SEGMENTASI CITRA MAMMOGRAM KANKER PAYUDARA MENGGUNAKAN METODE ACTIVE CONTOUR
Total View This Week0
Total View This Week0
Institusion
Institut Teknologi Perusahaan Listrik Negara
Author
FADHILLAH, WIDYA NUR
Kusward, Dwina
Agtriadi, Herman Bedi
Kusward, Dwina
Agtriadi, Herman Bedi
Subject
Teknik Informatika
Datestamp
2023-05-30 01:57:35
Abstract :
Breast cancer is one of the diseases with a high mortality rate. According to data from the Global Cancer Observatory in 2018 in Indonesia breast cancer patients ranked first with 58,256 new cases and ranked second for death cases totaling 22,692 cases. Breast cancer examination can be done using mammography radiology examination, but there are difficulties in diagnosing the results because it depends on the quality of the mammogram image and the experience of the radiologist. This study was conducted to perform segmentation to separate breast cancer lesions from other objects. Initially, the mammogram image will be enhanced using Inverse and Contrast Limited Adaptive Histogram Equalization (CLAHE) methods. The segmentation method used in this research is Active Contour. The implementation of the proposed method is applied to all mammogram images sourced from the CBIS-DDSM dataset. Based on testing using the Receiver Operating Characteristic (ROC) method, the average accuracy rate is 90.12% for benign breast cancer and 82.81% for maglinant breast cancer.
Breast cancer is one of the diseases with a high mortality rate. According to data from the Global Cancer Observatory in 2018 in Indonesia breast cancer patients ranked first with 58,256 new cases and ranked second for death cases totaling 22,692 cases. Breast cancer examination can be done using mammography radiology examination, but there are difficulties in diagnosing the results because it depends on the quality of the mammogram image and the experience of the radiologist. This study was conducted to perform segmentation to separate breast cancer lesions from other objects. Initially, the mammogram image will be enhanced using Inverse and Contrast Limited Adaptive Histogram Equalization (CLAHE) methods. The segmentation method used in this research is Active Contour. The implementation of the proposed method is applied to all mammogram images sourced from the CBIS-DDSM dataset. Based on testing using the Receiver Operating Characteristic (ROC) method, the average accuracy rate is 90.12% for benign breast cancer and 82.81% for maglinant breast cancer.
Download
book
BibTex
Latex, Jabref
cloud_download
Original Resource
url resource Institution
