Simplified grading scale for IR breast thermography using as a first-line component of a multi-imaging breast cancer detection strategy.

Abstract

Objective.In this study, we propose a simplified, objective grading scale (mild, moderate, or severe) for infrared breast thermography, intended as a first-line component of a multi-imaging breast cancer detection strategy. The goal was to provide a repeatable, automated alternative to traditional scales, such as the Ville Marie scale, which rely on subjective vascular assessments.Approach.Thermal images of the anterior view of the breasts from 246 asymptomatic volunteers and 54 women with biopsy-confirmed breast cancer were analyzed. Five distinct areas of interest were identified and segmented: the nipples and areolas, the breast tissue, the axillary tails, the axillas, and the submammary region. Breast hyperthermia, which is the difference between the maximal temperature of one breast (without the nipple and areola) and the mean temperature of the contralateral breast, was calculated. To minimize physiological and environmental variability, temperature differences relative to the body surface temperature were calculated. Abnormality and asymmetry levels were quantified using empiricalz-scores. To evaluate the global abnormality and asymmetry grading levels of the thermal images, Mahalanobis distances were calculated to assess the joint probability of six thermal variables against an empirical 6-dimensional normal distribution.Main results.Utilizing relative temperatures reduced variability from 1.0 °C - 1.5 °C to 0.4 °C - 0.9 °C compared to absolute measurements for images of asymptomatic women. While the axillary and submammary regions showed no correlation with the presence of cancer, the nipple with areola, breast regions, and breast hyperthermia exhibited significant differences in cases with confirmed cancer. Based on the maximum severity rule, 64.8% of women with cancer presented moderate or severe abnormality grades, whereas 94.7% of asymptomatic women fell within the mild-to-moderate range.Significance.The proposed model is fully objective and suitable for automated processing, thereby reducing the dependence on technician experience. It establishes a clear clinical triage protocol: mild cases indicate no thermographic abnormalities, moderate cases require follow-up within several months, and severe cases should be immediately referred for medical evaluation.