Classification of factors influencing the use of infrared thermography in humans: A review

Breast thermography from an image processing viewpoint: A survey

Breast cancer is one of the leading causes for high mortality rates among young women, in the developing countries. Currently mammography is used as the gold standard for screening breast cancer. Due to its inherent disadvantages, alternative techniques are being considered for this purpose. Breast thermography is one such imaging modality, which represents the temperature variations of breast in the form of intensity variations on an image. In the last decade, several studies have been made to evaluate the potential of breast thermograms in detecting abnormal breast conditions, from an image processing view point. This paper proposes a curvelet transform based feature extraction method for automatic detection of abnormality in breast thermograms. Statistical and texture features are extracted from thermograms in the curvelet domain, to feed a support vector machine for automatic classification. The classifier detects abnormal thermograms with an accuracy of 90.91 %. The results of the study indicate that texture features have better potential to detect abnormality in breast thermograms, when extracted in the multiresolution curvelet domain.

Detection of Breast Abnormality from Thermograms Using Curvelet Transform Based Feature Extraction

Evaluation of digital infra–red thermal imaging as an adjunctive screening method for breast carcinoma: A pilot study

For over the three decades, various researchers have aimed to construct a thermal (or bioheat) model of breast cancer, but these models have mostly lacked clinical data The present study developed a computational thermal model of breast cancer based on high-resolution infrared (IR) images, real three-dimensional (3D) breast surface geometries, and internal tumor definition of a female subject histologically diagnosed with breast cancer A state-of-the-art IR camera recorded IR images of the subject’s breasts, a 3D scanner recorded surface geometries, and standard diagnostic imaging procedures provided tumor sizes and spatial locations within the breast The study estimated the thermal characteristics of the subject’s triple negative breast cancer by calibrating the model to the subject’s clinical data Constrained by empirical blood perfusion rates, metabolic heat generation rates reached as high as 20E04 W/m3 for normal breast tissue and ranged between 10E05–12E06 W/m3 for cancerous breast tissue Results were specific to the subject’s unique breast cancer molecular subtype, stage, and lesion size and may be applicable to similar aggressive cases Prior modeling efforts are briefly surveyed, clinical data collected are presented, and finally thermal modeling results are presented and discussed

/pdf/determining-the-thermal-characteristics-of-breast-cancer-2oj8mk25cr.pdf

Determining the thermal characteristics of breast cancer based on high-resolution infrared imaging, 3D breast scans, and magnetic resonance imaging.

Background & objectives: Non-invasive and non-ionizing medical imaging techniques are safe as these can be repeatedly used on as individual and are applicable across all age groups. Breast thermography is a non-invasive and non-ionizing medical imaging that can be potentially used in breast cancer detection and diagnosis. In this study, we used breast thermography to estimate the tumour contour from the breast skin surface temperature. Methods: We proposed a framework called infrared thermography based image construction (ITBIC) to estimate tumour parameters such as size and depth from cancerous breast skin surface temperature data. Markov Chain Monte Carlo method was used to enhance the accuracy of estimation in order to reflect clearly realistic situation. Results: We validated our method experimentally using Watermelon and Agar models. For the Watermelon experiment error in estimation of size and depth parameters was 1.5 and 3.8 per cent respectively. For the Agar model it was 0 and 8 per cent respectively. Further, thermal breast screening was done on female volunteers and compared it with the magnetic resonance imaging. The results were positive and encouraging. Interpretation & conclusions: ITBIC is computationally fast thermal imaging system and is perhaps affordable. Such a system will be useful for doctors or radiologists for breast cancer diagnosis.

Framework for estimating tumour parameters using thermal imaging

Breast thermography is a painless, non-invasive and non-ionizing medical imaging technique useful for early breast screening Study shows that abnormal breast thermal image initiates the requirement for detailed diagnosis to probe the presence of cancerous cells Hence identification of the subject's breast thermal image as normal or a case for follow-up is a necessity for diagnosis Breast thermal image is a visual representation of breast skin surface temperature Direct visual interpretation of breast thermal image to conclude whether it is normal or a case for follow-up (abnormal) is tedious In this work we propose a interpretation system for characterization of breast thermal image as normal or a case for follow-up Our proposed system is represented as ITBIC interpreter Breast thermal images obtained from 50 female volunteers were characterized using ITBIC interpreter, results are matching to clinical findings With graphical user interface, ITBIC interpreter will be a useful tool for initial and mass screening of subjects

Sandeep Jaipurkar

Papers

Framework for estimating tumour parameters using thermal imaging

Interpreter for breast thermogram characterization