Medical imaging is one of the major tools that have enriched medical sciences in both function and pathology modeling. Computed tomography (CT) is the most widely used imaging modality in clinical practice. Our research of multiscale (macro and micro) structures of lung and thoracic diseases using synchrotron radiation- micro-computed tomography (SR-CT) and commercial high resolution CT images, allows elucidation of microstructures and development of detection and diagnosis systems. To analyze microstructure of acinus region with isotropic spatial resolution, we developed a method that segments acinar and subacinar airspaces by SR-CT. Results demonstrate that the proposed method can extract several acinar airspaces. We develop cancer computer-aided detection/diagnosis (CADe/CADx) systems using CT images based on multidisciplinary computational anatomy models that support clinicians to detect early-stage cancers, to determine risk-adaptive treatments, and to diagnose various thoracic diseases. We describe overview of our project and potential benefits of implementing our CAD systems clinically.
