Segmentasi Citra USG Kanker Payudara Dengan Menggunakan Metode Active Contour
Total View This Week0
Total View This Week0
Institusion
Institut Teknologi Perusahaan Listrik Negara
Author
Manurung, Joshua Melvin
Kuswardani, Dwina
Agtriadi, Herman Bedi
Kuswardani, Dwina
Agtriadi, Herman Bedi
Subject
Teknik Informatika
Datestamp
2022-09-28 02:23:00
Abstract :
Breast cancer is one of the cancers that has the highest number of deaths. In Indonesia, according to the Ministry of Health, breast cancer accounts for 16% of all types of cancer affecting women and 22.9% of invasive cancers in women. Ultrasonography is used as a tool to take images of tumors or cancer, but the resulting images or images still have noise. Image processing can be used to improve the quality of images and image segmentation is used to separate an object from other objects in an image into objects based on certain characteristics. Limited Adaptive Histogram Equalization (CLAHE) method and Contrast Stretching is used to improve image quality, for image segmentation using Active Contour method. And to validate the segmentation results using Receiver Operating Characteristic (ROC) method. Tests using 20 ultrasound images of breast cancer which are divided into benign cancer and malignant cancer, the results of segmentation in benign cancer produce an accuracy of 92.35%, a sensitivity of 80.5% and a specificity of 93.41% and in malignant cancer it produces an accuracy of 73.9%, a sensitivity of 57.83% and specificity 73.49%. This research uses the MATLAB application (R2015a).
Breast cancer is one of the cancers that has the highest number of deaths. In Indonesia, according to the Ministry of Health, breast cancer accounts for 16% of all types of cancer affecting women and 22.9% of invasive cancers in women. Ultrasonography is used as a tool to take images of tumors or cancer, but the resulting images or images still have noise. Image processing can be used to improve the quality of images and image segmentation is used to separate an object from other objects in an image into objects based on certain characteristics. Limited Adaptive Histogram Equalization (CLAHE) method and Contrast Stretching is used to improve image quality, for image segmentation using Active Contour method. And to validate the segmentation results using Receiver Operating Characteristic (ROC) method. Tests using 20 ultrasound images of breast cancer which are divided into benign cancer and malignant cancer, the results of segmentation in benign cancer produce an accuracy of 92.35%, a sensitivity of 80.5% and a specificity of 93.41% and in malignant cancer it produces an accuracy of 73.9%, a sensitivity of 57.83% and specificity 73.49%. This research uses the MATLAB application (R2015a).
Download
book
BibTex
Latex, Jabref
cloud_download
Original Resource
url resource Institution
