Automated Skin Lesion Detection and Prevalence Estimation in Tamanend's Bottlenose Dolphins

Abstract

Anthropogenic global change is occurring at alarming rates, leading to increased urgency in the ability to monitor wildlife health in real time. Monitoring sentinel marine species, such as bottlenose dolphins, is particularly important due to extensive anthropogenic modifications to their habitats. The most common non-invasive method of monitoring cetacean health is documentation of skin lesions, often associated with poor health or disease, but the current methodology is inefficient and imprecise. Recent advancements in technology, such as machine learning, can provide researchers with more efficient ecological monitoring methods to address health questions at both the population and the individual levels. Our work develops a machine learning model to classify skin lesions on the understudied Tamanends bottlenose dolphins (Tursiops erebennus) of the Chesapeake Bay, using manual estimates of lesion presence in photographs. We assess the models performance and find that our best model performs with a high mean average precision (65.6%-86.8%), and generally increased accuracy with improved photo quality. We also demonstrate the models ability to address ecological questions across scales by generating model-based estimates of lesion prevalence and testing the effect of gregariousness on health status. At the population level, our model accurately estimates a prevalence of 72.1% spot and 27.3% fringe ring lesions, with a slight underprediction compared to manual estimates (82.2% and 32.1%). On the other hand, we find that individual-level analyses from the model predictions may be more sensitive to data quality, and thus, some individual scale questions may not be feasible to address if data quality is inconsistent. Manually, we do find that lesion presence in individuals suggests a positive relationship between lesion presence and gregariousness. This work demonstrates that object detection models on photographic data are reasonably successful, highly efficient, and provide initial estimates on the health status of understudied populations of bottlenose dolphins.