Data augmentation in dermatology image recognition using machine learning

Aggarwal, Pushkar

doi:10.1111/srt.12726

Cited by 51 publications

(33 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, previous work focused mainly on the development of networks or analysis of images instead of practically applying CNN for the identification of rosacea and differentiating it from other skin diseases or for the classification of subtypes of rosacea [32]. Besides, the number of images for model development was quite limited (less than 100) in the previous studies and the sensitivity or specificity were barely satisfactory [33]. In our work, a vast number of images were incorporated for the training of CNN, and the precision and accuracy of our deep CNN system were 0.914 and 0.898, respectively, for the identification of rosacea among other skin diseases.…”

Section: Discussionmentioning

confidence: 99%

A Novel Convolutional Neural Network for the Diagnosis and Classification of Rosacea: Usability Study

Zhao¹,

Wu²,

Zhang³

et al. 2021

JMIR Med Inform

View full text Add to dashboard Cite

Background Rosacea is a chronic inflammatory disease with variable clinical presentations, including transient flushing, fixed erythema, papules, pustules, and phymatous changes on the central face. Owing to the diversity in the clinical manifestations of rosacea, the lack of objective biochemical examinations, and nonspecificity in histopathological findings, accurate identification of rosacea is a big challenge. Artificial intelligence has emerged as a potential tool in the identification and evaluation of some skin diseases such as melanoma, basal cell carcinoma, and psoriasis. Objective The objective of our study was to utilize a convolutional neural network (CNN) to differentiate the clinical photos of patients with rosacea (taken from 3 different angles) from those of patients with other skin diseases such as acne, seborrheic dermatitis, and eczema that could be easily confused with rosacea. Methods In this study, 24,736 photos comprising of 18,647 photos of patients with rosacea and 6089 photos of patients with other skin diseases such as acne, facial seborrheic dermatitis, and eczema were included and analyzed by our CNN model based on ResNet-50. Results The CNN in our study achieved an overall accuracy and precision of 0.914 and 0.898, with an area under the receiver operating characteristic curve of 0.972 for the detection of rosacea. The accuracy of classifying 3 subtypes of rosacea, that is, erythematotelangiectatic rosacea, papulopustular rosacea, and phymatous rosacea was 83.9%, 74.3%, and 80.0%, respectively. Moreover, the accuracy and precision of our CNN to distinguish rosacea from acne reached 0.931 and 0.893, respectively. For the differentiation between rosacea, seborrheic dermatitis, and eczema, the overall accuracy of our CNN was 0.757 and the precision was 0.667. Finally, by comparing the CNN diagnosis with the diagnoses by dermatologists of different expertise levels, we found that our CNN system is capable of identifying rosacea with a performance superior to that of resident doctors or attending physicians and comparable to that of experienced dermatologists. Conclusions The findings of our study showed that by assessing clinical images, the CNN system in our study could identify rosacea with accuracy and precision comparable to that of an experienced dermatologist.

show abstract

Section: Discussionmentioning

confidence: 99%

A Novel Convolutional Neural Network for the Diagnosis and Classification of Rosacea: Usability Study

Zhao¹,

Wu²,

Zhang³

et al. 2021

JMIR Med Inform

View full text Add to dashboard Cite

show abstract

“…Each channel of the sample was then clipped to the area of interest. The single channels were then rectified and max pooled according to the 1 2 λ and evaluated individually and converted from the original 16 bit integers to 32 bit floating point numbers and scaled to 0…2.0 (with most data in range 0…1.0).…”

Section: Machine Learning Modelmentioning

confidence: 99%

“…ML models have proven their effectiveness in various image recognition tasks Aggarwal [1], Chowdhury et al [9], Munir et al [25,26], Virkkunen et al [40] thus ML models could be employed to remove the bulk of the repetitiveness of NDT data analysis, even in the noisy and complex cases. Since the majority of the inspection data is usually without flaws, the ML model could be used to look for flawed areas.…”

Section: Introductionmentioning

confidence: 99%

Automated Flaw Detection in Multi-channel Phased Array Ultrasonic Data Using Machine Learning

et al. 2021

View full text Add to dashboard Cite

Modern ultrasonic inspections utilize ever-richer data-sets made possible by phased array equipment. A typical inspection may include tens of channels with different refraction angle, that are acquired at high speed. These rich data sets allow highly reliable and efficient inspection in complex cases, such as dissimilar metal or austenitic stainless steel welds. The rich data sets allow human inspectors to detect cracks with low signal-to-noise ratio from the wider signal patterns. There’s a clear trend in the industry to even richer data sets with full matrix capture (FMC) and related techniques. Convolutional neural networks have recently shown capability to detect flaws with human level accuracy in ultrasonic signals at the B-scan level. To enable automated flaw detection at human-level accuracy for critical applications, these neural networks need be developed to take advantage of today’s rich phased array data-sets. In the present paper, we extend previous work and develop convolutional neural networks that perform highly reliable flaw detection on typical multi-channel phased array data on austenitic welds. The results show, that the modern neural networks can accommodate the rich ultrasonic data and display high flaw detection performance.

show abstract

“…Modelos de inteligência artificial são utilizados em diversas áreas da medicina. Existem diversas publicações com aplicações na área de detecção de câncer de mama (McKinney et al, 2020), radiologia e medicina nuclear (Hosny et al, 2018;Syed & Zoga, 2018;Nensa, Demircioglu & Rischpler, 2019), alvos terapêuticos (Theofilatos et al, 2014), cardiologia (Krittanawong et al, 2017;Johnson et al, 2018;Dey et al, 2020), medicina reprodutiva (WANG et al, 2019), medicina personalizada (Schork, 2019), medicina de emergência (Stewart, Sprivulis & Dwivedi, 2018), nefrologia (Niel & Bastard, 2019), oftalmologia (Kapoor, Walter & Al-Aswad, 2018;Ting et al, 2019;Balyen, Peto, 2019), psiquiatria (Meyer-Lindenberg, 2018), dermatologia (Aggarwal, 2019), urologia (Suarez-Ibarrola et al, 2019) e oncologia (Shimizu & Nakayama, 2020).…”

Section: Introductionunclassified

Uso da inteligência artificial para predição de acidentes de trabalho com materiais biológicos em profissionais da saúde

Groto

Perlin

Andrade

et al. 2021

RSD

View full text Add to dashboard Cite

Este estudo buscou desenvolver um software que calcula a chance de o profissional de saúde ter zero, um, dois, três ou quatro ou mais acidentes com riscos biológicos. Para tal foram utilizados dados de 111 questionários de trabalhadores da saúde da atenção primária e pronto atendimento. O programa atingiu 95% de acurácia no conjunto de treinamento (n=88) e 74% no conjunto de teste (n=23). As associações estatisticamente significantes, que contaram também com dados de 1.094 Comunicações de Acidente de Trabalho, foram maior abandono do acompanhamento por médicos após acidente com materiais biológicos na comparação com outros profissionais (p=0.02), técnicos em enfermagem e maior prevalência de acidentes com materiais biológicos que outros profissionais (p<0.001), trabalhadores de pronto atendimento apresentam mais acidentes com materiais biológicos que profissionais da atenção primária (p<0.001) e aumento do abandono após acidente com materiais biológicos no triênio 2016-2018 na comparação com 2007-2009 (p<0.001).

show abstract

Data augmentation in dermatology image recognition using machine learning

Cited by 51 publications

References 13 publications

A Novel Convolutional Neural Network for the Diagnosis and Classification of Rosacea: Usability Study

A Novel Convolutional Neural Network for the Diagnosis and Classification of Rosacea: Usability Study

Automated Flaw Detection in Multi-channel Phased Array Ultrasonic Data Using Machine Learning

Uso da inteligência artificial para predição de acidentes de trabalho com materiais biológicos em profissionais da saúde

Contact Info

Product

Resources

About