2017/03/29 by Filipe Rolim Cordeiro, F. R. Cordeiro, Wellington Pinheiro dos Santos +3
Computer Science · Engineering · #AI in cancer detection #Advanced Neural Network Applications #Breast cancer #Computer-aided diagnosis #Cut #Digital mammography #Graph #Image segmentation #Mammography #Medical Image Segmentation Techniques #Pattern recognition (psychology) #Segmentation #cs.AI #cs.CV #cs.NE #eess.IV
paper · pdf · doi:10.1080/21681163.2015.1127775
published as Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, v. 5, p. 1-19, 2017
openalex publication_date 2017/03/29 · openalex created_date 2017/04/07 · arxiv created 2017/12/20 · arxiv updated 2017/12/21 · openalex updated_date 2026/08/05
Breast cancer is already one of the most common form of cancer worldwide. Mammography image analysis is still the most effective diagnostic method to promote the early detection of breast cancer. Accurately segmenting tumours in digital mammography images is important to improve diagnosis capabilities of health specialists and avoid misdiagnosis. In this work, we evaluate the feasibility of applying GrowCut to segment regions of tumour and we propose two GrowCut semi-supervised versions. All the analyses were performed by evaluating the application of segmentation techniques to a set of images obtained from the Mini-MIAS mammography image database. GrowCut segmentation was compared to Region Growing, Active Contours, Random Walks and Graph Cut techniques. Experiments showed that GrowCut, when compared to the other techniques, was able to acquire better results for the metrics analysed. Moreover, the proposed semi-supervised versions of GrowCut were proved to have a clinically satisfactory quality of segmentation.