Loading...

Prediction Normal and Colon Cancer Samples by Gene Expression Through Neural Network

Esmaeili, Sina | 2024

0 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 57631 (02)
  4. University: Sharif University of Technology
  5. Department: Mathematical Sciences
  6. Advisor(s): Foroughmand Araabi, Mohammad Hadi
  7. Abstract:
  8. Colon cancer is one of the most common and dangerous cancers, with a high mortality rate. Early diagnosis and accurate prediction of this disease are crucial for effective treatment of patients. This study aims to predict and diagnose colon cancer at an early stage using gene expression data. The main challenges in this field include the high dimensionality of gene expression data, the limited number of samples, and imbalanced data. Previous research has utilized feature selection methods to identify genes associated with colon cancer and applied machine learning algorithms to predict this cancer. In this thesis, we examine a feature selection method that utilizes Kullback-Leibler divergence to identify genes with higher divergence values as input features for the model. Subsequently, we introduce a neural network model with two hidden layers, where the loss function of the model is a focal loss function. Our results demonstrate that the proposed neural network model achieves an accuracy of 97.52%, a precision of 98.2%, a recall of 99.19%, an F-score of 98.68%, and an area under the receiver operating characteristic curve (AUC) of 99.59%, indicating its effective performance. Comparing our results with the previous studies, our proposed model has shown superior accuracy in certain metrics such as recall, F-score, and AUC, and has also outperformed four commonly used machine learning algorithms. These findings suggest that our proposed approach has successfully improved the accuracy and efficiency of existing methods and can be used as an effective tool for the early detection of colon cancer
  9. Keywords:
  10. Colon Cancer ; Gene Expression Data ; Gene Selection ; Kullback-Leibler Divergence ; Neural Network ; Focal Loss ; Cancer Diagnosis

 Digital Object List

 Bookmark

...see more