Statistical analysis of healthy and malignant breast thermography.

Analysis of thermograms has often been subjective and has resulted in inconsistency in the diagnosis of breast diseases by thermography. The aim of this paper is to study the problem of subjective interpretation of breast thermograms and hence using thermography as an adjunct tool for breast cancer diagnosis. It ws proposed that the thermograms should be taken within the recommended screening period, classified and analysed in conjunction with an artificial neural network (ANN). Qualitative interpretation of thermal images can be carried out using an active contours algorithm. The 256 x 200 pixel image can be segmented as one of the inputs to the ANN. To achieve quantitative analysis of the breast thermograms, firstly the inputs of the ANN should be determined, so that the thermograms could be successfuly classified and based on the suggested inputs.

[1]  C. A. Lipari,et al.  Image analysis of digitized infrared images of the breasts from a first generation infrared imaging system , 1997, Proceedings of the 19th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. 'Magnificent Milestones and Emerging Opportunities in Medical Engineering' (Cat. No.97CH36136).

[2]  T. L. Williams,et al.  Applications of Thermal Imaging , 1988 .

[3]  E Y Ng,et al.  Computerized breast thermography: study of image segmentation and temperature cyclic variations. , 2001, Journal of medical engineering & technology.

[4]  E. Yu,et al.  Infrared Imaging of the Breast: Initial Reappraisal Using High‐Resolution Digital Technology in 100 Successive Cases of Stage I and II Breast Cancer , 1998, The breast journal.