• Korean Journal of Radiology
• /
• v.24 no.8
• /
• pp.807-820
• /
• 2023

Objective: To assess whether computed tomography (CT) conversion across different scan parameters and manufacturers using a routable generative adversarial network (RouteGAN) can improve the accuracy and variability in quantifying interstitial lung disease (ILD) using a deep learning-based automated software. Materials and Methods: This study included patients with ILD who underwent thin-section CT. Unmatched CT images obtained using scanners from four manufacturers (vendors A-D), standard- or low-radiation doses, and sharp or medium kernels were classified into groups 1-7 according to acquisition conditions. CT images in groups 2-7 were converted into the target CT style (Group 1: vendor A, standard dose, and sharp kernel) using a RouteGAN. ILD was quantified on original and converted CT images using a deep learning-based software (Aview, Coreline Soft). The accuracy of quantification was analyzed using the dice similarity coefficient (DSC) and pixel-wise overlap accuracy metrics against manual quantification by a radiologist. Five radiologists evaluated quantification accuracy using a 10-point visual scoring system. Results: Three hundred and fifty CT slices from 150 patients (mean age: 67.6 ± 10.7 years; 56 females) were included. The overlap accuracies for quantifying total abnormalities in groups 2-7 improved after CT conversion (original vs. converted: 0.63 vs. 0.68 for DSC, 0.66 vs. 0.70 for pixel-wise recall, and 0.68 vs. 0.73 for pixel-wise precision; P < 0.002 for all). The DSCs of fibrosis score, honeycombing, and reticulation significantly increased after CT conversion (0.32 vs. 0.64, 0.19 vs. 0.47, and 0.23 vs. 0.54, P < 0.002 for all), whereas those of ground-glass opacity, consolidation, and emphysema did not change significantly or decreased slightly. The radiologists' scores were significantly higher (P < 0.001) and less variable on converted CT. Conclusion: CT conversion using a RouteGAN can improve the accuracy and variability of CT images obtained using different scan parameters and manufacturers in deep learning-based quantification of ILD.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.13 no.6
• /
• pp.49-62
• /
• 2018

The purpose of this study is to develop an assessment index for the selection of promising start-ups, which will enhance the efficiency of program that support start-ups. In order to develop assessment models for selecting start-ups, three major research steps were conducted. First, this study attempted to theoretically redefine the assessment index from the perspective of the Balanced Scorecard (BSC) through a literature review. Second, major assessment index were derived using Delphi technique for experts in start-up areas. Third, weights were derived by applying AHP technique to calculate the importance of each index. The results of this study are summarized as follows. First, this study attempted to apply the assessment model for selecting start-ups from the Balanced Scorecard (BSC) view through the previous study review. Second, the final major questions were derived with sufficient opinions collected and structured survey of leading start-up experts in areas related to research subjects and elicited the most representative questions. Third, the results of applying the weights of the main selected assessment index, commercialization viewpoint is the most priority, followed by market view, technology development viewpoint, and organizational capability viewpoint. In the middle section, th ability to make products in the commercialization viewpoint, market competitiveness in the market, product discrimination capacity in the technology development perspective, and the ability of the entrepreneur in the organizational capacity perspective were important. Overall important items were found to be in the order of the capabilities of entrepreneurs, market competitiveness, product fire capability, and product discrimination. The importance of small items was highest priority for comparative excellence of competing products, and the degree of marketability, capacity of entrepreneurship, ability to raise capital, desire for entrepreneurship, and passion were shown. The results of this study presented a conceptual alternative to the preceding study on the development of existing selection assessment indexes. And it provides meaningful and important implications as an attempt to develop more sophisticated indicators by overcoming the limitations of empirical research on only some of the evaluation metrics.