Geometric Deep Learning for Medical Image Processing Problems
Time: Fri 2024-11-29 09.00
Location: T2 (Jacobssonsalen), Hälsovägen 11C, Huddinge
Video link: https://kth-se.zoom.us/j/62762467727
Language: English
Subject area: Medical Technology
Doctoral student: Fabian Sinzinger , Medicinsk avbildning, Karolinska Institute
Opponent: Professor Thomas Schultz, University of Bonn
Supervisor: Professor Rodrigo Moreno, Medicinsk avbildning; Docent Joana Braga Pereira, Institutionen för klinisk neurovetenskap, Karolinska Institutet; Professor Örjan Smedby, Medicinsk avbildning
QC 2024-11-06
Abstract
This thesis consists of four studies, each suggesting incorporating geometric deep-learning methods in medical image-processing pipelines.
The rationale here is that a) conventional Deep learning (DL) models for medical imaging depend highly on the quality and quantity of training data, and b) medical images commonly represent structures with intrinsic geometrical properties that standard DL models do not necessarily respect.
The first study focuses on predicting stiffness tensors from micro-CT trabecular bone scans. This prediction task requires learning from the complex structures of trabecular bone with limited data available. Our proposed model uses a spherical convolutional neural network (SphCNN) for this purpose. The second study investigates lung cancer survival rate prediction based on image-based features. We evaluate a proposed SphCNN-based pipeline using CT images of non-small cell lung cancer. The third study centres on the stability of the streamline tractography algorithm under arbitrary 3D rotations. We propose integrating an SE(3)-equivariant transformer model into the tractography framework to preserve rotational equivariance. The fourth study evaluates a structural connectivity pipeline in combination with tractography filtering, subsequent classification and analysis. The pipeline is evaluated based on its ability to identify group differences in brain connectivity related to Parkinson's disease.