Towards a Mobile and Fast Melanoma Detection System

DIego Rivera; Felipe Grijalva; Byron Alejandro Acuna Acurio; Robin Alvarez

doi:10.1109/LA-CCI47412.2019.9037058

Towards a Mobile and Fast Melanoma Detection System

DIego Rivera
, Felipe Grijalva
, Byron Alejandro Acuna Acurio
, Robin Alvarez

Escuela Politecnica Nacional
Universidade Estadual de Campinas

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

8 Scopus citations

Abstract

Early detection of melanoma is crucial to avoid skin cancer deaths, but only with the recent advances of deep convolutional neural networks architectures, such as MobileNet, it is possible to create a reliable enough system to detect melanoma, that can be implemented on resource constrained environments such as mobile phones or embedded systems. With this aim, this work assesses the performance of the implementation of an early melanoma recognition system using MobileNet trained from the HAM10000 database. Besides, we explain in detail two strategies to improve melanoma classification task, i.e., data augmentation on an unbalanced dataset and a multiclass approach to address a binary classification problem. Numerical results in terms of AUC metric and ROC curves corroborate the validity of our model. The performance of the proposed model is also compared to the average dermatologist performance.

Original language	English
Title of host publication	2019 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728156668
DOIs	https://doi.org/10.1109/LA-CCI47412.2019.9037058
State	Published - Nov 2019
Externally published	Yes
Event	6th IEEE Latin American Conference on Computational Intelligence, LA-CCI 2019 - Guayaquil, Ecuador Duration: 11 Nov 2019 → 15 Nov 2019

Publication series

Name	2019 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2019

Conference

Conference	6th IEEE Latin American Conference on Computational Intelligence, LA-CCI 2019
Country/Territory	Ecuador
City	Guayaquil
Period	11/11/19 → 15/11/19

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Access to Document

10.1109/LA-CCI47412.2019.9037058

Cite this

Rivera, DI., Grijalva, F., Acurio, B. A. A., & Alvarez, R. (2019). Towards a Mobile and Fast Melanoma Detection System. In 2019 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2019 Article 9037058 (2019 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/LA-CCI47412.2019.9037058

@inproceedings{4cbc9661efbf40c0bb93a826a755fb93,

title = "Towards a Mobile and Fast Melanoma Detection System",

abstract = "Early detection of melanoma is crucial to avoid skin cancer deaths, but only with the recent advances of deep convolutional neural networks architectures, such as MobileNet, it is possible to create a reliable enough system to detect melanoma, that can be implemented on resource constrained environments such as mobile phones or embedded systems. With this aim, this work assesses the performance of the implementation of an early melanoma recognition system using MobileNet trained from the HAM10000 database. Besides, we explain in detail two strategies to improve melanoma classification task, i.e., data augmentation on an unbalanced dataset and a multiclass approach to address a binary classification problem. Numerical results in terms of AUC metric and ROC curves corroborate the validity of our model. The performance of the proposed model is also compared to the average dermatologist performance.",

author = "DIego Rivera and Felipe Grijalva and Acurio, \{Byron Alejandro Acuna\} and Robin Alvarez",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 6th IEEE Latin American Conference on Computational Intelligence, LA-CCI 2019 ; Conference date: 11-11-2019 Through 15-11-2019",

year = "2019",

month = nov,

doi = "10.1109/LA-CCI47412.2019.9037058",

language = "Ingl{\'e}s",

series = "2019 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2019",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2019 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2019",

}

Rivera, DI, Grijalva, F, Acurio, BAA & Alvarez, R 2019, Towards a Mobile and Fast Melanoma Detection System. in 2019 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2019., 9037058, 2019 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2019, Institute of Electrical and Electronics Engineers Inc., 6th IEEE Latin American Conference on Computational Intelligence, LA-CCI 2019, Guayaquil, Ecuador, 11/11/19. https://doi.org/10.1109/LA-CCI47412.2019.9037058

Towards a Mobile and Fast Melanoma Detection System. / Rivera, DIego; Grijalva, Felipe; Acurio, Byron Alejandro Acuna et al.
2019 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2019. Institute of Electrical and Electronics Engineers Inc., 2019. 9037058 (2019 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2019).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Towards a Mobile and Fast Melanoma Detection System

AU - Rivera, DIego

AU - Grijalva, Felipe

AU - Acurio, Byron Alejandro Acuna

AU - Alvarez, Robin

PY - 2019/11

Y1 - 2019/11

N2 - Early detection of melanoma is crucial to avoid skin cancer deaths, but only with the recent advances of deep convolutional neural networks architectures, such as MobileNet, it is possible to create a reliable enough system to detect melanoma, that can be implemented on resource constrained environments such as mobile phones or embedded systems. With this aim, this work assesses the performance of the implementation of an early melanoma recognition system using MobileNet trained from the HAM10000 database. Besides, we explain in detail two strategies to improve melanoma classification task, i.e., data augmentation on an unbalanced dataset and a multiclass approach to address a binary classification problem. Numerical results in terms of AUC metric and ROC curves corroborate the validity of our model. The performance of the proposed model is also compared to the average dermatologist performance.

AB - Early detection of melanoma is crucial to avoid skin cancer deaths, but only with the recent advances of deep convolutional neural networks architectures, such as MobileNet, it is possible to create a reliable enough system to detect melanoma, that can be implemented on resource constrained environments such as mobile phones or embedded systems. With this aim, this work assesses the performance of the implementation of an early melanoma recognition system using MobileNet trained from the HAM10000 database. Besides, we explain in detail two strategies to improve melanoma classification task, i.e., data augmentation on an unbalanced dataset and a multiclass approach to address a binary classification problem. Numerical results in terms of AUC metric and ROC curves corroborate the validity of our model. The performance of the proposed model is also compared to the average dermatologist performance.

UR - https://www.scopus.com/pages/publications/85083117054

U2 - 10.1109/LA-CCI47412.2019.9037058

DO - 10.1109/LA-CCI47412.2019.9037058

M3 - Contribución a la conferencia

AN - SCOPUS:85083117054

T3 - 2019 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2019

BT - 2019 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 6th IEEE Latin American Conference on Computational Intelligence, LA-CCI 2019

Y2 - 11 November 2019 through 15 November 2019

ER -

Rivera DI, Grijalva F, Acurio BAA, Alvarez R. Towards a Mobile and Fast Melanoma Detection System. In 2019 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2019. Institute of Electrical and Electronics Engineers Inc. 2019. 9037058. (2019 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2019). doi: 10.1109/LA-CCI47412.2019.9037058

Towards a Mobile and Fast Melanoma Detection System

Abstract

Publication series

Conference

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this