A Multi-resolution Coarse-to-Fine Segmentation Framework with Active Learning in 3D Brain MRI

We aim at segmenting small organs (e.g., the pancreas) from abdominal CT scans. As the target often occupies a relatively small region in the input image, deep neural networks can be easily confused by the complex and variable background. To alleviate this, researchers proposed a coarse-to-fine approach [46], which used prediction from the first (coarse) stage to indicate a smaller input region for the second (fine) stage. Despite its effectiveness, this algorithm dealt with two stages individually, which lacked optimizing a global energy function, and limited its ability to incorporate multi-stage visual cues. Missing contextual information led to unsatisfying convergence in iterations, and that the fine stage sometimes produced even lower segmentation accuracy than the coarse stage. This paper presents a Recurrent Saliency Transformation Network. The key innovation is a saliency transformation module, which repeatedly converts the segmentation probability map from the previous iteration as spatial weights and applies these weights to the current iteration. This brings us two-fold benefits. In training, it allows joint optimization over the deep networks dealing with different input scales. In testing, it propagates multi-stage visual information throughout iterations to improve segmentation accuracy. Experiments in the NIH pancreas segmentation dataset demonstrate the state-of-the-art accuracy, which outperforms the previous best by an average of over 2%. Much higher accuracies are also reported on several small organs in a larger dataset collected by ourselves. In addition, our approach enjoys better convergence properties, making it more efficient and reliable in practice.

This study compares the impact of two active learning methods; Problem-Based Learning (PBL), and Project-Oriented Learning (POL) versus the Traditional Lecture (TL) method on learners' ability to differentiate between monocotyledons and dicotyledons based on their morphological and anatomical characteristics. The research used a quasi-experimental design involving 150 students, divided into three groups: two experimental groups subjected to active learning methods and a control group exposed to traditional lectures. The study used mixed research methods to assess the effectiveness of these teaching strategies. Pre and post-test scores were employed to evaluate learners' improvements and observational techniques were employed to analyse classroom engagement and the development of scientific skills. The results indicate that both active learning methods significantly enhanced learner engagement, understanding, and the application of scientific concepts. The PBL and POL groups demonstrated superior critical thinking, collaboration, and problem-solving skills, with the POL group showing the highest improvement in project management and creative thinking. By contrast, the TL group exhibited moderate improvements, primarily in memorization rather than conceptual understanding. These findings support the growing body of literature that advocates for active learning as an effective alternative to traditional teaching methods in science education. Keywords: Active Learning, Problem-Based Learning, Project-Oriented Learning, Traditional Lecture, Monocots, Dicots. DOI: 10.7176/JEP/16-11-20 Publication date: October 30th 2025

Bio-inspired Active Learning method in spiking neural network

The article is devoted to modern approaches to the development of civic competence of young people. The authors of the article pay special attention to active methods of social learning. In the process of developing programs and trainings on the development of civic competence, it is advisable to use such methods of active learning, which in working with students should be: relevant to the target audience, contain innovative components, and meet the requirements of higher education. The article presents the author's socio-psychological program for the development of civic competence of young people using social media and media content. The article presents the author's social and psychological program for the development of civic competence of young people using social media and media content. The main directions of development of civic competence in the program are: 1) reflection on citizenship, experience of interaction with authorities at the national and local levels, 2) development of civic skills, acquisition / renewal of experience in solidarity and civic participation, 3) actualization of readiness to apply the acquired experience (knowledge, skills and abilities) in real situations of interaction. The program uses both traditional methods of active social learning and social media and media content. The method of web-quests is used to update the target and instrumental motives for the use of social media; to master the instrumental skills of constructive interaction with central and local authorities by digital means, as well as an effective means of mastering proactive roles to ensure constructive interaction with government institutions, civic society, groups and communities on social networks. The comics method is used to update individual components of civic competence and diagnose changes in strategies and ways of interacting with public authorities. The proposed program for the development of civic competence has been successfully tested.

Comparative educational outcomes of an active versus passive learning continuing professional development activity on self-management support for respiratory educators: A non-randomized controlled mixed-methods study

Bridging 2D and 3D segmentation networks for computation-efficient volumetric medical image segmentation: An empirical study of 2.5D solutions.

Due to the fact that it is expensive and time-consuming to annotate a large amount of data, the available labeled data to train a deep neural network is usually scarce, resulting in the poor performance of the deep classification network in most cases. In this paper, we propose a novel active learning method to train a competitive deep classification neural network by labeling a limited amount of diverse images. The proposed method advances most of the active learning methods in two aspects. First, active learning is enhanced with a co-auxiliary learning strategy. We use an auxiliary network to provide diverse pseudo-labels for the primary network. The auxiliary network is also adopted to remove a part of redundancy information from the candidate pool of active learning when image predictions of the primary network and the auxiliary network are the same. Meanwhile, the primary network can also provide pseudo-labels to improve the performance of the auxiliary network. Second, we further remove the redundancy within the query samples with multi-level diversity selection. The multi-level diversity strategy not only considers the feature-level diversity but also the class-level diversity with the predictions of the primary network, and it can select both representative and uncertain samples effectively and efficiently from the large-scale data. The extensive experiments on four large-scale datasets show that the proposed method outperforms the state-of-the-art methods.

Metallocene and Single Site Polymers (#1624)

Medical imaging is widely used in the diagnosis and treatment of clinical practice. At present, medical imaging technology has entered a new era of digitalization. In order to solve the scarcity of medical image standard data sets and the high cost of manual labeling, it is necessary to use active learning methods to select the most valuable data from the vast image data pool for labeling which the purpose is to make the labeling costs lower, reduce the pressure on professional physicians and make clinical decision-making easier. This article focuses on mammography medical imaging, analyzes the structure and characteristics of the images, deals with mammography medical imaging data and trains the model using machine learning model, called CSAL (CNN-Seq2Seq-Attention + Active Learning), in order to reduce the loss of image data sequence after graying, and filter out valuable data from the data pool by active learning. This paper uses two different active learning methods and two different data sets for comparative experiments. The finally experimental results achieved satisfactory effort.

Purpose: This research indicates the need to identify the right teaching and learning methods, ways to design teaching and learning methods for lecturers, and students in Vietnam's higher education system. From there, point out the limitations of current teaching methods and the advantages when teachers and learners design their new teaching and learning methods. Methodology: This research uses qualitative and quantitative research methods through interviews about teaching methods of lecturers and student learning methods; evaluation of lecturers and students about the advantages and disadvantages of the current teaching and learning method. Respondents included 1.000 students and 130 lecturers at several universities in the Ho Chi Minh City of Vietnam. Main Finding: Based on these data and analysis, this study shown a new paradigm in developing active teaching and learning methods for lecturers and students, optimal methods for achieving the expectations that teaching strategies and active learning by the instructors and students. Implications/Applications: This study contributes to the development of positive teaching and learning strategies, creating interest, and promoting students' self-study ability. The results will help lecturers, and students build proper teaching and learning strategies, creating funny, development capacity, and creativity of students. Novelty/Originality: The research, analyze and design the essential contents of the strategy development process for both teachers (lecturers) and learners (students). The main contributions of the research are the initial conditions necessary for teachers and students to develop effective teaching and learning strategies for themselves.

Deep learning has achieved great success in the field of computer vision, and the precision in image classification and image detection has surpassed humans. Therefore, this paper combines deep learning and medical image segmentation, focusing on how to improve the accuracy and speed of segmentation algorithm of medical exercise rehabilitation image. Aiming at the shortcomings of traditional medical image recognition methods, a medical exercise rehabilitation image segmentation algorithm based on hierarchical features of convolutional neural networks is proposed, this paper calls it as hierarchical features of convolutional neural networks (HFCNN). The algorithm firstly samples the convolution output of multiple layers in the convolutional neural network to a unified scale and combines them to construct a hierarchical feature. This hierarchical feature combines the structural information of objects contained in the shallow layer of the network with the semantic information of objects contained in the deep layers of the network, so it has a strong ability to express. Secondly, the image can be segmented into multiple super pixels by the super pixel segmentation algorithm. The classifier is trained using the hierarchical features of the super pixel, and then the classification result is mapped back to the pixel. Finally, a fully connected conditional random field algorithm including one-potential potential energy and paired potential energy is constructed. The corresponding energy function is used to smooth the classification result of the pixel, and the regional consistency and continuity of the pixel mark are improved. Compared with many classical convolutional neural network algorithms, this algorithm not only accelerates the network convergence speed, shortens the training time, but also significantly improves the accuracy of segmentation algorithm of medical exercise rehabilitation image, showing good practical value.

DSEU-net: A novel deep supervision SEU-net for medical ultrasound image segmentation

Collaborative filtering is a useful technique for exploiting the preference patterns of a group of users to predict the utility of items for the active user. In general, the performance of collaborative filtering depends on the number of rated examples given by the active user. The more the number of rated examples given by the active user, the more accurate the predicted ratings will be. Active learning provides an effective way to acquire the most informative rated examples from active users. Previous work on active learning for collaborative filtering only considers the expected loss function based on the estimated model, which can be misleading when the estimated model is inaccurate. This paper takes one step further by taking into account of the posterior distribution of the estimated model, which results in more robust active learning algorithm. Empirical studies with datasets of movie ratings show that when the number of ratings from the active user is restricted to be small, active learning methods only based on the estimated model don't perform well while the active learning method using the model distribution achieves substantially better performance.

In recent years, generative adversarial networks (GANs) have gained tremendous popularity for various imaging related tasks such as artificial image generation to support AI training. GANs are especially useful for medical imaging-related tasks where training datasets are usually limited in size and heavily imbalanced against the diseased class. We present a systematic review, following the PRISMA guidelines, of recent GAN architectures used for medical image analysis to help the readers in making an informed decision before employing GANs in developing medical image classification and segmentation models. We have extracted 54 papers that highlight the capabilities and application of GANs in medical imaging from January 2015 to August 2020 and inclusion criteria for meta-analysis. Our results show four main architectures of GAN that are used for segmentation or classification in medical imaging. We provide a comprehensive overview of recent trends in the application of GANs in clinical diagnosis through medical image segmentation and classification and ultimately share experiences for task-based GAN implementations.

Traditionally, the coarse and fine mechanical stages within a dual-stage positioning system are designed separately without consideration about their control performance in dual-stage integration. In this paper, a flexure-based Lorentz motor fine stage is designed concurrently with a simple PID controller to perform the dual-stage positioning, based on the existing coarse stage. The design of fine stage is carried out using a proposed integrated servo-mechanical design approach, where various specifications are considered and formulated as constraints in an optimization problem. Through the approach, both the plant modal parameters and controller parameters of fine stage are concurrently solved. It demonstrates that through suitable mechanical plant design, the fine stage can fulfill various control specifications by only using a simple PID controller, e.g., to compensate sensitivity peak, maintain stability, etc. Meanwhile, the proposed design approach also ensures certain open-loop positioning performance and the decoupling property of coarse/fine stages. The prototype of designed fine stage is fabricated, and experimental investigation indicates that the sensitivity peak is effectively reduced from 14.5 dB of coarse stage to 7.1 dB in the dual-stage system, and the fine stage is able to achieve submicrometer accuracy. The maximal tracking error is also reduced significantly from about 20 μm via the coarse stage to less than 2 μm through dual-stage positioning.