• Journal of the Korean Society of Marine Environment & Safety
• /
• v.24 no.2
• /
• pp.146-156
• /
• 2018

The ship's chart system was changed from the use of paper chart to the ENC (Electronic Navigational Chart) using ECDIS (Electronic Chart Display and Information System). The introduction of ENC in ships is necessary for ship automation and for the digitalizing of data and integration of information, but unexpected various problems have occurred and are posing a great threat to safe navigation in the transitional period when the new system has been applied to the sea. In this paper, to assess whether ECDIS contributes to the safety of navigation for its intended purposes as new navigation equipment, a usability test of ECDIS was conducted on masters and crew who have used ECDIS on ocean-going vessels. The result was verified with a paired sample T-test, and it was significantly analyzed with the effectiveness of a simplified task; cost efficiency was decreased since ECDIS was used. By analyzing 'MSC.1/Circ.1503 ECDIS - Guidance for good practice', we found that the effects of the maintenance of ECDIS software, operating anomalies identified within ECDIS, differences between raster chart display system (RCDS) and ECDIS, and matters of identification were compounded by the overlapping information on the safety of ships. The anomalies were also grouped according to their characteristics, and we proposed suitable improvements accordingly. The reason for the reduction in efficiency in the usability test was that the problems with ECDIS were intended to be solved only with the careful use of navigational officers who did not have systematic solutions. To solve these problems, the maintenance of software, the improvement of ECDIS anomalies, the reliable ENC issuance including the global oceans, and S-mode development are a priority.

• Korean Journal of Radiology
• /
• v.21 no.7
• /
• pp.869-879
• /
• 2020

Objective: To evaluate the performance of a convolutional neural network (CNN) model that can automatically detect and classify rib fractures, and output structured reports from computed tomography (CT) images. Materials and Methods: This study included 1079 patients (median age, 55 years; men, 718) from three hospitals, between January 2011 and January 2019, who were divided into a monocentric training set (n = 876; median age, 55 years; men, 582), five multicenter/multiparameter validation sets (n = 173; median age, 59 years; men, 118) with different slice thicknesses and image pixels, and a normal control set (n = 30; median age, 53 years; men, 18). Three classifications (fresh, healing, and old fracture) combined with fracture location (corresponding CT layers) were detected automatically and delivered in a structured report. Precision, recall, and F1-score were selected as metrics to measure the optimum CNN model. Detection/diagnosis time, precision, and sensitivity were employed to compare the diagnostic efficiency of the structured report and that of experienced radiologists. Results: A total of 25054 annotations (fresh fracture, 10089; healing fracture, 10922; old fracture, 4043) were labelled for training (18584) and validation (6470). The detection efficiency was higher for fresh fractures and healing fractures than for old fractures (F1-scores, 0.849, 0.856, 0.770, respectively, p = 0.023 for each), and the robustness of the model was good in the five multicenter/multiparameter validation sets (all mean F1-scores > 0.8 except validation set 5 [512 x 512 pixels; F1-score = 0.757]). The precision of the five radiologists improved from 80.3% to 91.1%, and the sensitivity increased from 62.4% to 86.3% with artificial intelligence-assisted diagnosis. On average, the diagnosis time of the radiologists was reduced by 73.9 seconds. Conclusion: Our CNN model for automatic rib fracture detection could assist radiologists in improving diagnostic efficiency, reducing diagnosis time and radiologists' workload.