Automated Breast Lesion Segmentation in Ultrasound Images
This work addresses breast cancer diagnosis by improving lesion segmentation in ultrasound images, but it is incremental as it combines existing methods.
The paper tackled the problem of segmenting breast lesions in ultrasound images by discarding low contrast regions and speckle noise, achieving accurate evaluation measures through comparison with ground-truth annotations.
The main objective of this project is to segment different breast ultrasound images to find out lesion area by discarding the low contrast regions as well as the inherent speckle noise. The proposed method consists of three stages (removing noise, segmentation, classification) in order to extract the correct lesion. We used normalized cuts approach to segment ultrasound images into regions of interest where we can possibly finds the lesion, and then K-means classifier is applied to decide finally the location of the lesion. For every original image, an annotated ground-truth image is given to perform comparison with the obtained experimental results, providing accurate evaluation measures.