Computer vision-based breast self-examination palpation pressure level classification using artificial neural networks and wavelet transforms
Breast cancer is the leading cause of cancer mortality among women and early diagnosis with proper treatment is the key to survival. Women who practice regular breast self-examination are the ones most likely to detect early abnormalities in their breast. However, studies have shown that most women...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | text |
| Published: |
Animo Repository
2012
|
| Subjects: | |
| Online Access: | https://animorepository.dlsu.edu.ph/faculty_research/1734 https://animorepository.dlsu.edu.ph/context/faculty_research/article/2733/type/native/viewcontent |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | De La Salle University |
| Summary: | Breast cancer is the leading cause of cancer mortality among women and early diagnosis with proper treatment is the key to survival. Women who practice regular breast self-examination are the ones most likely to detect early abnormalities in their breast. However, studies have shown that most women performing BSE do not carry out the procedure efficiently. This paper presents a method for BSE procedure guidance through the classification of palpation pressure levels, i.e. superficial, medium, and deep, based on computer vision. In particular, we utilize an artificial neural network (ANN) to classify the pressure levels of the image frames extracted from an actual BSE video yielding an accuracy of 91 % respectively. © 2012 IEEE. |
|---|