Does skin surface temperature variation account for Buruli ulcer lesion distribution?

Mycobacterium ulcerans not detected by PCR on human skin in Buruli ulcer endemic areas of south eastern Australia

INTRODUCTION

Mycobacterium ulcerans (MU) causes Buruli ulcer (Buruli), a geographically restricted infection that can result in skin loss, contracture and permanent scarring. Lesion-location maps compiled from more than 640 cases in south eastern Australia suggest biting insects are likely involved in transmission, but it is unclear whether MU is brought by insects to humans or if MU is already on the skin and inoculation is an opportunistic event that need not be insect dependent.

METHODS

We validated a PCR swab detection assay and defined its dynamic range using laboratory cultured M. ulcerans and fresh pigskin. We invited volunteers in Buruli-endemic and non-endemic areas to sample their skin surfaces with self-collected skin swabs tested by IS2404 quantitative PCR.

RESULTS

Pigskin validation experiments established a limit-of-detection of 0.06 CFU/cm2 at a qPCR cycle threshold (Ct) of 35. Fifty-seven volunteers returned their self-collected kits of 4 swabs (bilateral ankles, calves, wrists, forearms), 10 from control areas and 47 from endemic areas. Collection was timed to coincide with the known peak-transmission period of Buruli. All swabs from human volunteers tested negative (Ct ≥35).

CONCLUSIONS

M. ulcerans was not detected on the skin of humans from highly Buruli endemic areas.

Deep learning for AI-based diagnosis of skin-related neglected tropical diseases: A pilot study

BACKGROUND

Deep learning, which is a part of a broader concept of artificial intelligence (AI) and/or machine learning has achieved remarkable success in vision tasks. While there is growing interest in the use of this technology in diagnostic support for skin-related neglected tropical diseases (skin NTDs), there have been limited studies in this area and fewer focused on dark skin. In this study, we aimed to develop deep learning based AI models with clinical images we collected for five skin NTDs, namely, Buruli ulcer, leprosy, mycetoma, scabies, and yaws, to understand how diagnostic accuracy can or cannot be improved using different models and training patterns.

METHODOLOGY

This study used photographs collected prospectively in Côte d'Ivoire and Ghana through our ongoing studies with use of digital health tools for clinical data documentation and for teledermatology. Our dataset included a total of 1,709 images from 506 patients. Two convolutional neural networks, ResNet-50 and VGG-16 models were adopted to examine the performance of different deep learning architectures and validate their feasibility in diagnosis of the targeted skin NTDs.

PRINCIPAL FINDINGS

The two models were able to correctly predict over 70% of the diagnoses, and there was a consistent performance improvement with more training samples. The ResNet-50 model performed better than the VGG-16 model. A model trained with PCR confirmed cases of Buruli ulcer yielded 1-3% increase in prediction accuracy across all diseases, except, for mycetoma, over a model which training sets included unconfirmed cases.

CONCLUSIONS

Our approach was to have the deep learning model distinguish between multiple pathologies simultaneously-which is close to real-world practice. The more images used for training, the more accurate the diagnosis became. The percentages of correct diagnosis increased with PCR-positive cases of Buruli ulcer. This demonstrated that it may be better to input images from the more accurately diagnosed cases in the training models also for achieving better accuracy in the generated AI models. However, the increase was marginal which may be an indication that the accuracy of clinical diagnosis alone is reliable to an extent for Buruli ulcer. Diagnostic tests also have their flaws, and they are not always reliable. One hope for AI is that it will objectively resolve this gap between diagnostic tests and clinical diagnoses with the addition of another tool. While there are still challenges to be overcome, there is a potential for AI to address the unmet needs where access to medical care is limited, like for those affected by skin NTDs.

Deep learning for AI-based diagnosis of skin-related neglected tropical diseases: a pilot study

Background

Deep learning, which is a part of a broader concept of artificial intelligence (AI) and/or machine learning has achieved remarkable success in vision tasks. While there is growing interest in the use of this technology in diagnostic support for skin-related neglected tropical diseases (skin NTDs), there have been limited studies in this area and fewer focused on dark skin. In this study, we aimed to develop deep learning based AI models with clinical images we collected for five skin NTDs, namely, Buruli ulcer, leprosy, mycetoma, scabies, and yaws, to understand how diagnostic accuracy can or cannot be improved using different models and training patterns.

Methodology

This study used photographs collected prospectively in Côte d'Ivoire and Ghana through our ongoing studies with use of digital health tools for clinical data documentation and for teledermatology. Our dataset included a total of 1,709 images from 506 patients. Two convolutional neural networks, ResNet-50 and VGG-16 models were adopted to examine the performance of different deep learning architectures and validate their feasibility in diagnosis of the targeted skin NTDs.

Principal findings

The two models were able to correctly predict over 70% of the diagnoses, and there was a consistent performance improvement with more training samples. The ResNet-50 model performed better than the VGG-16 model. Model trained with PCR confirmed cases of Buruli ulcer yielded 1-3% increase in prediction accuracy over training sets including unconfirmed cases.

Conclusions

Our approach was to have the deep learning model distinguish between multiple pathologies simultaneously - which is close to real-world practice. The more images used for training, the more accurate the diagnosis became. The percentages of correct diagnosis increased with PCR-positive cases of Buruli ulcer. This demonstrated that it may be better to input images from the more accurately diagnosed cases in the training models also for achieving better accuracy in the generated AI models. However, the increase was marginal which may be an indication that the accuracy of clinical diagnosis alone is reliable to an extent for Buruli ulcer. Diagnostic tests also have its flaws, and they are not always reliable. One hope for AI is that it will objectively resolve this gap between diagnostic tests and clinical diagnoses with addition of another tool. While there are still challenges to be overcome, there is a potential for AI to address the unmet needs where access to medical care is limited, like for those affected by skin NTDs.

AUTHOR SUMMARY

The diagnosis of skin diseases depends in large part, though not exclusively on visual inspection. The diagnosis and management of these diseases is thus particularly amenable to teledermatology approaches. The widespread availability of cell phone technology and electronic information transfer provides new potential for access to health care in low-income countries, yet there are limited efforts targeting these neglected populations with dark skin and consequently limited availability of tools. In this study, we leveraged a collection of skin images gathered through a system of teledermatology in the West African countries of Côte d'Ivoire and Ghana, and applied deep learning, a form of artificial intelligence (AI) - to see if deep learning models can distinguish between different diseases and support their diagnosis. Skin-related neglected tropical diseases, or skin NTDs, prevail in these regions and were our target conditions: Buruli ulcer, leprosy, mycetoma, scabies, and yaws. The accuracy of prediction depended on the number of images that were fed into the model for training with marginal improvement using laboratory confirmed cases in training. Using more images and greater efforts in this area, it is possible that AI can help address the unmet needs where access to medical care is limited.

Genetics in the Host-Mycobacterium ulcerans interaction

Buruli ulcer is an emerging infectious disease associated with high morbidity and unpredictable outbreaks. It is caused by Mycobacterium ulcerans, a slow-growing pathogen evolutionarily shaped by the acquisition of a plasmid involved in the production of a potent macrolide-like cytotoxin and by genome rearrangements and downsizing. These events culminated in an uncommon infection pattern, whereby M. ulcerans is both able to induce the initiation of the inflammatory cascade and the cell death of its proponents, as well as to survive within the phagosome and in the extracellular milieu. In such extreme conditions, the host is sentenced to rely on a highly orchestrated genetic landscape to be able to control the infection. We here revisit the dynamics of M. ulcerans infection, drawing parallels from other mycobacterioses and integrating the most recent knowledge on its evolution and pathogenicity in its interaction with the host immune response.

Immunity against Mycobacterium ulcerans: The subversive role of mycolactone

Mycobacterium ulcerans causes Buruli ulcer, a neglected tropical skin disease manifesting as chronic wounds that can leave victims with major, life-long deformity and disability. Differently from other mycobacterial pathogens, M ulcerans produces mycolactone, a diffusible lipid factor with unique cytotoxic and immunomodulatory properties. Both traits result from mycolactone targeting Sec61, the entry point of the secretory pathway in eukaryotic cells. By inhibiting Sec61, mycolactone prevents the host cell's production of secreted proteins, and most of its transmembrane proteins. This molecular blockade dramatically alters the functions of immune cells, thereby the generation of protective immunity. Moreover, sustained inhibition of Sec61 triggers proteotoxic stress responses leading to apoptotic cell death, which can stimulate vigorous immune responses. The dynamics of bacterial production of mycolactone and elimination by infected hosts thus critically determine the balance between its immunostimulatory and immunosuppressive effects. Following an introduction summarizing the essential information on Buruli ulcer disease, this review focuses on the current state of knowledge regarding mycolactone's regulation and biodistribution. We then detail the consequences of mycolactone-mediated Sec61 blockade on initiation and maintenance of innate and adaptive immune responses. Finally, we discuss the key questions to address in order to improve immunity to M ulcerans, and how increased knowledge of mycolactone biology may pave the way to innovative therapeutics.