TY - GEN
T1 - Development of Convolutional Neural Network-Based AI-Dermatoscope for Non-Invasive Skin Assessments
AU - Kahatapitiya, Nipun Shantha
AU - Wijethunge, Akila
AU - Edirisinghe, Sajith
AU - Silva, Bhagya Nathali
AU - Jeon, Mansik
AU - Kim, Jeehyun
AU - Wijenayake, Udaya
AU - Wijesinghe, Ruchire Eranga
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Early detection of skin conditions is crucial, and some skin conditions can become more difficult to treat if left untreated. The gold standard Dermatoscope is a non-invasive technique used for the examination and evaluation of skin lesions, which is equipped with a magnifying lens and a light source. However, precise inspection of existing dermatoscopes has become a limitation due to the unavailability of image-analyzing methods. Herein, this study reports the successful development of a Convolutional Neural Networks (CNN) based, Artificial intelligence (AI)-Dermatoscope integrating optics and a smart illumination system to enhance the accurate examination of acne conditions of the skin. The system was trained on a large dataset of acne to accurately identify and classify skin conditions. Finally, the system utilizes CNN knowledge to predict new images of skin and provide diagnostic information to doctors and other healthcare professionals. Thus, this system will improve the accuracy and speed of skin diagnosis, and consequently, improve the health-related quality of life of patients.
AB - Early detection of skin conditions is crucial, and some skin conditions can become more difficult to treat if left untreated. The gold standard Dermatoscope is a non-invasive technique used for the examination and evaluation of skin lesions, which is equipped with a magnifying lens and a light source. However, precise inspection of existing dermatoscopes has become a limitation due to the unavailability of image-analyzing methods. Herein, this study reports the successful development of a Convolutional Neural Networks (CNN) based, Artificial intelligence (AI)-Dermatoscope integrating optics and a smart illumination system to enhance the accurate examination of acne conditions of the skin. The system was trained on a large dataset of acne to accurately identify and classify skin conditions. Finally, the system utilizes CNN knowledge to predict new images of skin and provide diagnostic information to doctors and other healthcare professionals. Thus, this system will improve the accuracy and speed of skin diagnosis, and consequently, improve the health-related quality of life of patients.
KW - acne
KW - computer vision
KW - convolutional neural network (CNN)
KW - dermatoscope
KW - image processing
KW - optics
KW - skin conditions
UR - http://www.scopus.com/inward/record.url?scp=85186139950&partnerID=8YFLogxK
U2 - 10.1109/ICAC60630.2023.10417424
DO - 10.1109/ICAC60630.2023.10417424
M3 - Conference contribution
AN - SCOPUS:85186139950
T3 - ICAC 2023 - 5th International Conference on Advancements in Computing: Technological Innovation for a Sustainable Economy, Proceedings
SP - 852
EP - 856
BT - ICAC 2023 - 5th International Conference on Advancements in Computing
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 5th International Conference on Advancements in Computing, ICAC 2023
Y2 - 7 December 2023 through 8 December 2023
ER -
