BLB (Brain/Lung cancer detection and segmentation and Breast Dense calculation)

Cancer Diagnosis and prediction have been one of the most important challenges faced by mankind in the last few decades. Accurate detection of cancer would facilitate saving millions of lives. Therefore, our research presents — Brain/Lung/Breast (BLB) automated detection system. We precisely predict the occurrence of cancer and segment the expected region of tumor/cancer in MRI/CTscan/Mammography. This system proposes different classification techniques including Support Vector Machine (SVM), Normal MRI, ExtraTrees and Convolutional Neural Network (CNN). SVM achieved 98% accuracy in classifying brain tumor and Normal in MRI images. ExtraTrees achieved 95.38% accuracy in classification of Breast Dense in mammography images. Convolutional Neural Network (CNN) deep learning accomplished acceptable results in lung cancer detection. The presented system consists of (Preprocessing/Postprocessing, Segmentation, Feature extraction, and Classification). This approach was applied on different datasets including (MIAS) for breast, (LUNA) for lung and (BRATS2015 and Brats2017) datasets for Brain.