Research Article
[Retracted] Developing an Efficient Cancer Detection and Prediction Tool Using Convolution Neural Network Integrated with Neural Pattern Recognition
Table 1
Cancer prediction tools and methodology.
| Tools/methodology | Year | Accuracy | Dataset requirements | Description |
| Granular computing [8, 14] | 2008 | 100% (stated) | Large | This algorithm eliminates noise and unwanted genes to predict better | Neural network with MRI image [12, 21] | 2010 | NA | Large | Neurofuzzy classifiers were used on the brain tumour test data | Support vector machine with fuzzy [22, 28, 31] | 2011 | 92% | Medium | It uses liver cancer datasets for testing. Various micro-ranking–level techniques were implemented to classify | Support vector machine with PSO [23, 34–36] | 2012 | 96% | Medium | Uses breast cancer datasets, but for other datasets, the result and accuracy can deviate | ANN with PSO [24, 37–39] | 2012 | 92.36% | Medium | It was used on the tumour cells. Also implemented on the breast cancer datasets | Particle swarm optimization (PSO) integrated with seeker optimization algorithm (SOA) [25] | 2013 | ~93% | Medium | Liver tumours were analysed and classified | Deep learning [26] | 2020 | NA | Medium | Using multiomics data for cancer classification |
|
|