Automatic orbital segmentation using deep learning-based 2D U-net and accuracy evaluation: A retrospective study.

The purpose of this study was to verify whether the accuracy of automatic segmentation (AS) of computed tomography (CT) images of fractured orbits using deep learning (DL) is sufficient for clinical application. In the surgery of orbital fractures, many methods have been reported to create a 3D anatomical model for use as a reference. However, because the orbit bone is thin and complex, creating a segmentation model for 3D printing is complicated and time-consuming. Here, the training of DL was performed using U-Net as the DL model, and the AS output was validated with Dice coefficients and average symmetry surface distance (ASSD). In addition, the AS output was 3D printed and evaluated for accuracy by four surgeons, each with over 15 years of clinical experience. One hundred twenty-five CT images were prepared, and manual orbital segmentation was performed in all cases. Ten orbital fracture cases were randomly selected as validation data, and the remaining 115 were set as training data. AS was successful in all cases, with good accuracy: Dice, 0.860 ± 0.033 (mean ± SD); ASSD, 0.713 ± 0.212 mm. In evaluating AS accuracy, the expert surgeons generally considered that it could be used for surgical support without further modification. The orbital AS algorithm developed using DL in this study is extremely accurate and can create 3D models rapidly at low cost, potentially enabling safer and more accurate surgeries.

Correction to: Ethical Perspectives of Japanese Engineers on Ambient Assisted Living Technologies: Semi-structured Interview.

[This corrects the article DOI: 10.1007/s41649-018-0053-0.].

Ethical Perspectives of Japanese Engineers on Ambient Assisted Living Technologies: Semi-structured Interview.

Ambient assisted living (AAL) technologies are expected to solve a significant number of problems related to elderly care. However, in Japan, limited discourse on the ethical issues concerning their application is hindering the spread of AAL technologies. Against this background, this study explores the ethical perspectives of AAL technology engineers in Japanese companies and the circumstances influencing their perspectives. A qualitative study using semi-structured interviews was conducted. Nineteen Japanese AAL-technology companies were contacted, and nine of them and their engineers responded to the interviews. The contents of the interviews were analyzed with thematic analysis which showed that the engineers had ethical concerns about their products as follows: (1) safety and related conflicts, (2) acceptance of the technology, (3) dependence on the technology, (4) accident liability, (5) fair access to the technologies, and (6) privacy. In relation to these issues, they identified as company employees with regard to the following: responding to social needs, having many users, and cost reduction. They also mentioned being influenced by the Japanese national program for AAL-technology promotion. The engineers experienced dilemmas between the various stakeholders' interests and they hoped that ethical guidelines for developing AAL technologies would resolve such dilemmas. In conclusion, Japanese AAL-technology engineers tackle ethical issues with regard to the application of their products. The engineers hope for the establishment of guidelines for the ethically responsible development of AAL technologies. The guidelines need to be established and implemented in an interactive manner, in order to avoid their being reduced to a bureaucratic formality.