Feature extraction from MRI ADC images for brain tumor classification using machine learning techniques

Abstract

Background: Diffusion-weighted (DW) imaging is a well-recognized magnetic resonance imaging (MRI) technique that is being routinely used in brain examinations in modern clinical radiology practices. This study focuses on extracting demographic and texture features from MRI Apparent Diffusion Coefficient (ADC) images of human brain tumors, identifying the distribution patterns of each feature and applying Machine Learning (ML) techniques to differentiate malignant from benign brain tumors.

Methods: This prospective study was carried out using 1599 labeled MRI brain ADC image slices, 995 malignant, 604 benign from 195 patients who were radiologically diagnosed and histopathologically confirmed as brain tumor patients. The demographics, mean pixel values, skewness, kurtosis, features of Grey Level Co-occurrence Matrix (GLCM), mean, variance, energy, entropy, contrast, homogeneity, correlation, prominence and shade, were extracted from MRI ADC images of each patient. At the feature selection phase, the validity of the extracted features were measured using ANOVA f-test. Then, these features were used as input to several Machine Learning classification algorithms and the respective models were assessed.

Results: According to the results of ANOVA f-test feature selection process, two attributes: skewness (3.34) and GLCM homogeneity (3.45) scored the lowest ANOVA f-test scores. Therefore, both features were excluded in continuation of the experiment. From the different tested ML algorithms, the Random Forest classifier was chosen to build the final ML model, since it presented the highest accuracy. The final model was able to predict malignant and benign neoplasms with an 90.41% accuracy after the hyper parameter tuning process.

Conclusions: This study concludes that the above mentioned features (except skewness and GLCM homogeneity) are informative to identify and differentiate malignant from benign brain tumors. Moreover, they enable the development of a high-performance ML model that has the ability to assist in the decision-making steps of brain tumor diagnosis process, prior to attempting invasive diagnostic procedures, such as brain biopsies.

Keywords: ANOVA f-test feature selection; Apparent diffusion coefficient; Brain tumor classification; Diffusion weighted imaging; Machine learning; Magnetic resonance imaging; Random forest.

Fig. 1

Supervised learning method applying to tumor classification. The flow chart illustrates the steps of building a classification model to differentiate brain neoplasms using supervised learning technique. Here, the problem was identified as a classification problem at the initial stage and then the necessary data was collected as the second step. Data pre-processing was executed as the third step and at the fourth step, the data set was split into training and testing sets. Then a suitable ML algorithm for the collected data was selected as the fifth step of the study flow and then, the selected algorithm was trained with the training data as the sixth step. Finally, the developed algorithm was evaluated with the test data and the hyperparameter of the developed model was tuned to reach the optimum accuracy level of the model

Fig. 2

Final confusion matrix. The confusion matrix express the performance of the optimized benign malignant brain tumor brain tumor classification model over the test set

Fig. 3

MRI ADC brain image of a 14-year-old female patient diagnosed with pilocytic astrocytoma which was radiologically and histo-pathologically identified as a benign tumor. The tumor area is surrounded by the ROI. The texture features were extracted form the selected area

Fig. 4

ANOVA f-test results chart. ANOVA f-test score for attributes 0 to 15 are illustrated in the graph; mean pixel value of ADC 32.3343, Skewness 3.3444 Kurtosis 9.6250, GLCM Mean1 32.6372, GLCM mean2 29.1327, GLCM variance1 14.0761, GLCM variance2 27.5219 GLCM energy, GLCM Homogeneity 3.4572, 33.9675, GLCM Entropy 4.989, GLCM contrast 47.9462, GLCM Correlation 48.6392, GLCM prominence 15.4134, GLCM Shade 17.1677, Patient Age 9.4337 and Patient Gender 73.7926

Fig. 5

Precision–recall curve; visualize the sensitivity–specificity trade-off in the classifier the information provided by the curve used to set the decision threshold of the model to maximize the sensitivity and specificity

Fig. 6

Receiver operating characteristic curve (ROC Curve). The curve illustrates the behaviour of the false positive rate (x-axis) and true positive rate (y-axis) for a series of different decision threshold values in between 1.00 and 0.00. The smaller values of the X-axis represent the lower false positive rate, and the higher true negative rate. In addition, the larger values of Y-axis represent the lower false negative rates and higher true positive rates