Development of computer-aided diagnosis or detection (CAD) requires maintenance of a database and collaboration with physicians who can explain the characteristics of the lesion and engineers who can design a program. Mutual communications and the handling of performance are important for efficiently proceeding with the research on a joint basis. While the participation of corporations is key to the commercialization of the outcomes of research, studies will be conducted by each of the corporations, physicians, and engineers, and areas will be developed together cooperatively. It is important to clearly express opinions to corporations when the results of a new initiative are inadequate because a poorly formed opinion and a compliant evaluation cause confusion and result in mistakes later.
In this short article, something about the industry-government-academia and medicine-engineering collaborations in developing CAD is described from the viewpoint of a researcher in engineering side. How to associate with medical doctors in the part of medicine-engineering collaboration and some requirement issues to industry in the part of industry-academia collaboration are mainly presented and discussed based on the author's own experiences, so the readers have to be careful in reading, because it might be hard to generalize.
The Japan Agency for Medical Research and Development (AMED) has been established to serve as an institution dedicated to improving medicine through research and development in Japan. Our goal is to fast-track medical R&D that directly benefits people, not only by extending lifespans, but also by improving quality of life. There are nine translational R&D sections such as medicine, medical devices and regenerative medicine and over three thousands of active research projects. In this paper, we introduce the AMED R&D projects focused on medical devices.
MRI clinical application has been expanded due to its rich image contrast, as MR contrast is sensitive to physiological environment. However, these MR parameters based on the physiological environment are not directly associated with single MR physics parameters. That makes MR engineers/scientist difficult simulate the physiological environment as phantom, and that result in challenge for technical validation of new technology. This challenge is engineering-medical collaboration opportunity in MRI technical development field, where human study is required in the early development phase. In this short article, importance of engineering-medical collaboration in the MRI development is discussed, then some examples of collaboration are presented. Current challenges and future opportunities in the academic-industrial collaboration in MRI development are also discussed from industrial perspective.
Since an appearance of X-ray CT scanner, European and American manufacturers have lead the field in technology and also business while in 20 th century. However we have continued to develop unique advanced CT technologies for a long period, and then we gained a major presence in global market recent years. In this paper, we would like to look back and find a hint of the growth from several examples for coordination between medicine and industry, and also to explore a way of coordination between medicine/engineer/industry.
Aiming to compensate for the lack of case images in computer-aided diagnosis/detection (CAD) development, efforts have been made to artificially create case images by embedding lesions (such as tumors) into lesion-free images. We provide some examples of the usefulness of such images in liver tumor CAD, verified by judgment equipment that was designed using training data including artificial cases. For this study, we created an artificial case database (DB) made up of different variations, in consideration of practical use, proposing combinations and methods for generating optimal performance enhancement to unknown data in CAD. We created learning data for combinations that emphasized a lesion as the artificial case images with a variety of sizes and contrast changes, and we investigated methods of constructing optimal learning data, based on performance of the judgment equipment that we designed against unknown data, and we confirmed its effectiveness. In order to further confirm the generalizability of this technique with regard to application to other regions, we also confirmed that this is effective when applied to breast cancer tumor CAD. Additionally, we also propose using an artificial case DB as a performance evaluation measure for the various types of CAD. That is, for lesions (such as tumors) of standard size and contrast, we believe we can obtain objective evaluation criteria by comparing detection performance in response to quantitative changes in size and brightness.
Various radiation dose quantities have been defined by ICRP (International Commission on Radiological Protection) and ICRU (International Commission on Radiation Units and Measurements) and the dose quantities should be properly used according to the purpose. In radiological practice, modality-specific dose indices are utilized, and the dose indices such as CTDI (computed tomography dose index) and DLP (dose length product) in x-ray CT examinations are used for the evaluation of x-ray output and quality control of CT scanners. The dose quantities such as organ dose and effective dose is used for the dose evaluation for patients in CT examinations. One of the methods of dose evaluation for patients is based on the measurements using small dosimeters implanted in various organ positions within an anthropomorphic phantom. Another method is based on Monte Carlo (MC) simulation of photon interactions within a computational phantom of human body and MC simulation for CT dose estimation requires information on the geometry of a CT scanner, scan parameters, and a computational phantom. This paper describes an outline of radiation dose quantities, dose indices used in CT examinations and methods of dose evaluation for the patients.