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.

Importance of consultations using mobile teams in the screening and treatment of neglected tropical skin diseases in Benin.

CONTEXT: Since 2013, the World Health Organization has recommended integrated control strategies for neglected tropical diseases (NTDs) with skin manifestations. We evaluated the implementation of an integrated approach to the early detection and rapid treatment of skin NTDs based on mobile clinics in the Ouémé and Plateau areas of Benin. METHODS: This descriptive cross-sectional study was performed in Ouémé and Plateau in Benin from 2018 to 2020. Consultations using mobile teams were performed at various sites selected by reasoned choice based on the epidemiological data of the National Program for the Control of Leprosy and Buruli Ulcer. All individuals presenting with a dermatological lesion who voluntarily approached the multidisciplinary management team on the day of consultation were included. The information collected was kept strictly anonymous and was entered into an Excel 2013 spreadsheet and analyzed with Stata 11 software. RESULTS: In total, 5,267 patients with various skin conditions consulted the medical team. The median age of these patients was 14 years (IQR: 7-34 years). We saw 646 (12.3%) patients presenting NTDs with skin manifestations, principally scabies, in 88.4% (571/646), followed by 37 cases of Buruli ulcer (5.8%), 22 cases of leprosy (3.4%), 15 cases of lymphatic filariasis (2.3%) and one case of mycetoma (0.2%). We detected no cases of yaws. CONCLUSION: This sustainable approach could help to decrease the burden of skin NTDs in resource-limited countries.

A combined effort of 11 laboratories in the WHO African region to improve quality of Buruli ulcer PCR diagnosis: The "BU-LABNET".

Buruli ulcer is one of the 20 neglected tropical diseases in the world. This necrotizing hypodermitis is a chronic debilitating disease caused by an environmental Mycobacterium ulcerans. At least 33 countries with tropical, subtropical and temperate climates have reported Buruli ulcer in African countries, South America and Western Pacific regions. Majority of cases are spread across West and Central Africa. The mode of transmission is unclear, hindering the implementation of adequate prevention for the population. Currently, early diagnosis and treatment are crucial to minimizing morbidity, costs and preventing long-term disability. Biological confirmation of clinical diagnosis of Buruli ulcer is essential before starting chemotherapy. Indeed, differential diagnosis are numerous and Buruli ulcer has varying clinical presentations. Up to now, the gold standard biological confirmation is the quantitative PCR, targeting the insertion sequence IS2404 of M. ulcerans performed on cutaneous samples. Due to the low PCR confirmation rate in endemic African countries (under 30% in 2018) for numerous identified reasons within this article, 11 laboratories decided to combine their efforts to create the network "BU-LABNET" in 2019. The first step of the network was to harmonize the procedures and ship specific reagents to each laboratory. With this system in place, implementation of these procedures for testing and follow-up was easy and the laboratories were able to carry out their first quality control with a very high success rate. It is now time to integrate other neglected tropical diseases to this platform, such as yaws or leprosy.

Novel Diagnostics for Kaposi Sarcoma and Other Skin Diseases in Resource-Limited Settings.

In resource-limited settings, point-of-care diagnostic devices have the potential to reduce diagnostic delays and improve epidemiologic surveillance of dermatologic conditions. We outline novel-point-of care diagnostics that have recently been developed for dermatologic conditions that primarily affect patients living in resource-limited settings, namely, Kaposi sarcoma, cutaneous leishmaniasis, leprosy, Buruli ulcer, yaws, onchocerciasis, and lymphatic filariasis. All of the technologies described in this article are prototypes, and some have undergone field testing. These devices still require validation in real-world settings and effective pricing to have a major impact on dermatologic care in resource-limited settings.

The co-infection of Buruli ulcer and cutaneous leishmaniasis in Sudanese patient: An association by choice or by chance?

Buruli ulcer and cutaneous leishmaniasis both have the similar cutaneous clinical presentation. Therefore, relying on clinical diagnosis can be challenging. We present a case of 45 years old woman diagnosed with cutaneous leishmaniasis, confirmed by skin biopsy. She received different modalities of anti-leishmanial treatment (fluconazole 450mg daily for 4 weeks, sodium stibogluconate (SSG) followed by thermal therapy, SSG/IV 20mg/kg for 30 days combined with paromomycin 15mg/kg IM for 17 days). These treatments were associated with partial improvement of the ulcer and failure of healing. A second biopsy demonstrated the presence of Mycobacterium ulcerans and hence the diagnosis of Buruli ulcer as a cause of the delayed healing of the ulcer. M. ulcerans releases a toxin known as mycolactone, which decreases immune system function and results in tissue death. M. ulcerans, is regarded as the third most prevalent Mycobacterium after M. tuberculosis and M. leprae. Treatment with streptomycin intramuscular injections 1g daily and rifampicin 600mg daily for 8 weeks was associated with complete healing of the ulcer. To our knowledge, this is the first report that describes the co-infection of Buruli ulcer and cutaneous leishmaniasis in Sudan.

Cell-mediated and serology-based tests for Mycobacterium ulcerans disease: A systematic review and meta-analysis.

Buruli ulcer (BU) is a subcutaneous necrotic infection of the skin caused by Mycobacterium ulcerans. It is the third most common human mycobacterial disease after tuberculosis (TB) and leprosy. The available methods for detection of the bacilli in lesions are microscopic detection, isolation and cultivation of the bacterium, histopathology, and polymerase chain reaction (PCR). These methods, although approved by the World Health Organization (WHO), have infrastructural and resource challenges in medical centres and cell-mediated immunity (CMI) and/or serology-based tests have been suggested as easier and more appropriate for accurate assessment of the disease, especially in remote or underdeveloped areas. This study systematically reviewed and conducted a meta-analysis for all research aimed at developing cell-mediated immunity (CMI) and/or serology-based tests for M. ulcerans disease. Information for this review was searched through PubMed and Web of Science databases and identified up to June 2019. References from relevant articles and reports from the WHO Annual Meeting of the Global Buruli Ulcer Initiative were also used. Twelve studies beginning in 1952, that attempted to develop CMI and/or serology-based tests for the disease were identified. These studies addressed issues of specificity and sensitivity in context of antigen composition as well as study heterogeneity and bias. The two main types of antigenic preparations considered were pathogen-derived and recombinant protein preparations. There was slight difference in test performance when M. ulcerans recombinant proteins [positivity: 67.5%; 32.5%] or pathogen-derived [positivity: 76.0%; 24.0%] preparations were used as test antigens among BU patients. However, pathogen-derived preparations were better at differentiating between patients and control groups [odds ratio (OR) of 27.92, 95%CI: 5.05-154.28]. This was followed by tests with the recombinant proteins [OR = 1.23, 95%CI: 0.27-5.62]. Overall, study heterogeneity index, I2 was 92.4% (p = 0.000). It is apparent from this review that standardisation is needed in any future CMI and/or serology-based tests used for M. ulcerans disease.

Integrated approach in the control and management of skin neglected tropical diseases in three health districts of Côte d'Ivoire.

BACKGROUND: Neglected tropical diseases (NTDs) comprise 20 communicable diseases that are prevalent in rural poor and remote communities with less access to the health system. For effective and efficient control, the WHO recommends that affected countries implement integrated control interventions that take into account the different co-endemic NTDs in the same community. However, implementing these integrated interventions involving several diseases with different etiologies, requiring different control approaches and driven by different vertical programs, remains a challenge. We report here the results and lessons learned from a pilot test of this integrated approach based on integrated screening of skin diseases in three co-endemic health districts of Côte d'Ivoire, a West African country endemic for Buruli ulcer, leprosy and yaw. METHOD: This cross-sectional study took place from April 2016 to March 2017 in 3 districts of Côte d'Ivoire co-endemic for BU, leprosy and yaws. The study was carried out in 6 stages: identification of potentially co-endemic communities; stakeholder training; social mobilization; mobile medical consultations; case detection and management; and a review meeting. RESULTS: We included in the study all patients with skin signs and symptoms at the screening stage who voluntarily accepted screening. In total, 2310 persons screened had skin lesions at the screening stage. Among them, 07 cases were diagnosed with Buruli ulcer. There were 30 leprosy cases and 15 yaws detected. Other types of ulcerations and skin conditions have been identified and represent the majority of cases detected. We learned from this pilot experience that integration can be successfully implemented in co-endemic communities in Côte d'Ivoire. Health workers are motivated and available to implement integrated interventions instead of interventions focused on a single disease. However, it is essential to provide capacity building, a minimum of drugs and consumables for the care of the patients identified, as well as follow-up of identified patients, including those with other skin conditions. CONCLUSIONS: The results of this study show that the integration of activities can be successfully implemented in co-endemic communities under the condition of staff capacity building and minimal care of identified patients.

Laboratory confirmation of Buruli ulcer cases in Ghana, 2008-2016.

BACKGROUND: Buruli ulcer (BU), a necrotizing skin infection caused by Mycobacterium ulcerans is the third most important mycobacterial disease globally after tuberculosis and leprosy in immune competent individuals. This study reports on the retrospective analyses of microbiologically confirmed Buruli ulcer (BU) cases in seventy-five health facilities in Ghana. METHOD/PRINCIPAL FINDINGS: Pathological samples were collected from BU lesions and transported either through courier services or by car directly to the laboratory. Samples were processed and analysed by IS2404 PCR, culture and Ziehl-Neelsen staining for detection of acid-fast bacilli. From 2008 to 2016, we analysed by PCR, 2,287 samples of 2,203 cases from seventy-five health facilities in seven regions of Ghana (Ashanti, Brong Ahafo, Central, Eastern, Greater Accra, Northern and Volta). The mean annual positivity rate was 46.2% and ranged between 14.6% and 76.2%. The yearly positivity rates from 2008 to 2016 were 52.3%, 76.2%, 56.7%, 53.8%, 41.2%, 41.5%, 22.9%, 28.5% and 14.6% respectively. Of the 1,020 confirmed cases, the ratio of female to male was 518 and 502 respectively. Patients who were 15 years of age and below accounted for 39.8% of all cases. The median age was 20 years (IQR = 10-43). Ulcerative lesions were 69.2%, nodule (9.6%), plaque (2.9%), oedema (2.5%), osteomyelitis (1.1%), ulcer/oedema (9.5%) and ulcer/plaque (5.2%). Lesions frequently occurred on the lower limbs (57%) followed by the upper limbs (38%), the neck and head (3%) and the least found on the abdomen (2%). CONCLUSIONS/SIGNIFICANCE: Our findings show a decline in microbiological confirmed rates over the years and therefore call for intensive education on case recognition to prevent over-diagnosis as BU cases decline.

Analysis of Mycobacterium ulcerans-specific T-cell cytokines for diagnosis of Buruli ulcer disease and as potential indicator for disease progression.

BACKGROUND: Buruli ulcer disease (BUD), caused by Mycobacterium (M.) ulcerans, is the third most common mycobacterial disease after tuberculosis and leprosy. BUD causes necrotic skin lesions and is a significant problem for health care in the affected countries. As for other mycobacterial infections, T cell mediated immune responses are important for protection and recovery during treatment, but detailed studies investigating these immune responses in BUD patients are scarce. In this study, we aimed to characterise M. ulcerans-specific CD4+ T cell responses in BUD patients and to analyse specific cytokine-producing T cells in the context of disease severity and progression. METHODOLOGY/PRINCIPAL FINDINGS: For this case-control study, whole blood samples of BUD patients (N = 36, 1.5-17 years of age) and healthy contacts (N = 22, 3-15 years of age) were stimulated with antigen prepared from M. ulcerans and CD4+ T cells were analysed for the expression of TNFα, IFNγ and CD40L by flow cytometry. The proportions and profile of cytokine producing CD4+ T cells was compared between the two study groups and correlated with disease progression and severity. Proportions of cytokine double-positive IFNγ+TNFα+, TNFα+CD40L+, IFNγ+CD40L+ (p = 0.014, p = 0.010, p = 0.002, respectively) and triple positive IFNγ+TNFα+CD40L+ (p = 0.010) producing CD4+ T cell subsets were increased in BUD patients. In addition, TNFα+CD40L-IFNγ- CD4+ T cells differed between patients and controls (p = 0.034). TNFα+CD40L-IFNγ- CD4+ T cells were correlated with lesion size (p = 0.010) and proportion were higher in 'slow' healers compared to 'fast healers' (p = 0.030). CONCLUSIONS: We were able to identify M. ulcerans-specific CD4+ T cell subsets with specific cytokine profiles. In particular a CD4+ T cell subset, producing TNFα but not IFNγ and CD40L, showed association with lesion size and healing progress. Further studies are required to investigate, if the identified CD4+ T cell subset has the potential to be used as biomarker for diagnosis, severity and/or progression of disease.

The contribution of community health workers to the control of Buruli ulcer in the Ngoantet area, Cameroon.

INTRODUCTION: Buruli ulcer (BU) is a skin disease caused by Mycobacterium ulcerans. It is the third most common mycobacterial infection after tuberculosis and leprosy. Community Health Workers (CHWs) hold the potential to support patients and their families at the community level. METHODS: We conducted a cross-sectional descriptive study to assess the participation of CHWs in the early diagnosis and treatment of BU in Ngoantet, Cameroon. The CHWs performance was measured using: the number of cases referred to the Ngoantet Health Centre, the percentage of accomplished referrals, the percentage of cases referred by CHWs confirmed by the staff of Ngoantet Health Centre. Data was analyzed using Epi-info version 3.4.1. and Microsoft Office Excel 2003. The study focused on 51 CHWs in the Ngoantet health area. RESULTS: The referral rate was 95.0%. Most of the suspicious cases (91.5%) referred were confirmed by health workers. Most CHWs (78.4%) declared that they had identified at least one presumptive case of BU infection. CONCLUSION: We conclude that the CHWs can play a key role in scaling up BU control activities using a referral system. This study confirms the role of home visits and inspections in the early detection and treatment of BU.

[International cooperation with the neglected tropical disease Buruli ulcer in Togo].

The objectives of this paper are to grasp the current status of an endemic disease, known as Buruli ulcer (BU), in the Republic of Togo and the expansion of international assistance in the field. By adopting the explicit support model, this paper also compares the obtained research results with those of the Republic of Ghana and Benin, to clarify the primary functions played among respective governments, WHO, and NGO. Under the auspices of the WHO Global Buruli Ulcer Initiative (GBUI, 1998-), National Buruli Ulcer Control Programme (NBUCP) in the Togo was initiated in 1999. However, due to the shortage of national budget and politico-economic instabilities of the nation, the actual implementation of NBUCP proved to be problematic. It was after 2007 that the programme began to move forward with the interventions of NGOs like DAHW and Handicap International. Currently, major players involved in the implementation of the policies provided by the GBUI are WHO, NGOs and the targeted governments. In other words, the organizations involved in BU treatment work together by fulfilling their functions. Unlike the neighboring countries, the Togolese government encountered much difficulty in materializing its national programme. Largely due to the political instability and the severe shortage of national budget, stronger assistances from NGOs were required at various levels of the national health measures from formulating to implementing the programme. As the programmes in Togo and Ghana/Benin expanded over the years, the respective support model revealed to be unique and different. In Ghana and Benin, intimate cooperation among WHO, government and NGOs has been established. In Togo, strengthening of collaboration among the three players is expected.

Laboratory confirmation of Buruli ulcer disease in Togo, 2007-2010.

BACKGROUND: Since the early 1990s more than 1,800 patients with lesions suspicious for Buruli ulcer disease (BUD) have been reported from Togo. However, less than five percent of these were laboratory confirmed. Since 2007, the Togolese National Buruli Ulcer Control Program has been supported by the German Leprosy and Tuberculosis Relief Association (DAHW). Collaboration with the Department for Infectious Diseases and Tropical Medicine (DITM), University Hospital, Munich, Germany, allowed IS2404 PCR analysis of diagnostic samples from patients with suspected BUD during a study period of three years. METHODOLOGY/PRINCIPAL FINDINGS: The DAHW integrated active BUD case finding in the existing network of TB/Leprosy Controllers and organized regular training and outreach activities to identify BUD cases at community level. Clinically suspected cases were referred to health facilities for diagnosis and treatment. Microscopy was carried out locally, external quality assurance (EQA) at DITM. Diagnostic samples from 202 patients with suspected BUD were shipped to DITM, 109 BUD patients (54%) were confirmed by PCR, 43 (29.9%) by microscopy. All patients originated from Maritime Region. EQA for microscopy resulted in 62% concordant results. CONCLUSIONS/SIGNIFICANCE: This study presents a retrospective analysis of the first cohort of clinically suspected BUD cases from Togo subjected to systematic laboratory analysis over a period of three years and confirms the prevalence of BUD in Maritime Region. Intensified training in the field of case finding and sample collection increased the PCR case confirmation rate from initially less than 50% to 70%. With a PCR case confirmation rate of 54% for the entire study period the WHO standards (case confirmation rate ≥50%) have been met. EQA for microscopy suggests the need for intensified supervision and training. In January 2011 the National Hygiene Institute, Lomé, has assumed the role of a National Reference Laboratory for PCR confirmation and microscopy.

Buruli ulcer.

Buruli ulcer, an infectious disease caused by Mycobacterium ulcerans, is the third most prevalent mycobacteriosis, after tuberculosis and leprosy. This atypical mycobacteriosis has been reported in over 30 countries, mainly those with tropical and subtropical climates, but its epidemiology remains unclear. The first autochthonous cases of infection in Brazil have recently been described, making this diagnosis important for Brazilian dermatologists. Clinical manifestations vary from nodules, areas of edema, and plaques, but the most typical presentation is a large ulcer, usually in the limbs. Despite considerable knowledge about its clinical manifestations in some endemic countries, in other areas the diagnosis may be overlooked. Therefore, physicians should be educated about Buruli ulcer, since early diagnosis and treatment, including measures to prevent disability, are essential for a good outcome.

Úlcera de Buruli / Buruli ulcer

A úlcera de Buruli, uma doença infecciosa causada pela Mycobacterium ulcerans (M. ulcerans),é a terceira micobacteriose em ocorrência, após a hanseníase e a tuberculose. Essa micobacteriose atípica tem sido relatada em mais de 30 países, principalmente, nos que têm climas tropicais e subtropicais, mas a sua epidemiologia permanece obscura. Recentemente, os primeiros casos autóctones do Brasil foram relatados, fazendo com que dermatologistas brasileiros estejam atentos a esse diagnóstico. O quadro clínico varia: nódulos, áreas de edema, placas, mas a manifestação mais típica é uma grande úlcera, que ocorre, em geral, nas pernas ou nos braços. Apesar do amplo conhecimento quanto ao seu quadro clínico em países endêmicos, nas outras áreas, esse diagnóstico pode passar despercebido. Assim, médicos devem ser orientados quanto à úlcera de Buruli, pois o diagnóstico precoce, o tratamento específico e a introdução de cuidados na prevenção de incapacidades são essenciais para uma boa evolução.

Buruli ulcer, an infectious disease caused by Mycobacterium ulcerans, is the third most prevalent mycobacteriosis, after tuberculosis and leprosy. This atypical mycobacteriosis has been reported in over 30 countries, mainly those with tropical and subtropical climates, but its epidemiology remains unclear. The first autochthonous cases of infection in Brazil have recently been described, making this diagnosis important for Brazilian dermatologists. Clinical manifestations vary from nodules, areas of edema, and plaques, but the most typical presentation is a large ulcer, usually in the limbs. Despite considerable knowledge about its clinical manifestations in some endemic countries, in other areas the diagnosis may be overlooked. Therefore, physicians should be educated about Buruli ulcer, since early diagnosis and treatment, including measures to prevent disability, are essential for a good outcome.

Antimicrobial treatment for early, limited Mycobacterium ulcerans infection: a randomised controlled trial.

BACKGROUND: Surgical debridement was the standard treatment for Mycobacterium ulcerans infection (Buruli ulcer disease) until WHO issued provisional guidelines in 2004 recommending treatment with antimicrobial drugs (streptomycin and rifampicin) in addition to surgery. These recommendations were based on observational studies and a small pilot study with microbiological endpoints. We investigated the efficacy of two regimens of antimicrobial treatment in early-stage M ulcerans infection. METHODS: In this parallel, open-label, randomised trial undertaken in two sites in Ghana, patients were eligible for enrolment if they were aged 5 years or older and had early (duration <6 months), limited (cross-sectional diameter <10 cm), M ulcerans infection confirmed by dry-reagent-based PCR. Eligible patients were randomly assigned to receive intramuscular streptomycin (15 mg/kg once daily) and oral rifampicin (10 mg/kg once daily) for 8 weeks (8-week streptomycin group; n=76) or streptomycin and rifampicin for 4 weeks followed by rifampicin and clarithromycin (7.5 mg/kg once daily), both orally, for 4 weeks (4-week streptomycin plus 4-week clarithromycin group; n=75). Randomisation was done by computer-generated minimisation for study site and type of lesion (ulceration or no ulceration). The randomly assigned allocation was sent from a central site by cell-phone text message to the study coordinator. The primary endpoint was lesion healing at 1 year after the start of treatment without lesion recurrence or extensive surgical debridement. Analysis was by intention-to-treat. This trial is registered with ClinicalTrials.gov, number NCT00321178. FINDINGS: Four patients were lost to follow-up (8-week streptomycin, one; 4-week streptomycin plus 4-week clarithromycin, three). Since these four participants had healed lesions at their last assessment, they were included in the analysis for the primary endpoint. 73 (96%) participants in the 8-week streptomycin group and 68 (91%) in the 4-week streptomycin plus 4-week clarithromycin group had healed lesions at 1 year (odds ratio 2.49, 95% CI 0.66 to infinity; p=0.16, one-sided Fisher's exact test). No participants had lesion recurrence at 1 year. Three participants had vestibulotoxic events (8-week streptomycin, one; 4-week streptomycin plus 4-week clarithromycin, two). One participant developed an injection abscess and two participants developed an abscess close to the initial lesion, which was incised and drained (all three participants were in the 4-week streptomycin plus 4-week clarithromycin group). INTERPRETATION: Antimycobacterial treatment for M ulcerans infection is effective in early, limited disease. 4 weeks of streptomycin and rifampicin followed by 4 weeks of rifampicin and clarithromycin has similar efficacy to 8 weeks of streptomycin and rifampicin; however, the number of injections of streptomycin can be reduced by switching to oral clarithromycin after 4 weeks. FUNDING: European Union (EU FP6 2003-INCO-Dev2-015476) and Buruli Ulcer Groningen Foundation.

[Atypical mycobacteriosis of the skin caused by Mycobacterium abscessus in an immunocompetent woman]. / Atypische Mykobakteriose der Haut durch Mycobacterium abscessus bei einer immunkompetenten Frau.

Mycobacterium abscessus is the most pathogenic of the fast-growing mycobacteria, and it is resistant to most of the antimicrobial and tuberculostatic drugs available. This non-tuberculous mycobacterium is significant in medicine because it can contaminate post-traumatic wounds and be a causative agent in chronic skin and soft tissue infection after surgical procedures.A 60-year-old immunocompetent woman was suffering from chronic ulcers and abscesses on the heels and malleoli of both feet. Histological examination revealed a granulomatous inflammation with detection of acid-fast rods, albeit without fibrinoid necrosis. The repeated detection of atypical mycobacteria, which were ultimately identified as Mycobacterium abscessus, allowed the diagnosis of an atypical mycobacteriosis of the skin. This was successfully treated first with clarithromycin and rifabutin and later with a combination of ethambutol, minocycline, clofazimine and azithromycin.