Predicting invasive ductal carcinoma tissues in whole slide images of breast Cancer by using convolutional neural network model and multiple classifiers

• Published in: Multimedia tools and applications 2022-03, Vol.81 (6), p.8575-8596
• Main Authors: Deepa, B. G., Senthil, S.
• Format: Article
• Language: English
• Subjects: Artificial neural networks; Breast cancer; Classifiers; Computer Communication Networks; Computer Science; Data Structures and Information Theory; Datasets; Decision trees; Deep learning; Libraries; Multimedia Information Systems; Neural networks; Prediction models; Recall; Special Purpose and Application-Based Systems; Support vector machines; Tensors
• ISSN: 1380-7501; 1573-7721
• DOI: 10.1007/s11042-022-12114-9

Breast Cancer (BC) is the common type of cancer found in women which is caused due to the abnormal growth of cells in the breast. Over 80% of the BC type detected till date is the invasive ductal carcinoma (IDC). In this work, a deep learning-based IDC prediction model is proposed based on the convolutional neural network (CNN). The developed deep learning method used a sequential Keras model like conv2D, Maxpooling2D, Dropout, Flatten and Dense. The proposed model is compared with multiple classifiers like logistic regression (LR), random forest (RF), k-nearest neighbor (K-NN), support vector machine (SVM), linear SVM, gaussian naïve bayesian (GNB) and decision tree (DT). The CNN model is generated by using SkLearn, Keras and Tensor flow libraries, and results are organized by MatPlot libraries. After evaluations, the proposed CNN based IDC framework provided 80%–86% of accuracy, 92%–94% of precision, 91%–96% of recall and 94%–96% of F1-score in prediction over the IDC dataset and 91%-94% of accuracy, 91%–95% of precision, 93%–96% of recall and 95%–98% of F1-score over the BreakHis dataset.