ABSTRACT
Purpose: Radiologists are tasked with visually scrutinizing large amounts of data produced by 3D volumetric imaging modalities. Small signals can go unnoticed during the 3D search because they are hard to detect in the visual periphery. Recent advances in machine learning and computer vision have led to effective computer-aided detection (CADe) support systems with the potential to mitigate perceptual errors. Approach: Sixteen nonexpert observers searched through digital breast tomosynthesis (DBT) phantoms and single cross-sectional slices of the DBT phantoms. The 3D/2D searches occurred with and without a convolutional neural network (CNN)-based CADe support system. The model provided observers with bounding boxes superimposed on the image stimuli while they looked for a small microcalcification signal and a large mass signal. Eye gaze positions were recorded and correlated with changes in the area under the ROC curve (AUC). Results: The CNN-CADe improved the 3D search for the small microcalcification signal ( Δ AUC = 0.098 , p = 0.0002 ) and the 2D search for the large mass signal ( Δ AUC = 0.076 , p = 0.002 ). The CNN-CADe benefit in 3D for the small signal was markedly greater than in 2D ( Δ Δ AUC = 0.066 , p = 0.035 ). Analysis of individual differences suggests that those who explored the least with eye movements benefited the most from the CNN-CADe ( r = - 0.528 , p = 0.036 ). However, for the large signal, the 2D benefit was not significantly greater than the 3D benefit ( Δ Δ AUC = 0.033 , p = 0.133 ). Conclusion: The CNN-CADe brings unique performance benefits to the 3D (versus 2D) search of small signals by reducing errors caused by the underexploration of the volumetric data.
ABSTRACT
Urbanization affects concurrent human-animal interactions as a result of altered resource availability and land use pattern, which leads to considerable ecological consequences. While some animals have lost their habitat due to urban encroachment, few of them managed to survive within the urban ecosystem by altering their natural behavioral patterns. The feeding repertoire of folivorous colobines, such as gray langur, largely consists of plant parts. However, these free-ranging langurs tend to be attuned to the processed high-calorie food sources to attain maximum benefits within the concrete jungle having insignificant greenery. Therefore, besides understanding their population dynamics, the effective management of these urbanized, free-ranging, non-human primate populations also depends on their altered feeding habits. Here, we have used a field-based experimental setup that allows gray langurs to choose between processed and unprocessed food options, being independent of any inter-specific conflicts over resources due to food scarcity. The multinomial logit model reveals the choice-based decision-making of these free-ranging gray langurs in an urban settlement of West Bengal, India, where they have not only learned to recognize the human-provisioned processed food items as an alternative food source but also shown a keen interest in it. However, such a mismatch between the generalized feeding behavior of folivorous colobines and their specialized gut physiology reminds us of Liem's paradox and demands considerable scientific attention. While urbanization imposes tremendous survival challenges to these animals, it also opens up for various alternative options for surviving in close proximity to humans which is reflected in this study, and could guide us for the establishment of a sustainable urban ecosystem in the future.
