Literature Review of Breast Thermography

Thermal imaging has been used for early breast cancer detection and risk prediction since the sixties. Examining thermograms for abnormal hyperthermia and hyper-vascularity patterns related to tumor growth is done by comparing images of contralateral breasts. Analysis can be tedious and challenging if the differences are subtle. The advanced computer technology available today can be utilized to automate the analysis and assist in decision-making. In our study, computer routines were used to perform ROI identification and image segmentation of infrared images recorded from 19 patients. Asymmetry analysis between contralateral breasts was carried out to generate statistics that could be used as input parameters to a backpropagation ANN. A simple 1-1-1 network was trained and employed to predict clinical outcomes based on the difference statistics of mean temperature and standard deviation. Results comparing the ANN output with actual clinical diagnosis are presented. Future work will focus on including more patients and more input parameters in the analysis. Performance of ANN network can be studied to select a set of parameters that would best predict the presence of breast cancer. http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=1403371 Computerized detection of breast cancer with artificial intelligence and thermograms Authors: E. Y. -K. Ng ; S. C. Fok ; Y. C. Peh ; F. C. Ng ; L. S. J. Sim b Affiliations: a College of Engineering, School of Mechanical and Production Engineering, Nanyang Technological University, 50 Nanyang Avenue, Singapore 639798. b Diagnostic Radiology Department, Singapore General Hospital, Outram Park, Singapore 169608. DOI: 10.1080/03091900210146941 Publication Frequency: 6 issues per year Published in: Journal of Medical Engineering & Technology, Volume 26, Issue 4 July 2002 , pages 152 157 Number of References: 5 Formats available: PDF (English)  In order to give pricing details we need to know your country. Please register and/or sign in to identify your country.  Sign In  Online Sample Abstract This paper shows the concurrent use of thermography and artificial neural networks (ANN) for the diagnosis of breast cancer, a disease that is growing in prominence in women all over the world. It has been reported that breast thermography itself could detect breast cancer up to 10 years earlier than the conventional golden methods such as mammography, in particular in the younger patient. However, the accuracy of thermography is dependent on many factors such as the symmetry of the breasts' temperature and temperature stability. A woman's body temperature is known to be stable in certain periods after menstruation and it was found that the accuracy of thermography in women whose thermal images are taken in a suitable period (5th 12th and 21st day of menstruation) is higher (80%) than the total population of patients (73%). The stability of the body temperature will depend on physiological state. This paper examines the use of ANN to complement the infrared heat radiating from the surface of the body with other physiological data. Four backpropagation neural networks were developed and trained using the results from the Singapore General Hospital patients' physiological data and thermographs. Owing to the inaccuracies found in thermography and the low population size gathered for this project, the networks developed could only accurately diagnose about 61.54% of the breast cancer cases. Nevertheless, the basic neural network framework has been established and it has great potential for future development of an intelligent breast cancer diagnosis system. This would be especially useful to the teenagers and young adults who are unsuitable for mammography at a young age. An intelligent breast thermography-neural network will be able to give an accurate diagnosis of breast cancer and can make a positive impact on breast disease detection. http://www.informaworld.com/smpp/content~content=a713816863~db=all Computed tomography in detection and diagnosis of breast cancer C. H. Joseph Chang, MD 1 , Justo L. Sibala, MD , Steven L. Fritz, PhD , Samuel J. Dwyer III, PhD , Arch W. Templeton, MD , Fritz Lin, MD , William R. Jewell, MD 3 Department of Diagnostic Radiology, University of Kansas Medical Center, Kansas City, Kansas Department of Pathology, University of Kansas Medical Center, Kansas City, Kansas Department of Surgery, University of Kansas Medical Center, Kansas City, Kansas * Correspondence to C. H. Joseph Chang, Department of Diagnostic Radiology, University of Kansas Medical Center, 39th and Rainbow Blvd., Kansas City, KS 66103 ABSTRACT From October 1, 1976 through July 31, 1979, at the University of Kansas Medical Center, CT/M examinations were performed on 1625 patients. Seventy-eight cancers were histologically diagnosed. A CT/M study using our contrast medium enhancement technique yields both static anatomical changes and dynamic measurements of abnormal iodide concentrations in the breast cancers. This unique ability of CT/M provides many advantages as compared with conventional mammography in the diagnosis of breast cancer. The detection rate in 78 cancers by CT/M was 94% and 77% for the mammography. The CT/M appears to be specially superior to the mammography for detecting cancers in dense, premenopausal dysplastic breasts. The CT/M can detect totally unsuspected very small breast cancers that were unable to be identified by conventional mammography or physical examinations. The CT/M scan also seems to be a better test for recognizing precancerous high risk lesions. CT/M evaluation affords definitive diagnostic help in instances where the mammographic and/or physical examinations are inconclusive. Although CT/M will not replace conventional mammography in routine breast examinations, it overcomes the limitation of mammography.From October 1, 1976 through July 31, 1979, at the University of Kansas Medical Center, CT/M examinations were performed on 1625 patients. Seventy-eight cancers were histologically diagnosed. A CT/M study using our contrast medium enhancement technique yields both static anatomical changes and dynamic measurements of abnormal iodide concentrations in the breast cancers. This unique ability of CT/M provides many advantages as compared with conventional mammography in the diagnosis of breast cancer. The detection rate in 78 cancers by CT/M was 94% and 77% for the mammography. The CT/M appears to be specially superior to the mammography for detecting cancers in dense, premenopausal dysplastic breasts. The CT/M can detect totally unsuspected very small breast cancers that were unable to be identified by conventional mammography or physical examinations. The CT/M scan also seems to be a better test for recognizing precancerous high risk lesions. CT/M evaluation affords definitive diagnostic help in instances where the mammographic and/or physical examinations are inconclusive. Although CT/M will not replace conventional mammography in routine breast examinations, it overcomes the limitation of mammography. http://www3.interscience.wiley.com/cgi-bin/abstract/112679338/ABSTRACT Breast thermography. Nyirjesy I. PIP: This discussion of breast thermography reviews the following: techniques; the "normal" thermogram found in approximately 65% of gynecologic patients; analysis and classification of a thermogram; factors influencing thermograms (breast symmetry, breast size, age, parity, history of breast feeding, menstrual cycle, pregnancy and lactation, exogenous steroid therapy, menopause and danazol, family history of breast carcinoma, benign breast disease, and time; thermograms and breast carcinoma; and clinical considerations. The temperature and the vascularization of the breast, which are modified by endocrine, inflammatory, and tumoral influences, can be studied through pictures formed by multiple simultaneous temperature in measurements called thermograms. Thermographic examinations must be performed in a draft-free, temperature, and humidity controlled room, where a constant temperature 20 degrees C is maintained. Using telethermography, a front and right and left oblique views must be taken. For contact thermographic studies, the cholesterol plate or sheet on which color distribution corresponds the best to the patient's mean temperature should be selected and a front and an oblique view should be taken of each breast. Thermograms must be analyzed by noting anatomic and vascular symmetry, by measuring temperature differences between comparable areas of the 2 breasts, and by observing the normal round contour of the breast. In addition, repeat thermograms must be compared to previous studies and any observed change must be noted. Increased heat can be vascular, focal, or diffuse. Recent reports and opinions on relationships between abnormal thermograms and cancer are controversial. The most favorable reports on the value of thermograms in the identification and management of breast cancers originate from the University of Strasbourg and the Cancer Institute of Marseille. It is the belief of this physician that thermography is not a specific test for carcinoma detection, for the diagnosis of any other breast disease. It is, however, a sensitive marker of local thermal and vascular abnormalities, which can be helpful in focusing attention on specific patients and for research. The greatest interest of clinical thermography lies in its use in the detection of carcinoma. Patients who have an abnormal thermogram need thorough clinical evaluation. It is possible that the greatest potential application of thermography is in its use in comparison studies. http://www.ncbi.nlm.nih.gov/sites/entrez?cmd=Retrieve&db=PubMed&list_uids=7105516&dop t=Citation Thermobiological assessment of benign and malignant breast diseases. Gautherie M. The recent technical and clinical advances in breast thermography are reviewed in this article. Emphasis is placed upon liquid crystal thermal imaging and computer-assisted analysis of breast thermograms. New data are presented concerning the value of thermography for the early detection of mammary carcinomas, the identification of women at high risk of developing breast cancer, and the detection of cancer in fibrocystic breasts. http://www.ncbi.nlm.nih.gov/sites/entrez?cmd=Retrieve&db=PubMed&list_uids=6650622&dop t=Citation Palpable solid breast masses: retrospective singleand multimodality evaluation of 201 lesions PA van Dam, ML Van Goethem, E Kersschot, J Vervliet, IB Van den Veyver, A De Schepper and P Buytaert Department of Obstetrics and Gynecology, Antwerp University Hospital, Edegem, Belgium. The diagnostic virtues and limitations of singleand multimodality testing in the evaluation of solid palpable breast masses were studied. Two hundred one consecutive patients who had a solid palpable breast mass and who underwent biopsy between September 1982 and July 1986 were included for blinded retrospective analysis of their physical examination, mammographic, ultrasonographic (US), thermographic, and pathologic characteristics. Benign breast disease was diagnosed histologically in 106 women, while carcinoma was established in 95. The sensitivities of physical examination, mammography, US, and thermography were 0.88, 0.94, 0.78, and 0.49, respectively. US alone had the highest sensitivity in correct diagnosis of a benign solid breast mass and had the highest accuracy (0.84). Use of four modalities increased the preoperative diagnostic true-positive rate to 0.97, with some decline in specificity. Multimodality testing seems particularly beneficial in preand perimenopausal patients. http://radiology.rsnajnls.org/cgi/content/abstract/166/2/435 Imaging of the radiographically dense breast VP Jackson, RE Hendrick, SA Feig and DB Kopans Department of Radiology, Indiana University Medical Center, Indianapolis. Despite recent improvements in mammography equipment and technique, the radiographically dense breast remains difficult to image. The problems in imaging the dense breast account for a large percentage of the cases of mammographically "missed" carcinomas. Other imaging modalities--such as ultrasonography, transillumination, thermography, computed tomography, magnetic resonance imaging, and radionuclide imaging--have been investigated for use in breast cancer detection. This overview discusses the current problems associated with imaging of the radiographically dense breast and suggests some avenues for investigation to develop solutions to these problems. http://radiology.rsnajnls.org/cgi/content/abstract/188/2/297 Prog Surg. 1974;13:1-65. Related Articles, Links Diagnosis of breast carcinoma. An evaluation of clinical examination, mammography, thermography and aspiration biopsy in breast disease. Bjurstam N, Hedberg K, Hultborn KA, Johansson NT, Johnsén C. http://www.ncbi.nlm.nih.gov/sites/entrez?cmd=Retrieve&db=PubMed&list_uids=4614325&dopt=Citati on Microwave thermography: principles, methods and clinical applications. Myers PC, Sadowsky NL, Barrett AH. We review the physical principles, method of operation, measurement limitations, and potential medical applications of microwave thermography. We present detailed results of a study of breast cancer detection at 1.3 and 3.3 GHz, including the dependence of detection rates on microwave frequency, time, tumor depth, and tumor size. At 1.3 GHz, microwave thermography detects breast cancer as well as infrared thermography (true-positive rate = 0.76 when true-negative rate = 0.63). When the two methods are combined, the true-positive rate increases by about 0.1 over that of either method alone http://www.ncbi.nlm.nih.gov/sites/entrez?cmd=Retrieve&db=PubMed&list_uids=259078&dopt=Citatio n Title Breast Cancer Detection: Mammography and other methods in breast imaging, second edition Creator/Author Bassett, L.W. ; Gold, R.H. Publication Date 1987 Jan 01 OSTI Identifier OSTI ID: 5722507