Table 1.
Metastatic and cancer prediction techniques.
| Authors | Objective | Prediction model | Dataset | Prediction accuracy |
|---|---|---|---|---|
| Ahmad et al.33 | To obtain the highest accuracy | CNN-LSTM, CNN-GRU and AlexNet GRU are used. Out of these three AlexNet GRU outperforms | Kaggle PCam imaging dataset | 99.5% |
| Choudhury34 | To diagnose and predict the cancer prognosis of Malignant Pleural Mesothelioma as early as possible (MPM) | 8 different algorithms are used | Clinical data collected by Dicle University | 79.29% |
| Bejnordi et al.35 | To investigate the predictive power of deep learning algorithms Vs 11 members of pathologists in a simulated time-constraint environment | In a research challenge competition. 32 deep learning models have been submitted by the contestants out of which 7 models showed a greater performance | Detecting lymph node metastases: A CAMELYON16 dataset | Area Under the Curve (AUC) of 0.994 |
| Abdollahiet al.36 | To detect metastatic breast cancer using the whole-slide pathology images | Ensemble model consisting of VGG16, Resnet50, Google net, and Mobile net | CAMELYON16 dataset | 98.84% |
| Papandrianos et al.37 | To identify bone metastasis of prostate cancer | Convolutional Neural Network (CNN) | Nuclear Medicine Department of Diagnostic Medical Center, Larisa, Greece | 97.38% |
| Gupta, and Gupta38 | Deep learning approaches for predicting breast cancer survivability | Restricted Boltzmann Machine | The Surveillance, Epidemiology, and End Results (SEER) database | 97% |
| Sharma and Mishra39 | Performance analysis of machine learning based optimized feature selection approaches for breast cancer diagnosis | voting classifier | Wisconsin Breast Cancer (WDBC) | 99.41% |
| Ak40 | A comparative analysis of breast cancer detection and diagnosis using data visualization and machine learning applications | logistic regression model | Dr. William H. Walberg of the University of Wisconsin Hospital | 98.1% |
| Maqsood et al.41 | A breast cancer detection and classification towards computer-aided diagnosis using digital mammography in early stages | Transferable texture convolutional neural network (TTCNN) | DDSM, INbreast, and MIAS datasets | 97.49% |
| Nanglia et al.42 | An enhanced predictive heterogeneous ensemble model for breast cancer prediction | Heterogeneous Stacking Ensemble Model | Coimbra breast cancer dataset | 78% |
| Feroz et al.43 | Machine learning techniques for improved breast cancer detection and prognosis—a comparative analysis | K-Nearest Neighbor and Random Forest | Wisconsin | 97.14% |
| Nasser44 | Application of Machine Learning Models to the Detection of Breast Cancer | Random forest | Breast Cancer Database of Coimbra | 83.3% |
| Seo et al.45 | Scaling multi-instance support vector machine to breast cancer detection on the BreaKHis dataset | SVM | BreaKHis dataset | |
| Alfian et al.46 | Predicting Breast Cancer from Risk Factors Using SVM and Extra-Trees-Based Feature Selection Method | SVM | Gynaecology Department of the University Hospital Centre of Coimbra (CHUC) | 80.23% |
| Afolayan et al.47 | Breast cancer detection using particle swarm optimization and decision tree machine learning technique | Particle swarm optimization and decision tree | Wisconsin breast cancer dataset | 92.26% |
| Lakshmi, et al.48 | Breast cancer detection using UCI machine learning repository dataset Wisconsin Diagnostic Breast Cancer (WDBC) is the cell nuclei features extracted from medical imaging | The paper discusses 11 different machine-learning algorithms for classification. The classification pipeline used is as follows: (1) Min–Max normalization, (2) dimensionality reduction PCA and t-SNE, and (3) the Randon Forest classification method | Wisconsin Diagnostic Breast Cancer (WDBC) | 99% accuracy |