Deep learning: Integrating artificial intelligence into the sonography curriculum

In recent times, machine learning and deep learning have quickly risen to prominence as highly effective instruments across a multitude of domains, encompassing areas such as image and speech interpretation, the processing of natural language, and even applications within the medical field. This paper offers an examination of the methodologies and practical uses of both machine learning and deep learning, detailing their respective advantages and disadvantages, alongside their prospective future trajectories. Furthermore, we delve into the inherent challenges linked with these technologies, such as concerns about data confidentiality, ethical questions, and the imperative for transparency within their operational decision-making frameworks. As two of the most transformative technologies within the artificial intelligence sphere, machine learning and deep learning have garnered significant popularity lately, largely due to their capacity for generating predictions, scrutinizing extensive datasets, and yielding insights previously unattainable. This document will investigate the fundamental principles of machine learning and deep learning, their distinguishing features, their varied applications, and their influence across different industrial sectors. The way we engage with technology is being fundamentally reshaped by machine learning and deep learning, which are also unlocking novel avenues for innovation. These technologies have already exerted considerable effects in numerous industries and possess the capability to continue revolutionizing our world. This review delivers a thorough overview of the core concepts of machine learning and deep learning, their differences, their applications, and their broader societal impact. By concentrating on contemporary literature and research, this article endeavors to foster a deeper comprehension of the potential held by machine learning and deep learning and their ramifications for the times to come.

Deep learning is a fast flattering highest development in the machine learning technique leading to augment performance in diverse medical applications. The tributary artificial intelligence is rapidly becoming metamorphic in the domain of Healthcare Technology rendering facility to analyze the medical data with high rapidity and exactness. Due to the overwhelming development of artificial intelligence (AI), the contemporary encroachments of deep learning employing advanced and futuristic deep learning methods has become a vivacious research domain for processing medical data in the health care industries. This paper presents a complete analysis about the deep structured learning based methods used in medical image analysis and also elucidate about the advancement of convolutional neural network which is a major class of deep neural networks used in medical image processing. It also gives insight about the fundamentals of deep learning methods and reviews in image interpretation. It also explains about the implementation of an integrated framework for medical image synthesis combining Speckle GAN and Di-Conv-AE-Net.

Deep learning algorithms can be used to design systems that report data on patients and deliver warnings to medical applications or electronic health information if there are changes in the patient's health. These systems could be created using deep Learning. This helps verify that patients get the proper effective care at the proper time for each specific patient. A healthcare decision support system was presented using the Internet of Things and deep learning methods. In the proposed system, we examined the capability of integrating deep learning technology into automatic diagnosis and IoT capabilities for faster message exchange over the Internet. We have selected the suitable Neural Network structure (number of best-hidden layers and activation function classes) to construct the e-health system. In addition, the e-health system relied on data from doctors to understand the Neural Network. In the validation method, the total evaluation of the proposed healthcare system for diagnostics provides dependability under various patient conditions. Based on evaluation and simulation findings, a dual hidden layer of feed-forward NN and its neurons store the tanh function more effectively than other NN. To overcome challenges, this study will integrate artificial intelligence with IoT. This study aims to determine the NN's optimal layer counts and activation function variations.

Problem The task of this project was to develop, implement, and evaluate a training program for lay preachers in the Seventh-day Adventist churches within the district of Fort Washington, New York, where the author of this document has served as pastor since 2014. Given that this missionary district comprises three churches (Fort Washington, Washington Avenue, and Luz y Esperanza), it is impossible for the pastor to always preach in every one of those congregations, Therefore, the preaching responsibility falls on the shoulders of church elders and other lay preachers. Pastoral observation indicates that, out of the 400 church members who attend weekly worship services, only fifteen participated in the quarterly preaching roll, and many of them did not have an adequate level of training in preaching. Methodology In order to fulfill the purpose of this research project, a study on preaching and related issues was undertaken in biblical literature, in the writings of Ellen White, and in contemporary literature. An analysis of the immediate context (the Seventh-day Adventist churches of Fort Washington, Washington Avenue and Luz y Esperanza) completed the theoretical platform for the design, implementation, and evaluation of a training program on preaching. Direct observation and surveys were used to evaluate the results of the project. Results A major contribution of this project was that it facilitated the design, implementation, and evaluation of a training program for lay preachers within the district of Fort Washington. The final assessment reveals that the participants significantly increased their preaching skills and their knowledge about preaching. From the total of 25 participants, 15 received a score greater than 35 (from a total of 40 points possible) in the final assessment. The program was received by participants with great interest, and it helped to bring about considerable improvement in the quality of preaching in the district of Fort Washington. The program also made it possible to add 10 new names to the preaching roll, which has brought variety to the preaching program, and it has also made the pastor’s burden a bit easier. After finishing the project, many of the preachers continued to use the abilities provided during the training, and most of them adopted the thematic sermon as their preferred model for the design and delivery of sermons. Conclusions The results of this project confirm what the Bible and contemporary Christian literature indicate: a training program on preaching has the potential of bringing about a positive impact on local congregations where leaders might feel the need for it, as it happened in the district where this project was implemented.

This paper investigates the vision-based autonomous driving with deep learning and reinforcement learning methods. Different from the end-to-end learning method, our method breaks the vision-based lateral control system down into a perception module and a control module. The perception module which is based on a multi-task learning neural network first takes a driver-view image as its input and predicts the track features. The control module which is based on reinforcement learning then makes a control decision based on these features. In order to improve the data efficiency, we propose visual TORCS (VTORCS), a deep reinforcement learning environment which is based on the open racing car simulator (TORCS). By means of the provided functions, one can train an agent with the input of an image or various physical sensor measurement, or evaluate the perception algorithm on this simulator. The trained reinforcement learning controller outperforms the linear quadratic regulator (LQR) controller and model predictive control (MPC) controller on different tracks. The experiments demonstrate that the perception module shows promising performance and the controller is capable of controlling the vehicle drive well along the track center with visual input.

Deep learning-assisted digital pathology has demonstrated the potential to profoundly impact clinical practice, even surpassing human pathologists in performance. However, as deep neural network (DNN) architectures grow in size and complexity, their explainability decreases, posing challenges in interpreting pathology features for broader clinical insights into physiological diseases. To better assess the interpretability of digital microscopic images and guide future microscopic system design, we developed a novel method to study the predictive feature length-scale that underpins a DNN’s predictive power. We applied this method to analyze a DNN’s capability in predicting brain metastasis from early-stage non-small-cell lung cancer biopsy slides. This study quantifies DNN’s attention for brain metastasis prediction, targeting features at both the cellular scale and tissue scale in H&E-stained histological whole slide images. At the cellular scale, the predictive power of DNNs progressively increases with higher resolution and significantly decreases when the resolvable feature length exceeds 5 microns. Additionally, DNN uses more macro-scale features associated with tissue architecture and is optimized when assessing visual fields greater than 41 microns. Our study computes the length-scale requirements for optimal DNN learning on digital whole-slide microscopic images, holding the promise to guide future optical microscope designs in pathology applications and facilitating downstream deep learning analysis.

Considering the nonspecific nature of gastrointestinal complaints and the broad differentials of gastrointestinal symptomatology, imaging plays a vital role in the formulation of diagnoses. As a result, artificial intelligence (AI) tools have emerged to assist radiologists in the interpretation of gastrointestinal imaging and to mitigate diagnostic errors. Among the main subtypes of AI applied in this field is deep learning (DL), a subfield of machine learning (ML) that uses artificial neural networks to analyze data and has proven to be superior to traditional ML methods in radiologic imaging analysis. In this review, we discuss DL applications in gastrointestinal imaging across different modalities, including x-ray imaging, ultrasonography, computed tomography, magnetic resonance tomography, and positron emission tomography. Moreover, we outline the challenges and ethical considerations facing the growing role of AI in clinical practice.

The Early Intervention and Mechanical Engineering (EIME) project provides real-world engineering design experience to undergraduate engineering students while significantly enhancing the services provided to children with special needs in the region surrounding Tennessee Technological University (Upper Cumberland region). These enhanced services are provided through a mutually beneficial collaboration between early intervention and engineering at Tennessee Tech. Engineering students engage in this project as part of a Design of Machinery Course. Student teams are matched with children with needs for novel applications of adaptive and assistive technology to facilitate transitioning of children from early intervention to preschool programs and inclusive environments. The projects are selected to emphasize motion control tasks. Examples include improved mobility, exercise, adaptations for feeding and everyday functioning, and interactive play. The project serves the engineering program by providing real-world design experiences as well as resources to develop and test projects. This paper will describe how the project is integrated into the design of machinery curriculum and present several examples of typical projects. Assessment of student outcomes relative to design and learning experience will be discussed. The paper will conclude with lessons learned and recommendations for future implementation of this project.

This study investigates the effectiveness of Artificial Intelligence (AI) and Deep Learning (DL) tools in enhancing academic journal writing skills among students in the Arabic Language Education program at UIN Maulana Malik Ibrahim Malang. Utilizing a mixed-methods approach within a quasi-experimental design, the research involved 90 final-year students divided into experimental and control groups. The intervention group employed AI-based tools such as ChatGPT, Grammarly, and Quilbolt throughout the writing process, while the control group relied on conventional methods. Data were collected through pre-test and post-test assessments, reflective journals, and structured questionnaires. Quantitative results showed a statistically significant improvement in writing performance among students who used AI tools, with large effect sizes (Cohen’s d > 1.0). Qualitative findings revealed that students engaged critically with AI outputs, valued teacher feedback, and developed ethical awareness regarding authorship and originality. The integration of AI tools also increased student confidence, enhanced writing fluency, and promoted autonomous learning. However, limitations in semantic precision and rhetorical fit especially in theology-specific content necessitated human revision. These findings affirm the role of AI as a cognitive scaffold in academic writing and highlight the need for culturally responsive, ethically guided AI integration in language teacher education.Keywords: Artificial Intelligence, Academic Writing, Deep Learning, Arabic Education, Cognitive Scaffold

The study aims to develop an integrated learning model that harmonizes advanced artificial intelligence technology with fundamental Islamic educational values and formulate an ethical framework guiding deep learning implementation in Islamic education contexts. This study employs a qualitative approach utilizing library research design to explore digital transformation impacts on Islamic education learning methods. Data collection was conducted through systematic exploration of contemporary academic literature published in accredited national and international journals, conference proceedings, and research reports concerning digital transformation in Islamic education and deep learning applications in educational contexts. Secondary data obtained were analyzed using content analysis methods with four sequential stages: identification and categorization of data based on relevance to digital transformation impacts in Islamic education, codification of primary findings regarding deep learning implementation, interpretation of emerging patterns and themes, and synthesis of findings to develop conceptual frameworks. The research reveals that Islamic educational institutions possess adaptive capacity to integrate advanced technology without sacrificing fundamental values. The developed integrated model encompasses four key components: adaptive technological infrastructure enabling personalized learning experiences, educator capacity development programs focusing on digital literacy and pedagogical innovation, technology-enriched curriculum design maintaining alignment with Islamic educational objectives, and an ethical framework based on Islamic principles including justice (adl), trust (amanah), and public interest (maslahah).

Applying deep learning in digital breast tomosynthesis for automatic breast cancer detection: A review.

Artificial intelligence may improve accuracy of myocardial perfusion imaging (MPI) but will likely be implemented as an aid to physician interpretation rather than an autonomous tool. Deep learning (DL) has high standalone diagnostic accuracy for obstructive coronary artery disease (CAD), but its influence on physician interpretation is unknown. We assessed whether access to explainable DL predictions improves physician interpretation of MPI. Methods: We selected a representative cohort of patients who underwent MPI with reference invasive coronary angiography. Obstructive CAD, defined as stenosis ≥50% in the left main artery or ≥70% in other coronary segments, was present in half of the patients. We used an explainable DL model (CAD-DL), which was previously developed in a separate population from different sites. Three physicians interpreted studies first with clinical history, stress, and quantitative perfusion, then with all the data plus the DL results. Diagnostic accuracy was assessed using area under the receiver-operating-characteristic curve (AUC). Results: In total, 240 patients with a median age of 65 y (interquartile range 58-73) were included. The diagnostic accuracy of physician interpretation with CAD-DL (AUC 0.779) was significantly higher than that of physician interpretation without CAD-DL (AUC 0.747, P = 0.003) and stress total perfusion deficit (AUC 0.718, P < 0.001). With matched specificity, CAD-DL had higher sensitivity when operating autonomously compared with readers without DL results (P < 0.001), but not compared with readers interpreting with DL results (P = 0.122). All readers had numerically higher accuracy with CAD-DL, with AUC improvement 0.02-0.05, and interpretation with DL resulted in overall net reclassification improvement of 17.2% (95% CI 9.2%-24.4%, P < 0.001). Conclusion: Explainable DL predictions lead to meaningful improvements in physician interpretation; however, the improvement varied across the readers, reflecting the acceptance of this new technology. This technique could be implemented as an aid to physician diagnosis, improving the diagnostic accuracy of MPI.

It is our great pleasure to welcome you to the 7th European Interactive Television Conference -- EuroITV2009. EuroITV2009 is a forum for professionals not only from Europe, but from all over the world who are interested in, work with and do research on all aspects of interactive television. This year the conference is held in the lively university town of Leuven, Belgium on 3, 4 and 5 June 2009. This annual conference features state-of-the-art academic as well as practitioner's work on different aspects of interactive television, e.g. IPTV, mobile TV, digital content production, entertainment computing, usability and user experience evaluation, and future technologies and systems. EuroITV2009 is the seventh edition of the EuroITV conference series, which started in 2003 and has since been growing steadily. The conference has been held twice in Brighton (UK), and subsequently in Aalborg (Denmark), Athens (Greece), Amsterdam (The Netherlands) and Salzburg (Austria). The theme of the 7th European Interactive Television Conference is 'Networked Television.' Interactive television is becoming one piece in a bigger puzzle of different interconnected devices. This not only has technical implications, but also impacts users and television viewers. Viewers use their cell phones to send text messages to broadcasters, they use their PC to download movies that can then be watched on the big television screen, social networks are including TV content and iTV is including social network features, secondary screens can be used to control the content on television, etc. Instead of an age of device convergence, we see that in practice we're heading towards device divergence. The conference addresses how we should shift our focus from looking at iTV as a system that functions on itself, to iTV as part of a bigger set of networked devices and communities, and explores how this impacts users as well as technologies. We received 91 full and short paper submissions, of which 36 (40%) were accepted and published in these main proceedings, next to numerous submissions in the other categories of which the accepted papers can be found in the adjunct proceedings. This resulted in a very diverse conference program, consisting of three keynote speakers, five tutorials, four workshops, 15 full and 21 short paper presentations, iTV in Industry presentations, poster and demo sessions, and a doctoral consortium attended by six PhD students. The academic and research papers are clustered around three tracks, addressing the multidisciplinary nature of iTV research: Human-Computer Interaction; Social, Media & Economic Studies; and Systems & Enabling Technologies. In the iTV in Industry section, interactive television topics are presented which are especially relevant to the industry concerning amongst others research and development, marketing, business cases, market insights, showcases, case studies, best practices and lessons learned. The conference also features an arts exhibition on the theme of networked television. This arts exhibition is being held for the first time in the EuroITV conference series. The keynote speakers address different aspects of the conference theme 'Networked Television.' Jan Van Bogaert, senior strategy director at Alcatel-Lucent and Bell Labs Fellow, talks about how the connected home redefines the TV experience and argues that networked TVs will become the main interface to a whole new set of home based applications and content delivery mechanisms. Rich Ezekiel, Director of Strategic Partnerships at Yahoo!'s Connected TV group, explains that by combining the key attributes of the Internet, including openness, community and personalization with the power of television, it will be possible to create a revolutionary new Internet experience to allow consumers to access the relevant information and content to enhance their television watching experience. Mr. Ezekiel discusses why past efforts have been unsuccessful and why this Internet-connected TV ecosystem being created and nurtured today will become a technology accepted by millions of TV viewers globally. The third keynote presentation is given by Prof. Dr. Marc Hassenzahl, professor for "Ergonomics and User Experience in Design" at the Folkwang University in Essen, Germany and research manager at MediaCity, Åbo Akademi University, Vaasa, Finland. He discusses current approaches and research into 'Experience' and their potential future application in the domain of iTV and crossmedia products, as they specifically aim at providing an entertaining, positive and enjoyable overall "experience" to its users.

Future robotic systems are likely to include AI-based professional to provide expert advice. For example, AI-based legal experts or judges try to explain the laws, and AI-based medical experts provide medical diagnosis and corresponding prescriptions. DeepFake is a collective of algorithms that aim to replace the face in one source video with the face of another person. The advancements in deep learning has made video manipulation and synthesis much more accessible than before. Thus,what if an AI-based DeepFake synthetic judge tries to explain the law differently and makes offensive decisions, or if a DeepFake synthetic doctor tries to give a wrong diagnosis and prescribes harmful medicines? Effective detection methods are important to combat malicious spread and use of damaging fake media as well as harmful fake robots in future robotic expert systems. This chapter first provides the general background on future robot-based expert systems,and on DeepFake,such as facial manipulation,forged video datasets,and detection techniques. These include 3D modeling and deep-learning-based manipulation techniques,forged video datasets from different sources,and current detection methods. This chapter covers a proposed detection method that utilizes image segmentation as part of the solution.

Liver cancer is one of the main causes of cancer-related mortality globally. It is a rising threat with over 700,000 deaths and 800,000 new cases annually. To tackle this, deep learning (DL) artificial intelligence (AI) tools have been researched extensively to create predictive models that aid in the early diagnosis and classification of liver cancers. The liver, however, is prone to metastasis from various gastrointestinal cancers, making it difficult to correctly classify tumors present in the organ. This paper is a thorough systematic evaluation of several published studies that used deep learning algorithms to diagnose, classify, and predict common liver tumors, including but not limited to Hepatocellular carcinoma and Intrahepatic cholangiocarcinoma. Articles selected in this review have been published between 2016 and 2024 from Google Scholar, Research Gate, Science Direct, IEEE Xplore, Springer Link, and other resources as per the PRISMA guidelines. Amongst these, the highest recorded accuracy was 99.38%, with other studies showing close results at 97% and below. The highest recorded sensitivity was 100%. Selected studies were also analyzed based on their choice of dataset, DL algorithm, and preprocessing techniques. Magnetic resonance imaging and computed tomography (CT) are by far the preferred medium for imaging data because of their high resolution; however, CT is used more often because it’s cheaper and provides a better view of extrahepatic space. Genetic datasets showed great potential in differentiating between primary and secondary liver cancers. Nonetheless, several gaps were identified across the current literature. The problem of accurately differentiating cancer types in the liver still persists. However, the use of 3D imaging datasets aids in this significantly. Though, it is clear that 3D datasets are underutilized. Dynamic imaging is also beneficial and should be considered more often. For future research, we strongly recommend the use of Gaussian Mixture Model, Watershed Transform, Sparsity classification, DLIR and Siamese algorithms as they each showed promising results. Lastly, we have shown a benchmark framework for a predictive AI model that can be referred to develop future models. Though numerous past methods have produced excellent prediction results, the prevalence of liver cancer-related deaths has not yet been reduced. To address the difficulties in the field of cancer prediction, more thorough research is required, along with the development of more efficient decision support systems using deep learning.