Accelerating research on 3D medical image classification and regression

This thesis describes the development and evaluation of deep learning approaches for analyzing three-dimensional medical images, with a particular focus on thoracic CT scans. The work emphasizes practical clinical applications while advancing reproducible research practices in medical image analysis, particularly through public datasets, standardized evaluation frameworks, and openly available implementation code. It introduces a method that can estimate global measurements while simultaneously determining regional contributions, demonstrated through applications in COVID-19 severity assessment and pulmonary function testing. The research presents a systematic evaluation of algorithm components for automatic COVID-19 grading from CT. It describes a medical image analysis challenge structure aimed at producing reusable methods that can be trained on private datasets and shows the viability of this challenge structure through a challenge for classifying severe COVID-19 from CT scans. To promote development of more generalizable solutions, a comprehensive database for 3D medical image classification is introduced, featuring standardized data formats and evaluation methods across multiple imaging modalities and anatomical regions.