Our Lab Publishes Two New AI-for-Healthcare Studies

Our lab has published two new AI-for-healthcare studies, both led by first author Majid Behzadpour. These studies were conducted in collaboration with Dr. Bengie L. Ortiz, a Texas Tech University alumnus, along with Ebrahim Azizi and Dr. Kai Wu.

The first paper, “A Novel Deep Learning Approach for Breast Tumor Applications Using Histopathological Images,” was published in IEEE SoutheastCon 2026. This study develops a deep-learning framework for breast tumor classification using histopathological images, aiming to improve the accuracy and reliability of AI-assisted cancer diagnosis. By leveraging modern convolutional neural network architectures and strategies to address data imbalance, the work demonstrates the potential of AI tools to support pathology image analysis and improve decision-making in breast cancer applications.

The second paper, “Enhancing Brain Tumor Segmentation Using Channel Attention and Transfer Learning,” was published in Biomedical Physics & Engineering Express. This study focuses on automated brain tumor segmentation from medical imaging data by integrating transfer learning, channel attention, and multiscale feature extraction into an enhanced deep-learning architecture. The proposed method aims to improve the precision of tumor-region identification, which is important for diagnosis, treatment planning, and monitoring in clinical practice.

Since our lab was established, AI for healthcare has emerged as an important new research direction, complementing our broader strengths in magnetic sensing, biomedical imaging, and translational engineering. These two papers represent an early step in this growing research portfolio, with several additional AI-for-healthcare studies currently under development.