Sistem Temu Kembali Citra Termal Kanker Payudara Pada Citra Rekam Medis

Abstract

Medical record images (Medical Imaging) in the form of the thermal images can be able to detect of of breast cancer as early detector for the patient. The technic process is by utilizing the thermal image of an existing breast cancer patient, the thermal image of the new patient can be searched by the similarities the image of the old patient. In order to get the exactly results, required an accurate system to find the thermal imaging of breast cancer patients in the thermal image database. This study aims to build a Content Based Imaged Retrieval (CBIR) system for thermal images of breast cancer patients based on thermal images have been diagnosed by specialist doctors. This system with using a combination of color histogram features and dominant color descriptors. To determine the similarity between the query image and the dataset image with using of two methods that is measuring the Euclidean Distance and the Minkowski Distance. The results of this research show from testing the combination between the two features, the F-measure evaluation value obtained from the top 10 retrieval was in the healthy image category of 0.07 and 0.09 in the cancer image category. From the conducting testing process result, the concluded is the most appropriate feature in carrying out the breast thermal image retrieval process is using a combination of dominant color descriptor features and color histograms.

Keywords

• thermal imaging, cbir, breast cancer, color coded histogram, dominant color descriptor, minkowski distance