Search results for: Seo-Yun Choi

Authors: Hyohun Kim, Dongwha Shin, Yeonseok Kim, Ji-Su Ahn, Kensuke Nakamura, Dongeun Choi, Byung-Woo Hong

Abstract:

Artefacts are commonly encountered in the imaging process of clinical computed tomography (CT) where the artefact refers to any systematic discrepancy between the reconstructed observation and the true attenuation coefficient of the object. It is known that CT images are inherently more prone to artefacts due to its image formation process where a large number of independent detectors are involved, and they are assumed to yield consistent measurements. There are a number of different artefact types including noise, beam hardening, scatter, pseudo-enhancement, motion, helical, ring, and metal artefacts, which cause serious difficulties in reading images. Thus, it is desired to remove nuisance factors from the degraded image leaving the fundamental intrinsic information that can provide better interpretation of the anatomical and pathological characteristics. However, it is considered as a difficult task due to the high dimensionality and variability of data to be recovered, which naturally motivates the use of machine learning techniques. We propose an image restoration algorithm based on the deep neural network framework where the denoising auto-encoders are stacked building multiple layers. The denoising auto-encoder is a variant of a classical auto-encoder that takes an input data and maps it to a hidden representation through a deterministic mapping using a non-linear activation function. The latent representation is then mapped back into a reconstruction the size of which is the same as the size of the input data. The reconstruction error can be measured by the traditional squared error assuming the residual follows a normal distribution. In addition to the designed loss function, an effective regularization scheme using residual-driven dropout determined based on the gradient at each layer. The optimal weights are computed by the classical stochastic gradient descent algorithm combined with the back-propagation algorithm. In our algorithm, we initially decompose an input image into its intrinsic representation and the nuisance factors including artefacts based on the classical Total Variation problem that can be efficiently optimized by the convex optimization algorithm such as primal-dual method. The intrinsic forms of the input images are provided to the deep denosing auto-encoders with their original forms in the training phase. In the testing phase, a given image is first decomposed into the intrinsic form and then provided to the trained network to obtain its reconstruction. We apply our algorithm to the restoration of the corrupted CT images by the artefacts. It is shown that our algorithm improves the readability and enhances the anatomical and pathological properties of the object. The quantitative evaluation is performed in terms of the PSNR, and the qualitative evaluation provides significant improvement in reading images despite degrading artefacts. The experimental results indicate the potential of our algorithm as a prior solution to the image interpretation tasks in a variety of medical imaging applications. This work was supported by the MISP(Ministry of Science and ICT), Korea, under the National Program for Excellence in SW (20170001000011001) supervised by the IITP(Institute for Information and Communications Technology Promotion).

Keywords: auto-encoder neural network, CT image artefact, deep learning, intrinsic image representation, noise reduction, total variation

Procedia PDF Downloads 190

Authors: Liza L. S. Choi

Abstract:

Organizational burnout in higher education presents a critical challenge, undermining faculty well-being and institutional effectiveness. This study adopts a systemic perspective, addressing burnout through evidence-based strategies beyond individual coping mechanisms. Utilizing a meta-synthesis of existing literature, the author examines the underlying causes of burnout through the lenses of relational leadership, interpretivist theory, nudge theory, and the ADKAR model. The methodology synthesizes secondary data from peer-reviewed research, comprehensively analyzing key contributors to burnout, including excessive workloads, inadequate leadership, insufficient resources, and the absence of psychological safety. Key findings reveal that addressing burnout requires multi-faceted interventions. Effective implementation begins with leadership training programs grounded in relational leadership principles. These programs empower leaders to build trust by acknowledging and addressing faculty's unique challenges, such as workload inequities and insufficient support. For example, leaders can utilize interpretivist approaches to collect qualitative feedback through focus groups or anonymous surveys, providing actionable insights into the lived experiences of faculty. Institutions should establish policies encouraging open communication and normalizing feedback mechanisms to promote psychological safety. These initiatives include regular town halls, anonymous feedback portals, and structured team-building activities. They create environments where faculty feel supported and valued, reducing the stigma of voicing concerns. Drawing inspiration from successful practices in the healthcare sector, the author advocates for adopting an Associate Vice President (AVP) of Wellness role to lead organizational well-being initiatives. This role would centralize efforts to address faculty burnout and job satisfaction, ensuring alignment across departments and breaking down silos of operation. By fostering cross-departmental collaboration, this approach can lead to more integrated and efficient solutions, maximizing resource utilization and enhancing institutional resilience. The ADKAR model offers a structured framework for managing organizational change, emphasizing Awareness, Desire, Knowledge, Ability, and Reinforcement. Specific applications include facilitating workshops to raise awareness of burnout's impact, providing professional development programs that enhance faculty time management skills, and embedding well-being practices—such as flexible scheduling and equitable resource distribution—into institutional policies. Nudge theory further supports these efforts by employing subtle cues, such as reminders and default options, to encourage healthier work habits and foster collaboration. Finally, institutions should regularly evaluate the effectiveness of these interventions by implementing metrics such as faculty engagement scores, turnover rates, and utilization of wellness resources. By adopting a holistic and scalable framework that includes the AVP Wellness role and eliminates operational silos, this study provides academic institutions with practical tools to enhance morale, foster collaboration, and build resilience, ultimately addressing organizational burnout and creating a supportive educational environment.

Keywords: higher education, organizational burnout, relational leadership, culture of well-being and engagement

Procedia PDF Downloads 9