Comparative Study on the Use of Analytical Software to Identify the Different Stages of Breast Cancer Using Discrete Temperature Data
- 199 Downloads
Breast cancer is the second leading cause of death in women. It occurs when cells in the breast begin to grow out of control and invade nearby tissues or spread throughout the body. The limitations of mammography as a screening modality, especially in young women with denser breasts, necessitated the development of novel and more effective screening strategies with acceptable sensitivity and specificity. The aim of this study was to develop a feasible interpretive software system which was able to detect and classify breast cancer patients by employing techniques of different analytical software. The protocol described uses 6,000 pieces of thermal data collected from 16-sensors, eight placed on the surface of each breast. Data was collected every 5 min for the duration of the test period. Placement of sensors was accomplished with the use of a template design from information provided by the national tumor registry to insure that the information was collected in areas of the breast where most breast cancers develop. Data in this study was collected from 90 individuals exhibiting four different breast conditions, namely: normal, benign, cancer and suspected-cancer. The temperature data collected from these 16 sensors placed on the surface of each breast were fed as inputs to the classifiers. Comparisons were made on five different kinds of classifiers: back-propagation algorithm, probabilistic neural network, fuzzy (Sugeno-type), Gaussian mixture model and support vector machine. These classifiers were able to attain approximately 80% accuracy in classifying the four different diagnoses (normal, benign, cancer and suspected-cancer). Gaussian mixture model was the most sensitive classifier, achieving the highest sensitivity of 94.8%. Support vector machine was considered the best classifier as it was able to produce the most specific and accurate results. Based on these evaluations, this current effort shows the feasibility of applying analytical software techniques together with the real-time functional thermal analysis to develop a potential tool for the detection and classification of breast cancer.
KeywordsBreast cancer Neural networks Sensor Temperature Fuzzy Classifier Gaussian mixture model Support vector machine
- 1.National Breast Cancer Foundation, INC. [accessed 2008 18th Feb]; available from: http://www.nationalbreastcancer.org/signs_and_symptoms/index.html.
- 2.American Cancer Society, Cancer facts and figures 2007 [accessed 2008 18th Feb]; available from: http://www.cancer.org/downloads/STT/CAFF2007PWSecured.pdf.
- 3.Sobti, A., Sobti, P. S., and Keith, L. G., Screening and diagnostic mammography: why the gold standard does not shine more brightly? Int. J. Fert. Women’s Med. 50:199–206, 2005.Google Scholar
- 4.Breast Cancer in Young Women. [accessed 2008 18th Feb]; available from: http://www.clevelandclinic.org/health/healthinfo/docs/3000/3020.asp?index=10740.
- 10.Local cancer specialists agree with breast MRIs for high-risk patients. 6th April 2007 [accessed 2008 9th Feb]; available from: http://www.herald-review.com/articles/2007/04/06/news/local_news/1022515.txt.
- 11.Keith, L. G., Oleszczuk, J. J., and Laguens, M., Circadian rhythm chaos: A new breast cancer marker. Int. J. Fert. Women’s Med. 46:238–247, 2001.Google Scholar
- 13.Gros, C., and Bourjat, M. G. P., Prognosis and post therapeutic follow-up of breast cancers by thermography. In: Aarts, N. J. M., Gautherine, M., and Ring, E. F. J. (Eds.), Thermography (pp. 77–90). Basel: Karger, 1975.Google Scholar
- 14.Gautherine, M. C. G., Contribution of infrared thermography to early diagnosis, pretherapeutic prognosis and post-irradiation follow-up of breast carcinomas. Med. Mundi. 21:135–149, 1976.Google Scholar
- 17.Ng, E. Y.-K., Tan, M. S., Lockwood, S., and Keith, L. G., ANN based classification of breast cancer with discrete temperature screening: Facts and myths, part-IV. In: Suri, J. S., Rangayyan, R., and Laxminarayan, S. (Eds.), Emerging Technologies In Breast Imaging And Mammography (pp. 1–20). USA/Canada: American Scientific Publishers.Google Scholar
- 19.Lifeline Biotechnologies, Inc, Florida, USA. [Last accessed Feb 2008]; available from: http://www.lbti.com/firstwarningsystgem.asp#top
- 21.Nozaki, I. T., Selecting fuzzy if-then rules with forgetting in fuzzy classification systems. J. Japan Soc. Fuzzy Theory Syst. 6(3):585–602, 1994.Google Scholar
- 33.Weston, J., and Watkins, C., Multi-class support vector machines. Technical report CSD-TR-98-04, Department of Computer Science, Royal Holloway, University of London, Egham, TW20 0EX, UK, 1998.Google Scholar
- 34.. Lei H., Govindaraju V., Half-against-half multi-class support vector machines. Proceeding Sixth International Workshop on Multiple Classifier Systems (MCS’05), Berlin, Germany: Springer-Verlag, pp 156–164, 2001.Google Scholar
- 35.Platt, J. C., Chrisianini, N., and Shawe-Taylor, J., Large margin DAGs for multiclass classification. Adv. Neural. Inf. Process. Syst. 12:547–553, 2000, MIT.Google Scholar
- 36.Schoonjans, F. MedCalc Online Help, Help-topics: Statistics, ROC. MedClac software and receiver operating characteristics (ROC) [accessed 17th Feb 2008]; available from: http://www.medcalc.be/
- 37.DeLeo, J. M., Receiver Operating Characteristic Laboratory (ROCLAB): Software for developing decision strategies that account for uncertainty management in artificial neural network decision-making. Proceedings of Second International Symposium on Uncertainty Modeling and Analysis, 25–28 Apr 1993 pp. 141–144, 1993.Google Scholar
- 38.Downey, T. J. Jr, Meyer, D. J., Price, R. K., and Spitznagel, E. L., Using the receiver operating characteristic to assess the performance of neural classifiers. Neural Netw. 5:3642–3646, 1999.Google Scholar
- 39.Homer, M. J., Mammographic interpretation: a practical approach (pp. 4–5). McGraw-Hill, New York, 1997.Google Scholar
- 42.MacMahon, B., Cole, P., Lin, T. et al., Age at first birth and breast cancer risk. Bull World Health Organ. 43:209–221, 1970.Google Scholar