Breast Cancer Prediction using varying Parameters of Machine Learning Models

This prospective study enrolled 147 women with invasive breast cancer who underwent low-dose breast CT (80 kVp, 25 mAs, 1.01–1.38 mSv) before treatment. From each tumor, we extracted eight perfusion parameters using the maximum slope algorithm and 36 texture parameters using the filtered histogram technique. Relationships between CT parameters and histological factors were analyzed using five machine learning algorithms. Performance was compared using the area under the receiver-operating characteristic curve (AUC) with the DeLong test. The AUCs of the machine learning models increased when using both features instead of the perfusion or texture features alone. The random forest model that integrated texture and perfusion features was the best model for prediction (AUC = 0.76). In the integrated random forest model, the AUCs for predicting human epidermal growth factor receptor 2 positivity, estrogen receptor positivity, progesterone receptor positivity, ki67 positivity, high tumor grade, and molecular subtype were 0.86, 0.76, 0.69, 0.65, 0.75, and 0.79, respectively. Entropy of pre- and postcontrast images and perfusion, time to peak, and peak enhancement intensity of hot spots are the five most important CT parameters for prediction. In conclusion, machine learning using texture and perfusion characteristics of breast cancer with low-dose CT has potential value for predicting prognostic factors and risk stratification in breast cancer patients.

Download Full-text

Value of the Application of CE-MRI Radiomics and Machine Learning in Preoperative Prediction of Sentinel Lymph Node Metastasis in Breast Cancer

Frontiers in Oncology ◽

10.3389/fonc.2021.757111 ◽

2021 ◽

Vol 11 ◽

Author(s):

Yadi Zhu ◽

Ling Yang ◽

Hailin Shen

Keyword(s):

Breast Cancer ◽

Machine Learning ◽

Lymph Node ◽

Sentinel Lymph Node ◽

Breast Cancer Patients ◽

Learning Models ◽

Preoperative Prediction ◽

Machine Learning Model ◽

Validation Set ◽

Machine Learning Models

PurposeTo explore the value of machine learning model based on CE-MRI radiomic features in preoperative prediction of sentinel lymph node (SLN) metastasis of breast cancer.MethodsThe clinical, pathological and MRI data of 177 patients with pathologically confirmed breast cancer (81 with SLN positive and 96 with SLN negative) and underwent conventional DCE-MRI before surgery in the First Affiliated Hospital of Soochow University from January 2015 to May 2021 were analyzed retrospectively. The samples were randomly divided into the training set (n=123) and validation set (n= 54) according to the ratio of 7:3. The radiomic features were derived from DCE-MRI phase 2 images, and 1,316 original eigenvectors are normalized by maximum and minimum normalization. The optimal feature filter and selection operator (LASSO) algorithm were used to obtain the optimal features. Five machine learning models of Support Vector Machine, Random Forest, Logistic Regression, Gradient Boosting Decision Tree, and Decision Tree were constructed based on the selected features. Radiomics signature and independent risk factors were incorporated to build a combined model. The receiver operating characteristic curve and area under the curve were used to evaluate the performance of the above models, and the accuracy, sensitivity, and specificity were calculated.ResultsThere is no significant difference between all clinical and histopathological variables in breast cancer patients with and without SLN metastasis (P >0.05), except tumor size and BI-RADS classification (P< 0.01). Thirteen features were obtained as optimal features for machine learning model construction. In the validation set, the AUC (0.86) of SVM was the highest among the five machine learning models. Meanwhile, the combined model showed better performance in sentinel lymph node metastasis (SLNM) prediction and achieved a higher AUC (0.88) in the validation set.ConclusionsWe revealed the clinical value of machine learning models established based on CE-MRI radiomic features, providing a highly accurate, non-invasive, and convenient method for preoperative prediction of SLNM in breast cancer patients.

Download Full-text

Importance of Feature Selection and Data Visualization Towards Prediction of Breast Cancer

Recent Patents on Computer Science ◽

10.2174/2213275912666190101121058 ◽

2019 ◽

Vol 12 (4) ◽

pp. 317-328 ◽

Cited By ~ 2

Author(s):

Rajalakshmi Krishnamurthi ◽

Niyati Aggrawal ◽

Lokendra Sharma ◽

Diva Srivastava ◽

Shivangi Sharma

Keyword(s):

Breast Cancer ◽

Machine Learning ◽

Feature Selection ◽

Support Vector ◽

Data Visualisation ◽

Learning Models ◽

Cancer Data ◽

Comparison Results ◽

Tree Classifier ◽

Machine Learning Models

Background: Breast cancer is one of the most common forms of cancers among women and the leading cause of death among them. Countries like United States, England and Canada have reported a high number of breast cancer patients every year and this number is continuously increasing due to detection at later stages. Hence, it is very important to create awareness among women and develop such algorithms which help to detect malignant cancer. Several research studies have been conducted to analyze the breast cancer data. Objective: This paper presents an effective method in predicting breast cancer and its stage and will also analyze the performance of different supervised learning algorithms such as Random Classifier, Chi2 Square test used in order to predict. The paper focuses on the three important aspects such as the feature selection, the corresponding data visualisation and finally making a prediction call on different machine learning models. Methods: The dataset used for this work is breast cancer Wisconsin data taken from UCI library. The dataset has been used to show the different 32 features which are all important and how it can be achieved using data visualisation. Secondly, after the feature selection, different machine learning models have been applied. Conclusion: The machine learning models involved are namely Support Vector Machine (SVM), KNearest Neighbour (KNN), Random Forest, Principal Component Analysis (PCA), Neural Network using Perceptron (NNP). This has been done to check which type of model is better under what conditions. At different stages several charts have been plotted and eliminated based on relative comparison. Results have shown that Random Tree classifier along with Chi2 Square proves to be an efficient one.

Download Full-text