Breast Cancer Detection Through LSTM-Based Deep Learning on Clinical Data
Alia Tabassum, Jianping Li, Abdus Saboor, Amin Ul Haq, Abdul Haq · 2024
At the early stage, the accurate and timely identification of breast cancer (BC) for proper treatment and recovery is significant. The previous deep learning-based methods of BC diagnosis do not precisely detect BC at an early stage. To tackle the accurate detection problem of existing methods of BC we proposed an intelligent model-based deep learning LSTM for accurate detection of BC. In designing the proposed model the LSTM deep learning model is incorporated and the model has been tested using the Breast Cancer Dataset (BCD). Additionally, the Holdout cross-validation (CV) technique was used for the training and testing of the model. The data set portion 80% was used for training and 20% for testing respectively. Various evaluation metrics were used to evaluate the performance of the proposed model (LSTM). The experimental results of the proposed model demonstrated that the performance of the model is higher as compared to baseline models in terms of accuracy and achieved 99.12% accuracy. Due to the high predictive accuracy of the proposed model we recommend it for the detection of BC in e-health systems.