Weiyi Xie successfully defends PhD thesis

On Tuesday August 29 at 12.30, Weiyi Xie successfully defended his PhD thesis on Deep Learning For Treatment Planning In Chronic Obstructive Pulmonary Diseases in the Aula of the Radboud University. We extend our congratulations to Xie on his fantastic achievement and wish him well in his new position at Stryker.

His thesis is devoted to deep learning for treatment planning in chronic pulmonary diseases with chapters summarised as follows:

Chapter 1 introduces chronic obstructive pulmonary disease (COPD) and gives background information on COPD diagnosis and treatment planning.

Chapter 2 presents a novel method using relational two-stage convolution neural networks for segmenting pulmonary lobes in CT images. The proposed method uses a non-local neural network to capture visual and geometric correspondence between high-level convolution features, which represents the relationships between objects and object parts.

Chapter 3 presents a method for labeling segmental airways given a segmented airway tree.

Chapter 4 proposes a novel weakly-supervised segmentation framework trained end-to-end, using only image-level supervision.

Chapter 5 expands on the method outlined in Chapter 4 to predict emphysema subtypes. The proposed algorithm generates high-resolution emphysema segmentation maps to aid in interpreting the prediction process, offering an improved model interpretability compared to the baseline.

Chapter 6 reflects on the thesis’s main findings and contributions. It also analyzes the advances and impact in the field and the existing limitations of the proposed methods and provides a future outlook for research opportunities in the field of deep learning for medical image analysis.

← Back to overview