Medical image analysis at the Biomedical Imaging Division at KTH
Abstract
Description: This project brings together two sub-projects from the KTH Biomedical Imaging Department that utilize GPUs for artificial intelligence. Here is a brief overview:
1. Deep Learning-Based Breast Image Analysis (PhD student Zhikai Yang). Objectives: A) Detect, segment, and classify breast cancer images using artificial intelligence. B) Image synthesis and translation of breast cancer images. C) Image reconstruction from CT and DBT using primal-dual neural networks. D) Generate reports from breast imaging.
2. Generative Models for Diffusion MRI (PhD student Sanna Persson). Objectives: To estimate diffusion MRI data with a given b-value (scanning parameter) from images taken at different b-values using a generative model. These images will be used to predict the mechanical properties of brain tissue.
All sub-projects use anonymized data, free of sensitive information or synthetic data.
Impact: All sub-projects aim to improve image quality, increase accuracy, or add additional information that clinicians may use in the future, potentially benefiting the healthcare system and society as a whole.
Continuation Project: This is a continuation of Berzelius-2025-212.
Relationship with KAW strategic initiatives: The two doctoral students in this program are affiliated with WASP and are part of the WASP Graduate School.
