Exploring convolutional neural networks with transfer learning for diagnosing Lyme disease from skin lesion images.

BACKGROUND AND OBJECTIVE: Lyme disease which is one of the most common infectious vector-borne diseases manifests itself in most cases with erythema migrans (EM) skin lesions. Recent studies show that convolutional neural networks (CNNs) perform well to identify skin lesions from images. Lightweight CNN based pre-scanner applications for resource-constrained mobile devices can help users with early diagnosis of Lyme disease and prevent the transition to a severe late form thanks to appropriate antibiotic therapy. Also, resource-intensive CNN based robust computer applications can assist non-expert practitioners with an accurate diagnosis. The main objective of this study is to extensively analyze the effectiveness of CNNs for diagnosing Lyme disease from images and to find out the best CNN architectures considering resource constraints. METHODS: First, we created an EM dataset with the help of expert dermatologists from Clermont-Ferrand University Hospital Center of France. Second, we benchmarked this dataset for twenty-three CNN architectures customized from VGG, ResNet, DenseNet, MobileNet, Xception, NASNet, and EfficientNet architectures in terms of predictive performance, computational complexity, and statistical significance. Third, to improve the performance of the CNNs, we used custom transfer learning from ImageNet pre-trained models as well as pre-trained the CNNs with the skin lesion dataset HAM10000. Fourth, for model explainability, we utilized Gradient-weighted Class Activation Mapping to visualize the regions of input that are significant to the CNNs for making predictions. Fifth, we provided guidelines for model selection based on predictive performance and computational complexity. RESULTS: Customized ResNet50 architecture gave the best classification accuracy of 84.42% ±1.36, AUC of 0.9189±0.0115, precision of 83.1%±2.49, sensitivity of 87.93%±1.47, and specificity of 80.65%±3.59. A lightweight model customized from EfficientNetB0 also performed well with an accuracy of 83.13%±1.2, AUC of 0.9094±0.0129, precision of 82.83%±1.75, sensitivity of 85.21% ±3.91, and specificity of 80.89%±2.95. All the trained models are publicly available at https://dappem.limos.fr/download.html, which can be used by others for transfer learning and building pre-scanners for Lyme disease. CONCLUSION: Our study confirmed the effectiveness of even some lightweight CNNs for building Lyme disease pre-scanner mobile applications to assist people with an initial self-assessment and referring them to expert dermatologist for further diagnosis.

Are Orienteers Protected Enough against Tick Bites? Estimating Human Exposure to Tick Bites through a Participative Science Survey during an Orienteering Competition.

Mass-participation events in temperate forests are now well-established features of outdoor activities and represent high-risk activities regarding human exposition to tick bites. In this study we used a citizen science approach to quantify the space-time frequency of tick bites and undetected tick bites among orienteers that participated in a 6-day orienteering competition that took place in July 2018 in the forests of Eastern France, and we looked at the use and efficacy of different preventive behaviors. Our study confirms that orienteers are a high-risk population for tick bites, with 62.4% of orienteers bitten at least once during the competition, and 2.4 to 12.1 orienteers per 100 orienteers were bitten by ticks when walking 1 km. In addition, 16.7% of orienteers bitten by ticks had engorged ticks, meaning that they did not detect and remove their ticks immediately after the run. Further, only 8.5% of orienteers systematically used a repellent, and the use of repellent only partially reduced the probability of being bitten by ticks. These results represent the first attempt to quantify the risk of not immediately detecting a tick bite and provide rare quantitative data on the frequency of tick bites for orienteers according to walking distance and time spent in the forest. The results also provide information on the use of repellent, which will be very helpful for modeling risk assessment. The study also shows that prevention should be increased for orienteers in France.