Purpose:
We aimed to identify clinically relevant deep learning algorithms for emphysema quantification using low-dose chest computed tomography (LDCT) through an invitation-based competition.
Materials and Methods:
The Korean Society of Imaging Informatics in Medicine (KSIIM) organized a challenge for emphysema quantification between November 24, 2020 and January 26, 2021. Seven invited research teams participated in this challenge. In total, 558 pairs of computed tomography (CT) scans (468 pairs for the training set, and 90 pairs for the test set) from 9 hospitals were collected retrospectively or prospectively. CT acquisition followed the hospitals’ protocols to reflect the real-world clinical setting. Using the training set, each team developed an algorithm that generated converted LDCT by changing the pixel values of LDCT to simulate those of standard-dose CT (SDCT). The agreement between SDCT and LDCT was evaluated using the intraclass correlation coefficient (ICC; 2-way random effects, absolute agreement, and single rater) for the percentage of low-attenuated area below −950 HU (LAA−950 HU), κ value for emphysema categorization (LAA−950 HU, <5%, 5% to 10%, and ≥10%) and cosine similarity of LAA−950 HU.
Results:
The mean LAA−950 HU of the test set was 14.2%±10.5% for SDCT, 25.4%±10.2% for unconverted LDCT, and 12.9%±10.4%, 11.7%±10.8%, and 12.4%±10.5% for converted LDCT (top 3 teams). The agreement between the SDCT and converted LDCT of the first-place team was 0.94 (95% confidence interval: 0.90, 0.97) for ICC, 0.71 (95% confidence interval: 0.58, 0.84) for categorical agreement, and 0.97 (interquartile range: 0.94 to 0.99) for cosine similarity.
Conclusions:
Emphysema quantification with LDCT was feasible through deep learning-based CT conversion strategies.
Analyzing public movement in transportation networks in a city is significant in understanding the life of citizen and making improved city plans for the future. This study focuses on investigating the flow orientation of major activity regions based on smart card transit data. The flow orientation based on the real movements such as transit data can provide the easiest way of understanding public movement in the complicated transportation networks. First, high inflow regions (HIRs) are identified from transit data for morning and evening peak hours. The morning and evening HIRs are used to represent major activity regions for major daytime activities and residential areas, respectively. Second, the directional orientation of flow is then derived through the directional inflow vectors of the HIRs to show the bias in directional orientation and compare flow orientation among major activity regions. Finally, clustering analysis for HIRs is applied to capture the main patterns of flow orientations in the city and visualize the patterns on the map. The proposed methodology was illustrated with smart card transit data of bus and subway transportation networks in Seoul, Korea. Some remarkable patterns in the distribution of movements and orientations were found inside the city. The proposed methodology is useful since it unfolds the complexity and makes it easy to understand the main movement patterns in terms of flow orientation.
SUMMARYSmart card payment systems provide a convenient billing mechanism for public transportation providers and passengers. In this paper, a smart card-based transit log is used to reveal functionally related regions in a city, which are called zones. To discover significant zones based on the transit log data, two algorithms, minimum spanning trees and agglomerative hierarchical clustering, are extended by considering the additional factors of geographical distance and adjacency. The hierarchical spatial geocoding system, called Geohash, is adopted to merge nearby bus stops to a region before zone discovery. We identify different urban zones that contain functionally interrelated regions based on passenger trip data stored in the smart card-based transit log by manipulating the level of abstraction and the adjustment parameters. key words: smart card-based transit log, zone discovery, public transportation, Geohash
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.