Apply lightweight deep learning on internet of things for low-cost and easy-To-Access skin cancer detection

Pranjal Sahu, Dantong Yu, Hong Qin

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Scopus citations

Abstract

Melanoma is the most dangerous form of skin cancer that often resembles moles. Dermatologists often recommend regular skin examination to identify and eliminate Melanoma in its early stages. To facilitate this process, we propose a hand-held computer (smart-phone, Raspberry Pi) based assistant that classifies with the dermatologist-level accuracy skin lesion images into malignant and benign and works in a standalone mobile device without requiring network connectivity. In this paper, we propose and implement a hybrid approach based on advanced deep learning model and domain-specific knowledge and features that dermatologists use for the inspection purpose to improve the accuracy of classification between benign and malignant skin lesions. Here, domain-specific features include the texture of the lesion boundary, the symmetry of the mole, and the boundary characteristics of the region of interest. We also obtain standard deep features from a pre-Trained network optimized for mobile devices called Google's MobileNet. The experiments conducted on ISIC 2017 skin cancer classification challenge demonstrate the effectiveness and complementary nature of these hybrid features over the standard deep features. We performed experiments with the training, testing and validation data splits provided in the competition. Our method achieved area of 0.805 under the receiver operating characteristic curve. Our ultimate goal is to extend the trained model in a commercial hand-held mobile and sensor device such as Raspberry Pi and democratize the access to preventive health care.

Original languageEnglish (US)
Title of host publicationMedical Imaging 2018
Subtitle of host publicationImaging Informatics for Healthcare, Research, and Applications
EditorsPo-Hao Chen, Jianguo Zhang
PublisherSPIE
ISBN (Electronic)9781510616479
DOIs
StatePublished - 2018
EventMedical Imaging 2018: Imaging Informatics for Healthcare, Research, and Applications - Houston, United States
Duration: Feb 13 2018Feb 15 2018

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume10579
ISSN (Print)1605-7422

Other

OtherMedical Imaging 2018: Imaging Informatics for Healthcare, Research, and Applications
CountryUnited States
CityHouston
Period2/13/182/15/18

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Atomic and Molecular Physics, and Optics
  • Radiology Nuclear Medicine and imaging

Keywords

  • Deep learning
  • Internet of things
  • Melanoma
  • Polar Harmonic Transform
  • Raspberry Pi
  • Skin cancer
  • Transfer learning

Fingerprint Dive into the research topics of 'Apply lightweight deep learning on internet of things for low-cost and easy-To-Access skin cancer detection'. Together they form a unique fingerprint.

Cite this