PAD-UFES-20: A skin lesion dataset composed of patient data and clinical images collected from smartphones

Pacheco, André G. C.; Lima, Gustavo R.; Salomão, Amanda S.; Krohling, Breno A.; Biral, Igor Peixoto; Angelo, Gabriel G. de; Alves, Fábio C. R.; Esgario, José G. M.; Simora, Alana C.; Castro, Pedro B. C.; Rodrigues, Felipe B.; Frasson, P; Krohling, Renato A.; Knidel, Helder; Santos, Maria C. S.; Santo, Rachel Bertolani do Espírito; Macedo, Telma L. S. G.; Canuto, Tania R. P.; Barros, Luíz F. S. de

doi:10.1016/j.dib.2020.106221

Cited by 132 publications

(61 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…is section contains the description of the data set (PAD-UFES-20) used in the studies, data preprocessing, and classification model used in the study. [29] data set was collected under the Dermatological and Surgical Assistance Program (PAD) at Federal University of Espírito Santo. e PAD-UFES-20 data set consists of skin lesions and clinical data with an average patient's age of 60 years.…”

Section: Methodsmentioning

confidence: 99%

Remote Diagnosis and Triaging Model for Skin Cancer Using EfficientNet and Extreme Gradient Boosting

et al. 2021

View full text Add to dashboard Cite

Due to the successful application of machine learning techniques in several fields, automated diagnosis system in healthcare has been increasing at a high rate. The aim of the study is to propose an automated skin cancer diagnosis and triaging model and to explore the impact of integrating the clinical features in the diagnosis and enhance the outcomes achieved by the literature study. We used an ensemble-learning framework, consisting of the EfficientNetB3 deep learning model for skin lesion analysis and Extreme Gradient Boosting (XGB) for clinical data. The study used PAD-UFES-20 data set consisting of six unbalanced categories of skin cancer. To overcome the data imbalance, we used data augmentation. Experiments were conducted using skin lesion merely and the combination of skin lesion and clinical data. We found that integration of clinical data with skin lesions enhances automated diagnosis accuracy. Moreover, the proposed model outperformed the results achieved by the previous study for the PAD-UFES-20 data set with an accuracy of 0.78, precision of 0.89, recall of 0.86, and F1 of 0.88. In conclusion, the study provides an improved automated diagnosis system to aid the healthcare professional and patients for skin cancer diagnosis and remote triaging.

show abstract

Section: Methodsmentioning

confidence: 99%

Remote Diagnosis and Triaging Model for Skin Cancer Using EfficientNet and Extreme Gradient Boosting

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Both polarized and non-polarized dermoscopic images were included. Non-dermoscopic smartphone images, captured by different non-standardized smartphone devices (Table 1 ), were derived from a recently published and biopsy-validated dataset (Pacheco et al 2020 ) dedicated to NMSC at a 1:3 random selection ( n = 159) and The Journal of Investigative Dermatology Editorial Images 2018 ( n = 39). Random selections were performed by using a Phyton script.…”

Section: Methodsmentioning

confidence: 99%

Non-melanoma skin cancer diagnosis: a comparison between dermoscopic and smartphone images by unified visual and sonification deep learning algorithms

Dascalu

Walker

Oron

et al. 2021

J Cancer Res Clin Oncol

View full text Add to dashboard Cite

Purpose Non-melanoma skin cancer (NMSC) is the most frequent keratinocyte-origin skin tumor. It is confirmed that dermoscopy of NMSC confers a diagnostic advantage as compared to visual face-to-face assessment. COVID-19 restrictions diagnostics by telemedicine photos, which are analogous to visual inspection, displaced part of in-person visits. This study evaluated by a dual convolutional neural network (CNN) performance metrics in dermoscopic (DI) versus smartphone-captured images (SI) and tested if artificial intelligence narrows the proclaimed gap in diagnostic accuracy. Methods A CNN that receives a raw image and predicts malignancy, overlaid by a second independent CNN which processes a sonification (image-to-sound mapping) of the original image, were combined into a unified malignancy classifier. All images were histopathology-verified in a comparison between NMSC and benign skin lesions excised as suspected NMSCs. Study criteria outcomes were sensitivity and specificity for the unified output. Results Images acquired by DI (n = 132 NMSC, n = 33 benign) were compared to SI (n = 170 NMSC, n = 28 benign). DI and SI analysis metrics resulted in an area under the curve (AUC) of the receiver operator characteristic curve of 0.911 and 0.821, respectively. Accuracy was increased by DI (0.88; CI 81.9–92.4) as compared to SI (0.75; CI 68.1–80.6, p < 0.005). Sensitivity of DI was higher than SI (95.3%, CI 90.4–98.3 vs 75.3%, CI 68.1–81.6, p < 0.001), but not specificity (p = NS). Conclusion Telemedicine use of smartphone images might result in a substantial decrease in diagnostic performance as compared to dermoscopy, which needs to be considered by both healthcare providers and patients.

show abstract

“…Another source of clinical images is MED-NODE [15]. This latest version of ebioMelDB includes 220 additional dermoscopy images, retrieved from the ISIC2018 Validation set of images and 2298 clinical images from the recently published PAD-UFES-20 [16] dataset which contains clinical images accompanied with clinical information.…”

Section: Image Data Collectionmentioning

confidence: 99%

A Collection of Multimodal Melanoma Data

2021

View full text Add to dashboard Cite

Computer-aided diagnosis, prognosis and therapy systems have been of great interest for a number of years. The availability of big volumes of data and of powerful computational resources have allowed artificial intelligence approaches to emerge in melanoma related studies. However, for such approaches to have good predictive performances data availability is of crucial importance. Melanoma related imaging, biological and clinical data can be found partially and scattered in various repositories. Thus, in this work, we assemble in a web accessible database, named ebioMelDB, the widest collection of clinical and dermoscopy images accompanied with patient clinical data and the widest collection of RNA-Seq gene expression data accompanied with patient clinical data. The database organization allows users to select the data that are appropriate for their application of interest (diagnosis, prognosis and therapy). Keywords: melanoma database, integrated data, dermoscopy, imaging, RNA-Seq, clinical data.

show abstract

PAD-UFES-20: A skin lesion dataset composed of patient data and clinical images collected from smartphones

Cited by 132 publications

References 17 publications

Remote Diagnosis and Triaging Model for Skin Cancer Using EfficientNet and Extreme Gradient Boosting

Remote Diagnosis and Triaging Model for Skin Cancer Using EfficientNet and Extreme Gradient Boosting

Non-melanoma skin cancer diagnosis: a comparison between dermoscopic and smartphone images by unified visual and sonification deep learning algorithms

A Collection of Multimodal Melanoma Data

Contact Info

Product

Resources

About