The UTrack framework for segmenting and measuring dermatological ulcers through telemedicine

Cazzolato, Mirela T.; Ramos, Jonathan S.; Rodrigues, Lucas S.; Scabora, Lucas C.; Chino, Daniel Yoshinobu Takada; Jorge, Ana Elisa Serafim; Azevedo-Marques, Paulo Mazzoncini de; Traina, Caetano; Traina, Agma J. M.

doi:10.1016/j.compbiomed.2021.104489

Cited by 10 publications

(6 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Some studies [ 21 – 23 ] chose to rely on classification DLMs, thus capping the achievable precision to discrete scores in contrast to our DLM, which predicts continuous metrics. Various segmentation approaches have also been applied to ulcers [ 24 ], skin cancer [ 25 , 26 ], eczema [ 27 ], and psoriasis [ 7 , 28 ], and therefore could also be used to produce metrics similar to our study. However, they all targeted diseases with plaques, single lesions, or lesions larger than PP efflorescences.…”

Section: Discussionmentioning

confidence: 99%

Quantification of Efflorescences in Pustular Psoriasis Using Deep Learning

Amruthalingam¹,

Buerzle

Gottfrois

et al. 2022

Healthc Inform Res

View full text Add to dashboard Cite

Objectives: Pustular psoriasis (PP) is one of the most severe and chronic skin conditions. Its treatment is difficult, and measurements of its severity are highly dependent on clinicians’ experience. Pustules and brown spots are the main efflorescences of the disease and directly correlate with its activity. We propose an automated deep learning model (DLM) to quantify lesions in terms of count and surface percentage from patient photographs. Methods: In this retrospective study, two dermatologists and a student labeled 151 photographs of PP patients for pustules and brown spots. The DLM was trained and validated with 121 photographs, keeping 30 photographs as a test set to assess the DLM performance on unseen data. We also evaluated our DLM on 213 unstandardized, out-of-distribution photographs of various pustular disorders (referred to as the pustular set), which were ranked from 0 (no disease) to 4 (very severe) by one dermatologist for disease severity. The agreement between the DLM predictions and experts’ labels was evaluated with the intraclass correlation coefficient (ICC) for the test set and Spearman correlation (SC) coefficient for the pustular set. Results: On the test set, the DLM achieved an ICC of 0.97 (95% confidence interval [CI], 0.97–0.98) for count and 0.93 (95% CI, 0.92–0.94) for surface percentage. On the pustular set, the DLM reached a SC coefficient of 0.66 (95% CI, 0.60–0.74) for count and 0.80 (95% CI, 0.75–0.83) for surface percentage. Conclusions: The proposed method quantifies efflorescences from PP photographs reliably and automatically, enabling a precise and objective evaluation of disease activity.

show abstract

Section: Discussionmentioning

confidence: 99%

Quantification of Efflorescences in Pustular Psoriasis Using Deep Learning

Amruthalingam¹,

Buerzle

Gottfrois

et al. 2022

Healthc Inform Res

View full text Add to dashboard Cite

show abstract

“…Plataforma mobile de uso profissional e paciente para medir temperatura dos tecidos na ferida em pé diabético Song et al 45 A novel point-of-care solution to streamline development of local wound care formularies Metodológico Plataforma web de uso profissional para registro do atendimento profissional a pessoas com feridas Chang et al 6 The impact of an mHealth app on knowledge, skills and anxiety about dressing changes: A randomized controlled trial Prospectivo randomizado controlado Plataforma mobile de uso do paciente para informações de troca de curativos Carmichael et al 46 Triage and transfer to a regional burn center-impact of a mobile phone app Coorte retrospectivo Plataforma mobile de uso profissional para triagem e transferência de pacientes com queimaduras Cazzolato et al 47 The UTrack framework for segmenting and measuring dermatological ulcers Com base nas questões de extração de dados, investigaram-se alguns aspectos sobre os sistemas computacionais para área da cicatrização de feridas. As informações são apresentadas nas Tabelas 2 a 4.…”

Section: Ensaio Clínicounclassified

Sistemas Computacionais Para Auxílio Na Cicatrização De Feridas: Revisão De Escopo

Rodrigues

Bezerra

Calçada

2023

ESTIMA, Braz. J. Enterostomal Ther.

View full text Add to dashboard Cite

Objetivo:Investigar estudos que apresentem sistemas computacionais de auxílio à cicatrização de feridas e quais sistemas se referem ao uso de laser de baixa intensidade. Método: Revisão de escopo que visou responder à questão de pesquisa: Quais sistemas computacionais auxiliam na cicatrização de feridas? Uma subquestão foi: quais sistemas computacionais se referem ao uso do laser de baixa intensidade? Resultados: A partir da busca, aplicando os critérios de elegibilidade, 49 artigos compuseram a amostra final. Os sistemas apresentaram várias finalidades de apoio à cicatrização de feridas, em que a maioria apresentou como usuário do sistema o profissional de saúde, sendo a medicina a área profissional mais mencionada, embora a enfermagem esteja envolvida com o manejo do cuidado às pessoas com feridas. Foi relatada com frequência a inovação na assistência a partir do uso do sistema computacional, o que demonstra a importância desse tipo de ferramenta para a prática clínica. Verificou-se com frequência o uso de plataforma mobile, como tendência da atualidade. Conclusão: Os sistemas computacionais têm sido utilizados como ferramentas para apoiar pacientes e principalmente profissionais na cicatrização de feridas. Quanto ao laser de baixa intensidade, houve escassez de sistemas computacionais com essa finalidade, com apenas um estudo.

show abstract

“…The research on imaging tools for the examination of skin lesions has already demonstrated its clinical interest with increased diagnostic accuracy [13][14][15][16] . To help the diagnosis and monitoring treatment evolution of CVD, digital photographs are regularly captured and stored by healthcare professionals [17][18][19] . These photographs allow an easier evaluation of the patient's condition by comparing the classification (i.e.…”

mentioning

confidence: 99%

“…These photographs allow an easier evaluation of the patient's condition by comparing the classification (i.e. according to CEAP and VCSS) and lesion extension in different periods 17,19,20 . References on the clinical images (e.g.…”

mentioning

confidence: 99%

A multi-task convolutional neural network for classification and segmentation of chronic venous disorders

Oliveira

Torres

Morais

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Chronic Venous Disorders (CVD) of the lower limbs are one of the most prevalent medical conditions, affecting 35% of adults in Europe and North America. Due to the exponential growth of the aging population and the worsening of CVD with age, it is expected that the healthcare costs and the resources needed for the treatment of CVD will increase in the coming years. The early diagnosis of CVD is fundamental in treatment planning, while the monitoring of its treatment is fundamental to assess a patient’s condition and quantify the evolution of CVD. However, correct diagnosis relies on a qualitative approach through visual recognition of the various venous disorders, being time-consuming and highly dependent on the physician’s expertise. In this paper, we propose a novel automatic strategy for the joint segmentation and classification of CVDs. The strategy relies on a multi-task deep learning network, denominated VENet, that simultaneously solves segmentation and classification tasks, exploiting the information of both tasks to increase learning efficiency, ultimately improving their performance. The proposed method was compared against state-of-the-art strategies in a dataset of 1376 CVD images. Experiments showed that the VENet achieved a classification performance of 96.4%, 96.4%, and 97.2% for accuracy, precision, and recall, respectively, and a segmentation performance of 75.4%, 76.7.0%, 76.7% for the Dice coefficient, precision, and recall, respectively. The joint formulation increased the robustness of both tasks when compared to the conventional classification or segmentation strategies, proving its added value, mainly for the segmentation of small lesions.

show abstract

The UTrack framework for segmenting and measuring dermatological ulcers through telemedicine

Cited by 10 publications

References 35 publications

Quantification of Efflorescences in Pustular Psoriasis Using Deep Learning

Quantification of Efflorescences in Pustular Psoriasis Using Deep Learning

Sistemas Computacionais Para Auxílio Na Cicatrização De Feridas: Revisão De Escopo

A multi-task convolutional neural network for classification and segmentation of chronic venous disorders

Contact Info

Product

Resources

About