野村 行弘

A machine learning-based method using a database of clinical data, such as Computer-Assisted Detection/Diagnosis (CAD), is one of the next key technologies in clinical imaging. The most important issue for machine learning, based on clinical data, is construction of the database, and one of the promising improvements this technology offers is in the field of in-hospital development because of increased data accessibility and periodical updates. This chapter first discusses the database problems in CAD development comprehensively. Then, it introduces the authors' integrated platform, called the Clinical Infrastructure for Radiologic Computation of United Solutions (CIRCUS), for in-hospital research, development, use, and evaluation of clinical image processing. Based on the authors' clinical experience and the data collected through the CIRCUS system, they present research results on the improvement of CAD performance as well as simulated studies for additional learning. Finally, the authors' future plans, including radiologist-CAD collaboration beyond machine learning, are also discussed.