Since 2012, Tohoku University Hospital has been preparing for MR image-guided radiotherapy. Although it was much later than expected, from February 28th, 2022, the MR Linac (Elekta Unity) started using clinically as the second institution in Japan. By integrating MRI and Linac, it is possible to (1) visualize soft tissue clearly, enable accurate positioning, and design a treatment plan that matches the condition of the day on the spot, and (2) visualize in real-time during radiation irradiation, it enables to perform highly accurate irradiation against the movement of the tumor due to respiration. However, there are major problems such as re-setting of ROI, creation of dose distribution, approval, verification, etc., which require a lot of time and manpower. Therefore, the number of irradiation patients per day is limited. Unfortunately, there is no addition of medical fees, which can be said to be a major issue in the future.

In recent years, modern artificial intelligence (AI) is one of the most attractive topics in many scientific fields and now developed for real world applications including medical ones. In fact, deep learning, a typical modern AI, for medical image diagnosis has achieved break-through performance that is comparable to human experts. However, deep learning has so-called black-box nature that is one of critical issues for medical applications. In this review, the-state-of-the-art AIs for medical image diagnosis are overviewed with some problems caused by the black-box nature. Then, systems approach will be introduced to investigate the problems and reveal the core mechanism of break-through and drawback. Future direction will be suggested for overcoming the problems.

The purpose of this study is to examine the abdominal X-ray image contrast with additional Cu filtration using Scheffé’s paired comparison method. We obtained abdominal phantom images with different Cu filter thickness after dynamic processing. We measured the image contrast of abdominal phantom images and evaluated them using Scheffé’s paired comparison method. The observers were 7 radiological technologists (2 to 33 years of experience, average 15.6 years). Approximately, there was a maximum of 16 % decreasement in the image contrast when we added 0.3 mm Cu filtration. There was no significant difference in Scheffé’s paired comparison method (95 % confidence interval) . From these results, abdominal X-ray with up to 0.3 mm Cu filtration does not decrease visually significant image contrast. Abdominal X-ray with up to 0.3 mm Cu filtration does not decrease visually image contrast.