differentiated BC tissues]; 50 tissue biopsies from female patients with benign breast tumors and 25 apparently normal individuals with healthy breast tissues (included as the control group for this study). Immunohistochemistry was achieved for the detection of the expressed surface biomarker proteins related to B cell CD20 and NK cell CD56 present on the infiltrative lymphocytic subpopulations in breast tissues by using specific primary antibodies for these proteins via utilizing an immune-enzymatic antigen detection system. The detection of IHC reactions for the expressed B cell CD20 - cell surface ( CD) biomarker proteins were observed in 53 out of 100 (53.0%) BC tissues, and in 24 out of 50 (48.0%) benign breast tumorous tissues, while CD20- positive cell surface markers was detected in apparently healthy breast tissues of the control group in a percentage of 32.0% (8 out of 25 tissues). Statistical significant differences (P<0.05) between both groups of malignant and benign breast tumors and the control group were found. However, between breast malignant and benign tumor groups, no significant difference was found ( p >0.05). Detection of CD56- IHC reactions revealed in 14% (14 out of 100 BC tissues), in 16% (8 out of 50 benign breast tissues) and none of control breast tissues revealed CD56- IHC reactions. Among all the enrolled groups, no significant differences (P>0.05) were detected. The observed significant rates that showed highly significant differences between both studied groups of breast malignant and benign tumor in comparison to the control group indicate that the CD20- positive infiltrative B cell- lymphocytic subpopulations might contributed in the defense against these subsets of benign and malignant breast tumors. However, the observed rates of NK cell CD56 present on the lymphocytic subpopulations infiltrating the examined malignant and benign breast tumorous tissues seeming to play irrelevant roles in the defense against these studied breast tumor groups.

Detection of smoke from videos captured by surveillance cameras in outdoor environments is one of the useful outcome of Internet of Things (IoT) applications. The potential benefit increases when deep learning (DL) architectures are involved. However, an inherent difficulty is to detect smoke while natural events like fog exists. The effectiveness of color spaces in detection performance has not yet fully evaluated in those architectures. Moreover, the energy and memory requirements of DL architectures may not be applicable for handling IoT implementation demands. Therefore, in this work, a DL architecture with a suitable color space model, applicable for IoT implementations is proposed to detect smoke from videos in foggy environment. By collecting several videos including smoke samples, the performance comparison of popular and the state-of-the-art DL architectures denoted the outperforming result according to both accuracy and memory usage.

This study proposes a compact deep learning (DL) architecture and a highly parallelized computing hardware platform to reconstruct the blood flow index (BFi) in diffuse correlation spectroscopy (DCS). We leveraged a rigorous analytical model to generate autocorrelation functions (ACFs) to train the DL network. We assessed the accuracy of the proposed DL using simulated and milk phantom data. Compared to convolutional neural networks (CNN), our lightweight DL architecture achieves 66.7% and 18.5% improvement in MSE for BFi and the coherence factor β, using synthetic data evaluation. The accuracy of rBFi over different algorithms was also investigated. We further simplified the DL computing primitives using subtraction for feature extraction, considering further hardware implementation. We extensively explored computing parallelism and fixed-point quantization within the DL architecture. With the DL model's compact size, we employed unrolling and pipelining optimizations for computation-intensive for-loops in the DL model while storing all learned parameters in on-chip BRAMs. We also achieved pixel-wise parallelism, enabling simultaneous, real-time processing of 10 and 15 autocorrelation functions on Zynq-7000 and Zynq-UltraScale+ field programmable gate array (FPGA), respectively. Unlike existing FPGA accelerators that produce BFi and the β from autocorrelation functions on standalone hardware, our approach is an encapsulated, end-to-end on-chip conversion process from intensity photon data to the temporal intensity ACF and subsequently reconstructing BFi and β. This hardware platform achieves an on-chip solution to replace post-processing and miniaturize modern DCS systems that use single-photon cameras. We also comprehensively compared the computational efficiency of our FPGA accelerator to CPU and GPU solutions.

Prediction of the stage of cancer plays an important role in planning the course of treatment and has been largely reliant on imaging tools which do not capture molecular events that cause cancer progression. Gene-expression data-based analyses are able to identify these events, allowing RNA-sequence and microarray cancer data to be used for cancer analyses. Breast cancer is the most common cancer worldwide, and is classified into four stages - stages 1, 2, 3, and 4 [2]. While machine learning models have previously been explored to perform stage classification with limited success, multi-class stage classification has not had significant progress. There is a need for improved multi-class classification models, such as by investigating deep learning models. Gene-expression-based cancer data is characterised by the small size of available datasets, class imbalance, and high dimensionality. Class balancing methods must be applied to the dataset. Since all the genes are not necessary for stage prediction, retaining only the necessary genes can improve classification accuracy. The breast cancer samples are to be classified into 4 classes of stages 1 to 4. Invasive ductal carcinoma breast cancer samples are obtained from The Cancer Genome Atlas (TCGA) and Molecular Taxonomy of Breast Cancer International Consortium (METABRIC) datasets and combined. Two class balancing techniques are explored, synthetic minority oversampling technique (SMOTE) and SMOTE followed by random undersampling. A hybrid feature selection pipeline is proposed, with three pipelines explored involving combinations of filter and embedded feature selection methods: Pipeline 1 - minimum-redundancy maximum-relevancy (mRMR) and correlation feature selection (CFS), Pipeline 2 - mRMR, mutual information (MI) and CFS, and Pipeline 3 - mRMR and support vector machine-recursive feature elimination (SVM-RFE). The classification is done using deep learning models, namely deep neural network, convolutional neural network, recurrent neural network, a modified deep neural network, and an AutoKeras generated model. Classification performance post class-balancing and various feature selection techniques show marked improvement over classification prior to feature selection. The best multiclass classification was found to be by a deep neural network post SMOTE and random undersampling, and feature selection using mRMR and recursive feature elimination, with a Cohen-Kappa score of 0.303 and a classification accuracy of 53.1%. For binary classification into early and late-stage cancer, the best performance is obtained by a modified deep neural network (DNN) post SMOTE and random undersampling, and feature selection using mRMR and recursive feature elimination, with an accuracy of 81.0% and a Cohen-Kappa score (CKS) of 0.280. This pipeline also showed improved multiclass classification performance on neuroblastoma cancer data, with a best area under the receiver operating characteristic (auROC) curve score of 0.872, as compared to 0.71 obtained in previous work, an improvement of 22.81%. The results and analysis reveal that feature selection techniques play a vital role in gene-expression data-based classification, and the proposed hybrid feature selection pipeline improves classification performance. Multi-class classification is possible using deep learning models, though further improvement particularly in late-stage classification is necessary and should be explored further.

The aims of this work are (1) to explore deep learning (DL) architectures, spectroscopic input types, and learning designs toward optimal quantification in MR spectroscopy of simulated pathological spectra; and (2) to demonstrate accuracy and precision of DL predictions in view of inherent bias toward the training distribution. Simulated 1D spectra and 2D spectrograms that mimic an extensive range of pathological in vivo conditions are used to train and test 24 different DL architectures. Active learning through altered training and testing data distributions is probed to optimize quantification performance. Ensembles of networks are explored to improve DL robustness and reduce the variance of estimates. A set of scores compares performances of DL predictions and traditional model fitting (MF). Ensembles of heterogeneous networks that combine 1D frequency-domain and 2D time-frequency domain spectrograms as input perform best. Dataset augmentation with active learning can improve performance, but gains are limited. MF is more accurate, although DL appears to be more precise at low SNR. However, this overall improved precision originates from a strong bias for cases with high uncertainty toward the dataset the network has been trained with, tending toward its average value. MF mostly performs better compared to the faster DL approach. Potential intrinsic biases on training sets are dangerous in a clinical context that requires the algorithm to be unbiased to outliers (i.e., pathological data). Active learning and ensemble of networks are good strategies to improve prediction performances. However, data quality (sufficient SNR) has proven as a bottleneck for adequate unbiased performance-like in the case of MF.

We have developed a magnetic resonance (MR) image-based radiomic biopsy approach for estimation of malignancy grade in parotid gland cancer (PGC). Preoperative T1- and T2-weighted MR images of 39 PGC patients with 20 highand 19 intermediate-/low-malignancy grades were employed. High- versus intermediate-/low-malignancy grades were estimated using MR-radiomic biopsy approaches, i.e. 972 hand-crafted feature and transfer learning of five pre-trained deep learning (DL) architectures (AlexNet, GoogLeNet, VGG-16, ResNet-101, DenseNet-201). The 39 patients were divided into 70% for training datasets and 30% for test datasets. The hand-crafted features were extracted from cancer regions in T1- and T2-weighted MR images. Three features were selected as a radiomic signature by using a least absolute shrinkage and selection operator (LASSO), whose coefficients of three features were used for constructing the radiomic score (Rad-score). The two grade malignancy was estimated by using an optimal cut-off value of Rad-score. On the other hand, last three layers of the DL architectures were replaced with new three layers for the estimation task. The DL architectures were fine-tuned with training datasets and were evaluated with test datasets. The performances of the MR-radiomic biopsy approaches were assessed by using the accuracy and the area under the receiver operating characteristic curve (AUC). The VGG-16 demonstrated the best performance (accuracy=85.4%, AUC=0.906), but the other approaches showed worse performances (Rad-score: 83.3%, 0.830, AlexNet: 84.4%, 0.915, GoogLeNet: 84.9%, 0.884, ResNet-101: 84.9%, 0.918, DenseNet-201: 84.4%, 0.869) than the VGG-16. The VGG-16-based MR-radiomic biopsy could be feasible for the malignancy grade estimation of PGC.

The emergence of artificial intelligence (AI) and its related capabilities has led industries to rethink the existing practices of conventional supply chain management and data analysis. Machine learning (ML), Deep Learning (DL) and their unique ability to predict future data and classify data have led to important research in the supply chain (SC) domain, particularly in identifying and prioritizing supply chain risks. This paper proposes several DL methodologies to exploit the benefit of DL, particularly to identify whether any product will be delivered late due to any unforeseen reason in a complex SC system. Four different DL architectures (Simple-LSTM, Deep-LSTM, 1D-CNN, and TCN-1DSPCNN models) are proposed to extract features, while six variant classifiers: Softmax, random trees (RT), random forest (RF), K-nearest neighbor (KNN), artificial neural network (ANN), and support vector machine (SVM), were used to classify delay or non-delay information. By seamlessly capturing intricate temporal dependencies, these DL models enhance accuracy in robustly identifying supply chain late orders. Leveraging their hierarchical feature learning, these proposed DL models excel in recognizing subtle patterns and correlations, making them ideal for classifying late orders within the supply chain. Their parallel processing prowess facilitates real-time decision support, allowing organizations to address potential delays and allocate resources effectively and proactively. Five-fold cross-validation is presented to avoid over-fitting and to prove the efficiency of the proposed DL models. The total accuracies of the six ML classifiers are 74.03, 75.81, 93.35, 87.72, 93.59, and 95.10, respectively, while the maximum accuracies obtained from four proposed DL methodologies obtained an accuracy of 97.6, 98.63, 100, 100% respectively using the SVM classifier for predicting late orders based on five-fold cross-validation.

The purpose of this study was to the diagnostic value of conventional ultrasound (US), contrast-enhanced ultrasound (CEUS) and shear wave elastography (SWE) for identifying benign and malignant BI-RADS 4 breast lesions. From February 2022 to November 2024, 95 patients aged 20 to 90 years with breast diseases, all of whom were female, were included. These lesions were diagnosed as BI-RADS 4 breast lesions by conventional ultrasound. All lesions were pathologically confirmed by surgical resection or tissue biopsy, and they were further evaluated by CEUS and SWE. The sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy of US, CEUS, and SWE were statistically analyzed, and ROC curves were generated. The diagnostic efficacy of US, US + SWE, US + CEUS, and US + CEUS + SWE were subsequently compared, with the pathology results used as the reference standard. (1) Among the 95 BI-RADS 4 lesions, 44 (46.31%) were benign, and 51 (53.69%) were malignant. The sensitivity, specificity, PPV, NPV and accuracy of the BI-RADS classification via conventional US were 86.3, 72.7, 78.6, 82.1 and 80.0%, respectively. (2) The sensitivity, specificity, PPV, NPV, and accuracy of US combined with SWE in the diagnosis of breast nodules were 96.1, 79.5, 84.5, 94.6, and 88.4%, respectively. (3) The sensitivity, specificity, PPV, NPV, and accuracy of US combined with CEUS in the diagnosis of breast nodules were 84.3, 86.4, 87.8, 82.6, and 85.3%, respectively. (4) The areas under the ROC curve (AUCs) of US, US + SWE, and US + CEUS were 0.795, 0.877, and 0.917, respectively. Statistical methods were used to evaluate the US + CEUS + SWE method, and the results indicated excellent diagnostic performance. The AUC was 0.946, while the sensitivity, specificity, PPV, NPV, and accuracy were 90.7, 93.2, 94.2, 95.3, and 94.7%, respectively. In this this study, the AUCs of US, SWE, and CEUS were compared, and the results revealed that both SWE and CEUS could increase the AUC for breast lesion diagnosis with good diagnostic performance. These methods can increase the sensitivity, specificity and accuracy of the US examination when combined with conventional US. Moreover, the diagnostic performance for breast lesions was highest with the combined application of the three modalities, with a diagnostic AUC that was significantly higher than those of US alone, US + SWE and US + CEUS. The differences were significant (p < 0.05). (1) CEUS and SWE provide diagnostic information about the microvascular perfusion and tissue stiffness of lesions, respectively, which can assist in the differentiation of benign from malignant breast tumors by conventional US and improve the sensitivity, specificity and accuracy of diagnosis, especially for US BI-RADS 4a breast lesions. (2) The combined use of CEUS and SWE in conventional US enhance the overall diagnostic performance with respect to breast lesions, with the best sensitivity and specificity and the highest diagnostic efficacy. The use of US + CEUS + SWE is beneficial for further differentiating benign and malignant breast lesions according to the US BI-RADS 4, thereby reducing unnecessary biopsies or surgeries.

AI-based emotion recognition has emerged as a critical component of affect-aware educational technologies, particularly in online, large-scale, and technology-mediated learning environments where direct observation of learners’ emotional states is limited. By leveraging facial expressions, speech, physiological signals, and interaction data, emotion-aware systems aim to support adaptive instruction, learner engagement, and instructional decision-making. Despite rapid technical progress, the integration of emotion recognition into authentic educational practice remains constrained by dataset limitations, cultural bias, weak pedagogical alignment, and unresolved ethical concerns. This article presents a critical and theory-informed review of recent advances in AI-based emotion recognition in education, with particular emphasis on deep learning architectures and multimodal fusion approaches, while highlighting persistent challenges and future research directions.Purpose:This study aims to critically examine the current state of AI-based emotion recognition in educational contexts by analyzing dominant modeling paradigms, sensing modalities, application domains, and ethical implications, in order to identify key gaps between technical development and pedagogical practice.Methods/Study design/approach:The study adopts a narrative literature review approach grounded in educational and affective computing theories. Representative and influential studies were analyzed across facial, speech, physiological, and multimodal emotion recognition systems, with emphasis on deep learning, attention-based, and transformer architectures. The review synthesizes findings related to system performance, educational applications, dataset characteristics, and ethical considerations.Result/Findings:The findings indicate that multimodal emotion recognition systems generally outperform unimodal approaches in detecting learning-relevant affective states such as engagement, frustration, and confusion. Advances in deep learning, particularly attention-based and transformer models, improve temporal modeling and robustness. However, most systems rely on non-educational datasets, demonstrate limited cultural generalizability, and prioritize recognition accuracy over pedagogical interpretability and long-term educational impact. Ethical challenges related to privacy, consent, bias, and emotional surveillance remain insufficiently addressed.Novelty/Originality/Value:This study provides an integrative and pedagogically grounded synthesis that bridges affective computing research with educational theory and governance perspectives. By reframing AI-based emotion recognition as a decision-support mechanism rather than an automated control system, the article offers a conceptual foundation for responsible, culturally inclusive, and ethically aligned deployment of emotion-aware AI in education, serving as a reference for future interdisciplinary research and policy development.

Natural language processing (NLP) techniques have evolved substantially in recent years, with transformer-based architectures emerging as powerful tools for textual analysis across various fields. This paper investigates the underexplored area of Arabic legal text classification through the implementation of transformer-based language models integrated with deep learning (DL) architectures. Even though transformer models are widely used in legal NLP for high-resource languages, their application to Arabic legal texts remains limited due to linguistic complexities and dataset scarcity. We introduce a classification model for Arabic legal text and present a new dataset of over 27,000 Moroccan legal cases with seven categories. Our methodology implements a segment-based approach to overcome the token limitations of transformer models, processing document segments individually before aggregating embeddings to create complete document representations. Four deep learning architectures are then used to classify those documents. Experimental evaluations demonstrate that MARBERTv2 combined with Gated Recurrent Unit (GRU) architecture achieves superior performance with 95.01% accuracy and Matthews Correlation Coefficient (MCC) of 0.9090.

Objective To evaluate the value of MRI dynamic contrast-enhanced imaging combined with DWI in the differential diagnosis of benign and malignant breast tumors. Methods From October, 2017 to October, 2018, the clinical data of 96 patients (total 109 lesions) with breast tumor were collected retrospectively. All the patients were examined by MRI dynamic contrast-enhanced imaging, DWI and biopsies after admission. Surgical and pathological diagnosis was taken. The morphological features of benign and malignant breast tumors, such as uniformity, boundary and morphology, were compared. According to the TIC curve and ADC value, MRI dynamic contrast enhanced imaging combined with DWI in the diagnosis of benign and malignant breast tumors was evaluated. The accuracies, specificities and sensitivities of MRI dynamic contrast-enhanced imaging and DWI alone and their combination in the diagnosis of benign and malignant breast tumors were evaluated by using biopsy and pathology as the gold standard . Results The enhancement of malignant tumor of breast was not uniform; the boundary was not clear; and the proportion of irregular shape was higher than that of benign breast tumor (P<0.05). The accuracy, specificity and sensitivity of MRI combined with DWI in the diagnosis of breast malignant tumors were higher than those of ADC and the TIC curve, with statistical differences (all P<0.05). Conclusion MRI dynamic contrast-enhanced imaging combined with DWI has important value in the differential diagnosis of benign and malignant breast tumors and provides important basis for clinical treatment. Key words: Breast neoplasms; MRI dynamic contrast-enhanced imaging; DWI; Differential diagnosis of benign and malignant tumors

This study compared popular Deep Learning (DL) architectures to classify machining surface roughness using sound and force data. The DL architectures considered in this study include Multi-Layer Perceptron (MLP), Convolution Neural Network (CNN), Long Short-Term Memory (LSTM), and transformer. The classification was performed on the sound and force data generated during machining aluminum sheets for different levels of spindle speed, feed rate, depth of cut, and end-mill diameter, and it was trained on 30 s machining data (10–40 s) of the machining experiments. Since a raw audio waveform is seldom used in DL models, Mel-Spectrogram and Mel Frequency Cepstral Coefficients (MFCCs) audio feature extraction techniques were used in the DL models. The results of DL models were compared for the training–validation accuracy, training epochs, and training parameters of each model. Although the roughness classification by all the DL models was satisfactory (except for CNN with Mel-Spectrogram), the transformer-based modes had the highest training (>96%) and validation accuracies (≈90%). The CNN model with Mel-Spectrogram exhibited the worst training and inference accuracy, which is influenced by limited training data. Confusion matrices were plotted to observe the classification accuracy visually. The confusion matrices showed that the transformer model trained on Mel-Spectrogram and the transformer model trained on MFCCs correctly predicted 366 (or 91.5%) and 371 (or 92.7%) out of 400 test samples. This study also highlights the suitability and superiority of the transformer model for time series sound and force data and over other DL models.

Permittivity is one of the properties of a material that shows transmission of an external electric field. The study is going to determine the permittivity of urine for patients with benign breast tumour and patients with malignant breast tumuor. Samples of urine were collected from 20 subjects with benign breast tumour and 20 subjects with malignant breast tumour. The study determines the significant differences in permittvity between patients with benign breast tumour and patients with malignant breast tumour. The result showed that there were significant differences in permittivity between these groups of patients at certain frequencies.