Tiny Diffusion, Big Brain: Lightweight Dual-control Stable Diffusion for Brain MRI Synthesis

Serena Pei, School of Engineering, MIT, Cambridge, MA, USA

ABSTRACT

We present a lightweight pipeline using Stable Diffusion v1.5 [7] for generating anatomically accurate brain MRI images depicting tumors. Using a public dataset of 1,426 glioma MRI slices from 233 patients [5,2] we condition image generation on both descriptive text prompts (text input) and visually transformed grayscale MRI slices (visual input). We explore three visual transforms: Gaussian-blurring, checkerboard-masked, and edge-mapped. Inspired by ControlNet [9], our method supports dual conditioning during both training and inference but avoids duplicating the U-Net architecture—significantly reducing memory overhead. This enables training on standard GPUs such as a single 15GB T4 in Google Colab. To assess image realism on synthesized images, we use both qualitative inspection and Fréchet Inception Distance (FID). This model is an important step towards building more flexible, privacy-preserving methods for creating high-quality medical images in low-data, low-memory settings— with potential applications in rare disease research and AI-driven healthcare.

Keywords

Stable Diffusion, ControlNet, healthcare, medical imaging.

Generative Artificial Intelligence in Higher Education: Opportunities, Challenges, and Future Directions

Yanhua Zhong^{1, 2} and Mohd Shafie b. Rosli², ¹Advanced Learning Technology Department, Faculty of Educational Sciences and Technology, Universiti Teknologi Malaysia, 81310 Skudai, Johor Bahru, Johor, Malaysia, ²Institute of Marxism, Ganzhou Polytechnic, Ganzhou, Jiangxi, 341000, China

ABSTRACT

The integration of Generative Artificial Intelligence (GAI) in higher education has garnered significant scholarly attention. This comprehensive review synthesizes current literature to examine the transformative potential, implementation challenges, and future trajectories of GAI in academic settings. Our analysis reveals that GAI offers substantial opportunities for personalized learning, pedagogical innovation, and creative skill development while simultaneously presenting critical challenges related to academic integrity, data privacy, and algorithmic bias. We analyze these developments through three interconnected dimensions: technological applications, stakeholder perceptions, and contextual implementation. The paper concludes by proposing six key research priorities: assessment integrity and pedagogical strategies, ethical frameworks and policy development, teaching-learning process impacts, stakeholder perceptions research, technological enhancements, and future skills preparation. These findings provide both theoretical foundations and practical guidance for the responsible integration of GAI technologies in higher education institutions.

Keywords

Generative Artificial Intelligence, Higher Education, Systematic Review, ChatGPT, Academic Integrity