The objective of this study is to design a breast cancer detection model using hybrid deep learning. The design model encapsulates pre-processing, feature extraction, and classification. Convolutional neural networks (CNN) and recurrent neural networks (RNN) are the names of the two deep learning architectures. Furthermore, the tumour-segmented binary image is regarded as input to CNN, and both GLCM and GLRM are regarded as input to RNN. The study's conclusion demonstrates that, in general, the AND operation of two classifier outputs will produce diagnostic accuracy that is superior to that of conventional models. We compare the proposed model with contemporary neural network systems. The proposed model outperforms the contemporary neural network model with a substantial prediction accuracy of 99.11%. The major contribution of this work is the development and application of a deep forest model for breast cancer classification. The proposed model was simulated in MATLAB 2018R software. For the validation of algorithms, test two reputed datasets, such as DDMS and MIAS. The analysis of the results suggests that the proposed algorithm is very efficient in terms of existing algorithms for breast cancer detection.