Search for: All records

Abstract Developmental dysplasia of the hip (DDH) is a condition in which the acetabular socket inadequately contains the femoral head (FH). If left untreated, DDH can result in degenerative changes in the hip joint. Several imaging techniques are used for DDH assessment. In radiographs, the acetabular index (ACIN), center-edge angle, Sharp's angle (SA), and migration percentage (MP) metrics are used to assess DDH. Determining these metrics is time-consuming and repetitive. This study uses a convolutional neural network (CNN) to identify radiographic measurements and improve traditional methods of identifying DDH. The dataset consisted of 60 subject radiographs rotated along the craniocaudal and mediolateral axes 25 times, generating 1500 images. A CNN detection algorithm was used to identify key radiographic metrics for the diagnosis of DDH. The algorithm was able to detect the metrics with reasonable accuracy in comparison to the manually computed metrics. The CNN performed well on images with high contrast margins between bone and soft tissues. In comparison, the CNN was not able to identify some critical points for metric calculation on a few images that had poor definition due to low contrast between bone and soft tissues. This study shows that CNNs can efficiently measure clinical parameters to assess DDH on radiographs with high contrast margins between bone and soft tissues with purposeful rotation away from an ideal image. Results from this study could help inform and broaden the existing bank of information on using CNNs for radiographic measurement and medical condition prediction. 

Abstract Environmental adaptation and species divergence often involve suites of co‐evolving traits. Pigmentation in insects presents a variable, adaptive, and well‐characterized class of phenotypes for which correlations with multiple other traits have been demonstrated. InDrosophila, the pigmentation genesebonyandtanhave pleiotropic effects on flies' response to light, creating the potential for correlated evolution of pigmentation and vision. Here, we investigate differences in light preference within and between two sister species,Drosophila americanaandD. novamexicana, which differ in pigmentation in part because of evolution atebonyandtanand occupy environments that differ in many variables including solar radiation. We hypothesized that lighter pigmentation would be correlated with a greater preference for environmental light and tested this hypothesis using a habitat choice experiment. In a first set of experiments, using males ofD. novamexicanaline N14 andD. americanaline A00, the light‐bodiedD. novamexicanawas found slightly but significantly more often thanD. americanain the light habitat. A second experiment, which included additional lines and females as well as males, failed to find any significant difference betweenD. novamexicana‐N14 andD. americana‐A00. Additionally, the other dark line ofD. americana(A04) was found in the light habitat more often than the light‐bodiedD. novamexicana‐N14, in contrast to our predictions. However, the lightest line ofD. americana, A01, was found substantially and significantly more often in the light habitat than the two darker lines ofD. americana, thus providing partial support for our hypothesis. Finally, across all four lines, females were found more often in the light habitat than their more darkly pigmented male counterparts. Additional replication is needed to corroborate these findings and evaluate conflicting results, with the consistent effect of sex within and between species providing an especially intriguing avenue for further research.