Supervised Visual System for Recognition of Erythema Migrans, an Early Skin Manifestation of Lyme Borreliosis

Abstract

Lyme borreliosis is the most common human tick-borne infectious disease in the northern hemisphere, occurring predominantly in temperate regions of North America, Europe and Asia. The disease's most frequent manifestation is erythema migrans, a skin lesion that appears within days to weeks of a tick bite. Early recognition of the lesion is important since it enables proper management and thus prevention of later consequences of the disease which can hamper normal life. In this article, a novel visual system for recognition of erythema migrans is presented based on new multimedia interactive terminal technology available also on smartphones. For potential erythema migrans skin lesion edge detection, we compared three different methods: GrowCut, maximal similarity based region merging and random walker segmentation method. The results obtained with GrowCut method are better than those obtained with random walker method. The GrowCut method, improved with our new finger draw (FD1) marker yields comparable results to those obtained with maximal similarity based region merging method. Several classification algorithms including naive Bayes, support vector machine, AdaBoost, random forest, and neural network were compared and used for classification of skin lesions into ellipse, the most common shape of erythema migrans and erythema migrans class.

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

“…Čuk et al [31] reported accuracies in the range of 69.23% to 80.42% using classical machine learning methods whereas, Burlina et al [32] reported the best accuracy of 81.51% using ResNet50 architecture for the case of EM vs all classification problems. There was a common subset of images collected from the internet in both the dataset of Burlina et al [4] and our Lyme dataset.…”

“…The unavailability of public EM datasets as a result of privacy concerns of medical data may be the reason for the lack of extensive studies in this field. Čuk et al [31] proposed a visual system for EM recognition on a private EM dataset using classical machine learning techniques including naïve Bayes, SVM, boosting, and neural nets (not deep learning). Burlina et al [4] created a dataset of EM by collecting images from the internet and trained a CNN architecture ResNet50 as a binary classifier to distinguish between EM and other skin conditions.…”

Using Deep Learning in Lyme Disease Diagnosis

“…Deep convolutional neural networks (DCNNs) are solutions to a wide variety of problems in computer vision, natural language processing and robotics. The use of DCNNs in the diagnosis of EM rashes has been investigated before, but these studies focus on the creation of the algorithm rather than it's implementation into a usable form [ [12], [13]].…”