Automatic Edge Correction for Nodule Cancer Segmentation using Fast Scanning Algorithm
Sigit Widiyanto, Dini Sundani, Yuli Karyanti, Dini Tri Wardani · Solid State Technology · 2020
Nodule detection is one of the goals in the field of medical imaging. The problem that often occurs from the detectionof nodules in medical images such as mammographic image is the result of improper segmentation, which results inlow segmentation accuracy. The low accuracy of segmentation can affect the area and shape of nodules. These twofeatures can be used for the classification of the cancer stage. Therefore, a method that can be used to improvesegmentation accuracy is proposed, namely edge correction. The initial edge nodules are obtained using a quantumcanny enhancement method. Edge correction is done adaptively by looking at the pixel values around the edge pixelsso that the actual edge pixels are obtained. Edge correction can also connect broken edges by looking at the edgepattern and direction. The results of this proposed method increase the average segmentation accuracy from 87%,which is the result of segmentation without using edge correction, to 95.1%. Accuracy is assessed using the Jaccardsimilarity method.