ﺗﺸﺨﯿﺺ ﺳﺮﻃﺎن ﭘﺴﺘﺎن ﺑﺎ اﺳﺘﻔﺎده از ﺗﺮﮐﯿﺐ روشﻫﺎي ﯾﺎدﮔﯿﺮي ﻣﺎﺷﯿﻦ و ﺑﯿﻨﺎﯾﯽ ﻣﺎﺷﯿﻦ در ﺗﺼﺎوﯾﺮ ﺗﺮﻣﻮﮔﺮاﻓﯽ

Diagnosis of Breast Cancer by Integrating Machine Learning and Machine Vision Techniques in Thermography Images

ﺳﺮﻃﺎﻥ ﭘﺴﺘﺎﻥ ﺩﺭ ﺳﺎﻝﻫﺎﻱ ﺍﺧﻴﺮ ﺩﺭ ﺑﻴﻦ ﺯﻧﺎﻥ ﺍﻓﺰﺍﻳﺶ ﻳﺎﻓﺘﻪ ﺍﺳﺖ ﻭ ﻳﻜﻲ ﺍﺯ ﺷﺎﻳﻊﺗﺮﻳﻦ ﻋﻠﻞ ﻣﺮﮒ ﻭ ﻣﻴﺮ ﺩﺭ ﺯﻧﺎﻥ ﻣﻲﺑﺎ ﺷﺪ. ﻣﻄﺎﻟﻌﺎﺕ ﻧﺸﺎﻥ ﻣﻲﺩﻫﺪ ﮐﻪ ﺗﺮﻣﻮﮔﺮﺍﻓﻲ، ﻧﺴﺒﺖ ﺑﻪ ﺳﺎﻳﺮ ﺭﻭﺵﻫﺎﻱ ﺗﺸﺨﻴﺼﻲ، ﺭﻭﺷﻲ ﺳﺮﻳﻊﺗﺮ، ﺍﺭﺯﺍﻥﺗﺮ، ﻏﻴﺮﻓﻌﺎﻝ، ﺑﺪﻭﻥ ﺭﻳﺴﮏ، ﺑﺪﻭﻥ ﺍﺷﻌﻪ ﻭ ﺩﺭﺩ ﺍﺳﺖ. ﺭﻭﺵﻫﺎﻱ ﺟﺪﻳﺪ ﺩﺭ ﭘﺮﺩﺍﺯﺵ ﺗﺼﻮﻳﺮ، ﺑﻴﻨﺎﻳﻲ ﻭ ﻳﺎﺩﮔﻴﺮﻱ ﻣﺎ ﺷﻴﻦ ﺳﺒﺐ ﺷﺪﻩ ﺗﺎ ﻣﻄﺎﻟﻌﺎﺕ ﻣﻮﻓﻘﻴﺖﺁﻣﻴﺰﻱ ﺑﻪ ﻣﻨﻈﻮﺭ ﺍﻳﺠﺎﺩ ﺳﻴ ﺴﺘﻢﻫﺎﻱ ﺗﺸﺨﻴ ﺼﻲ ﺳﺮﻃﺎﻥ ﭘﺴﺘﺎﻥ ﺑﺎ ﺑﮑﺎﺭﮔﻴﺮﻱ ﺗﺼﺎﻭﻳﺮ ﺗﺮﻣﻮﮔﺮﺍﻓﻲ ﺍﻳﺠﺎﺩ ﺷﻮﺩ. ﺩﺭ ﺍﻳﻦ ﻣﻄﺎﻟﻌﻪ ﻳﮏ ﺭﻭﺵ ﻣﻨﺎﺳﺐ ﺑﺮﺍﻱ ﺗﺸﺨﻴﺺ ﻧﺎﻫﻨﺠﺎﺭﻱ ﺗﺼﺎﻭﻳﺮ ﺗﺮﻣﻮﮔﺮﺍﻓﻲ ﺍﺯ ﻧﻤﺎﻱ ﺭﻭﺑﻪﺭﻭ ﺍﺭﺍﺋﻪ ﺷﺪﻩ ﺍﺳﺖ ﮐﻪ ﺑﺎ ﺑﮑﺎﺭﮔﻴﺮﻱ ﺍﻳﻦ ﺭﻭﺵ ﺗﻔﮑﻴﮏ ﻧﺎﺣﻴﻪ ﺳــﻴﻨﻪ ﻭ ﻫﻤﻪ ﻧﻮﺍﺣﻲ ﻣﺪﻧﻈﺮ ﭘﺰﺷــﮏ ﮐﻪ ﺑﺮﺍﻱ ﺗﺸــﺨﻴﺺ ﺳــﺮﻃﺎﻥ ﭘﺴــﺘﺎﻥ ﺿــﺮﻭﺭﻱ ﻣﻲﺑﺎﺷــﻨﺪ، ﺍﺯ ﺗﺮﻣﻮﮔﺮﺍﻡﻫﺎ ﺟﺪﺍﺳــﺎﺯﻱ ﺭﻧﮕﻲ ﻣﻲﺷــﻮﻧﺪ ﻭ ﻧﻮﺍﺣﻲ ﭘﺮﺣﺮﺍﺭﺕ ، ﺑﺎ ﺍﺳــﺘﻔﺎﺩﻩ ﺍﺯ ﺍﻟﮕﻮﺭﻳﺘﻢ FCM ﺍﺯ ﺗﺼــﺎﻭﻳﺮ ﺍﺳــﺘﺨﺮﺍﺝ ﺷــﺪﻩ ﻭ ﺑﻪ ﮐﻤﮏ ﺁﻧﺎﻟﻴﺰ ﻓﺮﺍﮐﺘﺎﻟﻲ، ﺑﻌﺪ ﻓﺮﺍﮐﺘﺎﻝ ﺍﻳﻦ ﻧﻮﺍﺣﻲ ﺑﺎ ﺍﺳﺘﻔﺎﺩﻩ ﺍﺯ ﺳﻪ ﺭﻭﺵ ﻣﺘﻔﺎﻭﺕ ﻣﺤﺎﺳﺒﻪ ﻣﻲﺷﻮﻧﺪ. ﺟﻨﺒﻪ ﻧﻮﺁﻭﺭﻱ ﺍﻳﻦ ﻣﻄﺎﻟﻌﻪ ﺑﺮﺭﺳﻲ ﻧﻘﺶ ﺁﻧﺎﻟﻴﺰ ﻓﺮﺍﮐﺘﺎﻟﻲ ﺩﺭ ﺭﺩﻳﺎﺑﻲ ﺗﻮﺯﻳﻊ ﺣﺮﺍﺭﺕ ﻣﺘﻘﺎﺭﻥ ﺩﺭ ﺩﻭ ﺑﺎﻓﺖ ﺳــﻴﻨﻪ ﺍﺳــﺖ. ﻧﺘﺎﻳﺞ ﻧﺸــﺎﻥ ﻣﻲﺩﻫﺪ ﮐﻪ ﺁﻧﺎﻟﻴﺰ ﻓﺮﺍﮐﺘﺎﻟﻲ ﺑﻪ ﻃﻮﺭ ﺑﺎﻟﻘﻮﻩ ﻣﻲﺗﻮﺍﻧﺪ ﻗﺎﺑﻠﻴﺖ ﺍﻃﻤﻴﻨﺎﻥ ﺗﺮﻣﻮﮔﺮﺍﻓﻲ ﺩﺭ ﺗﺸــﺨﻴﺺ ﺗﻮﻣﻮﺭ ﺭﺍ ﺑﻬﺒﻮﺩ ﺑﺨﺸــﺪ. ﻫﻤﭽﻨﻴﻦ ﺁﻧﺎﻟﻴﺰ ﻓﺮﺍﮐﺘﺎﻟﻲ ﻧﻘﺶ ﻣﻬﻤﻲ ﺩﺭ ﺭﺩﻳﺎﺑﻲ ﺗﻮﺯﻳﻊ ﺣﺮﺍﺭﺕ ﻣﺘﻘﺎﺭﻥ، ﺩﺭ ﺩﻭ ﺑﺎﻓﺖ ﭘﺴﺘﺎﻥ ﺟﻬﺖ ﺭﺩﻳﺎﺑﻲ ﻧﺎﻫﻨﺠﺎﺭﻱﻫﺎ ﺩﺍﺭﺩ.

Breast cancer has increased among women in recent years and is one of the leading causes of death in women. Studies show that thermography is a faster, cheaper, passive, risk-free, radiation-free and pain-free method than other diagnostic methods. New methods of image processing, vision and machine learning have led to successful investigations into the invention of breast cancer detection systems by thermometric images. In the present study, a proper method of diagnosing abnormality through thermography images of the obverse view is presented. By this segregation method, the breast area and every other area targeted by the physician that is vital for breast cancer diagnosis are color-divided in the thermographs. Warmer regions known as vital centers are extracted by the FCM algorithm and the fractal dimension of these regions is calculated using three different methods. The Studies suggesting that fractal analysis may potentially improve the reliability of thermography in breast tumor detection. The innovative aspect of this paper is the study of the role of fractal analysis in tracking the symmetrical heat distribution in two breast tissues in thermographic images. The results show that fractal analysis plays an important role in tracking the symmetrical heat distribution in two breast tissues to investigate asymmetry in order to detect breast abnormalities.