Search

This article presents the scientific outcomes of the 2020 Data Fusion Contest (DFC2020) organized by the Image Analysis and Data Fusion Technical Committee of the IEEE Geoscience and Remote Sensing Society. The 2020 Contest addressed the problem of automatic global land-cover mapping with weak supervision, i.e., estimating high-resolution semantic maps while only low-resolution reference data are available during training. Two separate competitions were organized to assess two different scenarios: 1) high-resolution labels are not available at all; and 2) a small amount of high-resolution labels are available additionally to low-resolution reference data. In this article, we describe the DFC2020 dataset that remains available for further evaluation of corresponding approaches and report the results of the best-performing methods during the contest.

The 2021 Data Fusion Contest, organized by the Image Analysis and Data Fusion Technical Committee (IADF TC) of the IEEE Geoscience and Remote Sensing Society (GRSS), promotes research on geospatial artificial intelligence (AI) for social good. The global objective is to build models for understanding the state of and changes in artificial and natural environments from remote sensing data toward sustainable development.

Objective: To investigate the relationship between parameters of diastolic function, loading conditions and remodeling of the left ventricle in the appropriate-for-gestational age and small-for-gestational age fetus. Methods: Two-dimensional echocardiographic left ventricular images were digitized in 24 appropriate-for-gestational age and 14 small-for-gestational age fetuses. The maximal short axis and long axis were measured. The left ventricular contour was divided into 12 segments. The changes in whole left ventricular cavity area were calculated for ventricular global area change assessment. The coefficient of variation for segmental fractional area change was calculated for the evaluation of left ventricular regional wall motion nonuniformity. Results: Mean left ventricular long axis/short axis ratio in the small-for-gestational age fetus (1.11 ± 0.08) was smaller (P < 0.01) than in the appropriate-for-gestational age fetus (1.75 ± 0.26). Mean fractional area change in the small-for-gestational age fetus was larger (P < 0.01) than in the appropriate-for-gestational age fetus (37.8 ± 17.6% vs. 21.1 ± 9.9%). Mean left ventricular global area change in the small-for-gestational age fetus was smaller (P < 0.05) than in the appropriate-for-gestational age fetus (53.2 ± 7.4% vs. 61.5 ± 10.3%). Mean ventricular isovolumic relaxation time in the appropriate-for-gestational age fetus was shorter (P = 0.03) than in the small-for-gestational age fetus (37 ± 6 ms vs. 57 ± 9 ms). Mean transmitral E-wave/A-wave ratio in the small-for-gestational age fetus was smaller (P < 0.01) than in the appropriate-for-gestational age fetus (0.69 ± 0.08 vs. 0.80 ± 0.08). A negative correlation (P < 0.05) was demonstrated between: (i) fractional area change and global area change in both small-for-gestational age (r = -0.62) and appropriate-for-gestational age fetuses (r = -0.58); (ii) umbilical artery systolic/diastolic ratio and transmitral E-wave/A-wave ratio in both appropriate-for-ges