Affiliations: [a] Department of Electronics and Communication Engineering, College of Engineering Guindy, Anna University, Chennai, India | [b] Non Invasive Imaging and Diagnostics Laboratory, Biomedical Engineering Group, Department of Applied Mechanics, Indian Institute of Technology Madras, Chennai, India
Correspondence:
[*]
Corresponding author: S. Prabha, Department of Electronics and Communication Engineering, College of Engineering Guindy, Anna University, Chennai, India. Tel.: +91 9962987495; E-mail:harprabha@gmail.com
Abstract:
BACKGROUND: Breast thermography is a potential imaging method for the early
detection of breast cancer. The pathological conditions can be determined by
measuring temperature variations in the abnormal breast regions. Accurate
delineation of breast tissues is reported as a challenging task due to
inherent limitations of infrared images such as low contrast, low signal to
noise ratio and absence of clear edges. OBJECTIVE: Segmentation technique is attempted to delineate the breast
tissues by detecting proper lower breast boundaries and inframammary folds.
Characteristic features are extracted to analyze the asymmetrical thermal
variations in normal and abnormal breast tissues. METHODS: An automated analysis of thermal variations of breast tissues is
attempted using nonlinear adaptive level sets and Riesz transform. Breast
thermal images are initially subjected to Stein's unbiased risk estimate
based orthonormal wavelet denoising. These denoised images are enhanced
using contrast-limited adaptive histogram equalization method. The breast
tissues are then segmented using non-linear adaptive level set method. The
phase map of enhanced image is integrated into the level set framework for
final boundary estimation. The segmented results are validated against the
corresponding ground truth images using overlap and regional similarity
metrics. The segmented images are further processed with Riesz transform and
structural texture features are derived from the transformed coefficients to
analyze pathological conditions of breast tissues. RESULTS: Results show that the estimated average signal to noise ratio of
denoised images and average sharpness of enhanced images are improved by
38% and 6% respectively. The interscale consideration adopted in the
denoising algorithm is able to improve signal to noise ratio by preserving
edges. The proposed segmentation framework could delineate the breast
tissues with high degree of correlation (97%) between the segmented and
ground truth areas. Also, the average segmentation accuracy and sensitivity
are found to be 98%. Similarly, the maximum regional overlap between
segmented and ground truth images obtained using volume similarity measure
is observed to be 99%. Directionality as a feature, showed a considerable
difference between normal and abnormal tissues which is found to be 11%. CONCLUSION: The proposed framework for breast thermal image
analysis that is aided with necessary preprocessing is found to be useful in
assisting the early diagnosis of breast abnormalities.
Keywords: Breast thermography, level sets, segmentation, denoising, Riesz transform
