Location
Innovation Lab Atrium
Start Date
4-2-2025 2:00 PM
End Date
4-2-2025 3:30 PM
Presentation Date
2 April 2025, 2:00pm - 3:30pm
Biography
Victoria Wegley is a sophomore from Lee's Summit, Missouri studying electrical and computer engineering. She is involved with the Kummer Vanguard Scholars program, Honors Academy, and Christian Campus Fellowship. Additionally, she is exploring her research interests in artificial intelligence, deep learning, and digital image processing under the guidance of Dr. Stanley through the Opportunities for Undergraduate Research (OURE) program. She also plays violin for the S&T Orchestra. Some of her hobbies include playing piano, crocheting, and reading books.
Meeting Name
2025 - Miners Solving for Tomorrow Research Conference
Department(s)
Electrical and Computer Engineering
Document Type
Poster
Document Version
Final Version
File Type
event
Language(s)
English
Rights
© 2025 The Authors, All rights reserved
Included in
Training AI Models for Automatic Melanoma Detection
Innovation Lab Atrium
Comments
Advisor: R. Joe Stanley
Abstract:
Melanoma is recognized as one of the deadliest forms of skin cancer. Despite improved developments in treatment, the number of cases continues to rise at an unprecedented rate. Due to the rapid growth of melanoma, an early diagnosis is imperative for reducing the severity of the disease. Melanoma detection sensitivity by US dermatologists in two dermoscopy studies ranged only from 66-84%. By applying deep learning techniques for a melanoma detection AI, doctors will be assisted in diagnosis decisions. However, the training sets of images available for researchers are limited in the quality and variety of images, which impacts the accuracy of the AI. Using the largest dataset available from the International Skin Imaging Collaboration (ISIC) archive, features including overlays and annotations are added to organize and improve the quality of the dataset using digital image processing techniques. This improved dataset will be publicly available for other researchers to implement.