loading page

A Machine Learning validation to identify the difference between Cysts and Malignant tumours in Breast Cancer
  • +2
  • Saurav Mallik,
  • Akshara Makrariya Makrariya,
  • Rabia Musheer Aziz,
  • Mohd Inshal Naved,
  • Guimin Qin
Saurav Mallik
Harvard University Department of Environmental Health

Corresponding Author:[email protected]

Author Profile
Akshara Makrariya Makrariya
VIT Bhopal University
Author Profile
Rabia Musheer Aziz
VIT Bhopal University
Author Profile
Mohd Inshal Naved
VIT University School of Mechanical Engineering
Author Profile
Guimin Qin
The University of Texas Health Science Center at Houston School of Biomedical Informatics
Author Profile


One of the most common women’s tumours infest the breast. Various benign disorders like cysts in a woman’s breast occur due to hormonal changes and are at the risk of becoming malignant. Several thermal models are reported to differentiate between normal and malignant tissues of the breast. But no thermal model is reported in the study of the effect of benign disorders on the literature to distinguish between benign and malignant disorders in women’s breasts. An attempt has been made in this paper to study the thermal disturbances caused by cysts and malignant tumours in the fat tissues of a woman’s breast. The model is developed for a two-dimensional steady-state case using penne’s bioheat equation and incorporating parameters like thermal conductivity, blood mass flow rate, and self-controlled metabolic heat generation. The appropriate adiabatic boundary conditions have been framed for various environmental conditions. The finite element method has been employed to obtain the solution. The results have been obtained for different spherical-shaped cysts and different depths of tissues in a hemispherical-shaped woman’s breast. Furthermore, the comparison of thermal profiles for cysts and malignant tumours in a woman’s breast has been performed. As a result, a contrast in the thermal behaviour of cyst and malignant tumour in a woman’s breast is observed, which can be helpful to distinguish between the malignant tumour and cyst in a woman’s breast to prevent false-positive test for malignant tumour. Accordingly, this study found that various factors could affect cancer classification and prediction. Therefore, in this study, Breast cancer data classification has been done using three classification techniques which are Artificial Neural Network (ANN), Support Vector Machine (SVM), and Random Forest (R.F.); to improve the performance of the model, trained the model with selected features according to the analysis done.