DermaDL: advanced Convolutional Neural Networks for automated melanoma detection

Author(s)

Rodrigues-Jr, Jose F. ; Brandoli, Bruno ; Amer-Yahia, Sihem ; DeHerrera, AGS ; Gonzalez, AR ; Santosh, KC ; Temesgen, Z ; Kane, B ; Soda, P

• Document type: Journal article
• Source: 2020 IEEE 33RD INTERNATIONAL SYMPOSIUM ON COMPUTER-BASED MEDICAL SYSTEMS(CBMS 2020); v. N/A, p. 6-pg., 2020-01-01.

Abstract

Early detection of melanoma, one of the deadliest types of cancer, is of paramount importance. Currently, the use of Convolutional Neural Networks (CNNs) is the main line of investigation for the automated detection of this kind of disease. Most of the existing works, however, were designed based on transferlearning general-purpose architectures to the domain of skin lesions, posing inflexibility and high processing costs to the task. In this work, we introduce a novel architecture that benefits from cutting-edge CNNs techniques Aggregated Transformations combined to the mechanism of Squeeze-and-Excite organized in a residual block; our architecture is designed and trained from scratch having the melanoma problem as goal. Our results demonstrate that such an architecture is competitive to major state-of-the-art architectures adapted to the melanoma detection problem. Having a fraction of the number of weights of previous works, our architecture is prone to evolve and to provide low processing cost for real-world in situ applications. (AU)

• FAPESP's process: 18/17620-5 - Preventive medicine by means of deep learning techniques applied in healthcare prognosis
• Grantee: José Fernando Rodrigues Júnior
• Support Opportunities: Scholarships abroad - Research
• FAPESP's process: 16/17078-0 - Mining, indexing and visualizing Big Data in clinical decision support systems (MIVisBD)
• Grantee: Agma Juci Machado Traina
• Support Opportunities: Research Projects - Thematic Grants