AI-based detection of erythema migrans and disambiguation against other skin lesions

Burlina, Philippe; Joshi, Neil; Mathew, Phil A.; Paul, William; Rebman, Alison W.; Aucott, John N.

doi:10.1016/j.compbiomed.2020.103977

Cited by 29 publications

(22 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…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.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

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

Hossain¹,

Hervé²,

Hassan³

et al. 2022

Computer Methods and Programs in Biomedicine

View full text Add to dashboard Cite

Lyme disease is one of the most common infectious vector-borne diseases in the world. In the early stage, the disease manifests itself in most cases with erythema migrans (EM) skin lesions. Better diagnosis of these early forms would allow improving the prognosis by preventing the transition to a severe late form thanks to appropriate antibiotic therapy. Recent studies show that convolutional neural networks (CNNs) perform very well to identify skin lesions from the image 2 but, there is not much work for Lyme disease prediction from EM lesion images. 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 architecture for the purpose. There is no publicly available EM image dataset for Lyme disease prediction mainly because of privacy concerns. In this study, we utilized an EM dataset consisting of images collected from Clermont-Ferrand University Hospital Center (CF-CHU) of France and the internet. CF-CHU collected the images from several hospitals in France. This dataset was labeled by expert dermatologists and infectiologists from CF-CHU. First, we benchmarked this dataset for twenty-three well-known CNN architectures in terms of predictive performance metrics, computational complexity metrics, and statistical significance tests. Second, to improve the performance of the CNNs, we used transfer learning from ImageNet pre-trained models as well as pre-trained the CNNs with the skin lesion dataset "Human Against Machine with 10000 training images (HAM1000)". In that process, we searched for the best performing number of layers to unfreeze during transfer learning finetuning for each of the CNNs. Third, 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. Fourth, we provided guidelines for model selection based on predictive performance and computational complexity. Our study confirmed the effectiveness and potential of even some lightweight CNNs for building Lyme disease pre-scanner mobile applications to assist people with an initial diagnosis in the absence of an expert dermatologist. We also made all the trained models 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.

show abstract

Section: Resultsmentioning

confidence: 99%

“…MobileNetV3 [50] incorporated squeeze-and-excitation layers [51] in the building block of MobileNetV2 and used MnasNet [52] to search for a coarse architecture which was further optimized with NetAdapt [53] algorithm. Burlina et al [32] used ImageNet pre-trained MobileNetV2 architecture for Lyme disease analysis.…”

Section: Mobilenet Architecturementioning

confidence: 99%

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

Hossain¹,

Hervé²,

Hassan³

et al. 2022

Computer Methods and Programs in Biomedicine

View full text Add to dashboard Cite

show abstract

“…The accuracy of clinician assessment of patients presenting with a single EM lesion (n = 42) was not assessed. The challenges of discriminating between an EM lesion of LD and a non-EM lesion are included below, along with a description of a novel imaging tool that may aid clinician assessment of this sign of LD (9). Many patients struggle with getting a timely diagnosis and treatment for LD.…”

Section: Diagnosismentioning

confidence: 99%

Recent Progress in Lyme Disease and Remaining Challenges

Bobe

Jutras

Horn³

et al. 2021

Front. Med.

Self Cite

View full text Add to dashboard Cite

Lyme disease (also known as Lyme borreliosis) is the most common vector-borne disease in the United States with an estimated 476,000 cases per year. While historically, the long-term impact of Lyme disease on patients has been controversial, mounting evidence supports the idea that a substantial number of patients experience persistent symptoms following treatment. The research community has largely lacked the necessary funding to properly advance the scientific and clinical understanding of the disease, or to develop and evaluate innovative approaches for prevention, diagnosis, and treatment. Given the many outstanding questions raised into the diagnosis, clinical presentation and treatment of Lyme disease, and the underlying molecular mechanisms that trigger persistent disease, there is an urgent need for more support. This review article summarizes progress over the past 5 years in our understanding of Lyme and tick-borne diseases in the United States and highlights remaining challenges.

show abstract

“…Examined by Philippe M. Burlina et al [36] on skin lesions and detecting Erythema Migrans (EM) [9,11,37] using Artificial Intelligence (AI) and Deep Learning (DL) methods [38,39] is the main approach of this study. Early accurate identification of EM avoids rheumatology, neurology, and complications in cardiac.…”

Section: Erythema Migransmentioning

confidence: 99%

Survey on Erythema Migrans, and Basal Cell Carcinoma in Computer-Aided Diagnosis

Radhakrishnan

Sudalaimuthu

Dhanalakshmi³

2021

Advances in Parallel Computing Technologies and Applications

View full text Add to dashboard Cite

Lyme disease appears by various means one of the causes is infection from a bite of a black-legged tick which leads to the formation of a rash called Erythema Migrans (EM). This Lyme disease is the direct root of skin cancer and the primary phase is known as Basal Cell Carcinoma (BCC). Skin cancer causes pathological situations it integument the body’s surfaces, including skin, hair, nails, and associated glands. Identifying EM and BCC in biomedical representation is a common platform known as biopsies and many works are done in the traditional methodology. But early detection of EM and BCC in the field of medical imaging using computer-aided diagnosis provides more accuracy and rapidity. This survey is classified under two categories; the first is EM detection and the second is the segmentation of BCC. The circumstances of this review are under the base of different algorithms, various methods used by the non-medicals appliance are discussed and compared by the several measures taken by increasing the parameters to improve the accuracy levels.

show abstract

AI-based detection of erythema migrans and disambiguation against other skin lesions

Cited by 29 publications

References 32 publications

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

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

Recent Progress in Lyme Disease and Remaining Challenges

Survey on Erythema Migrans, and Basal Cell Carcinoma in Computer-Aided Diagnosis

Contact Info

Product

Resources

About