The present work presents a methodology to automatically detect the symmetry point of breast. In order to achieve this goal, the algorithm corrects thermal image tilt to find a breast symmetry axis, compute a modified symmetric index that can be used as a measure of image quality, breast cosmetic and pathologic issues, and a seed location for a former algorithm reported to automatically achieve breast cancer analysis. The methodology involves filtering, edge detection, windowing edge analysis and shape detection based on the Hough transform. Experimental results show that the proposed method is able to define the symmetry axis as precise as a person do, and correctly detected breast areas in 100% of the cases considered, allowing automatic breast analysis by a previous algorithm.

Abstract. Breast thermography is a promising technique allowing breast cancer detection with the aid of infrared technology. However, the automatic segmentation of the regions of interest (ROI) to be analyzed is a difficult task and, thus, it is not commonly performed. In this paper we propose an automated technique for ROI extraction. The algorithm uses Canny edge detection with automatic threshold and symmetry inspection in order to correct tilt errors and to define a symmetry axis in the image. Furthermore, the Hough transform is used to provide circles giving a favorable approximation to the ROI. A region-based active contours technique and an edge smoothing technique are also used to improve the previous segmentation, taking in consideration the energies of the images. Experimental results indicate that the ROI were extracted more accurately and with higher precision than a state-of-the-art method.

No abstract