A02-KB102 A Machine Learning Based Framework for Developing Various Computer-assisted Detection System with Generated Image Features

From Multidisciplinary Computional Anatomy
Jump to: navigation, search


  • Primary Investigator
    Mitsutaka Nemoto (Kindai University, Faculty of biology-oriented science and technology, Lecturer)


The purpose of this study is to establish a generalized framework for developing computer-assisted detection (CADe) system automatically. The generalization means the modality- and lesion-free automated development. In the framework, a CADe system is automatically developed from only a data-set, which includes medical images with pixel-by-pixel painted target lesions, by machine learning techniques. It would enable clinicians without expertise in medical image analysis to develop CADe systems to use in their clinical site.

Project Design