Spiking Neural Network (SNN) Using to Detect Breast Cancer

Abstract

The spiking neural networks (SNNs) use event-driven signals to encipher physical data for neural computation. SNN takes the spiking somatic cell because the basic unit. It modulates the method of nerve cells from receiving stimuli to firing spikes. Therefore, SNN is a lot of biologically plausible. Though the SNN has a lot of characteristics of biological neurons, SNN isn't used for medical image recognition because of its poor performance. During this paper, a reservoir spiking neural network is employed for carcinoma image recognition. Because of the difficulties of extracting the lesion options in medical pictures, a salient feature extraction technique is employed in image recognition. The salient feature extraction network consists of spiking convolution layers, which might effectively extract the options of lesions. 2 temporal secret writing manners, namely, linear time secret writing and entropy-based time secret writing strategies, are accustomed encipher the input patterns. Readout neurons use the ReSuMe algorithmic program for coaching, and therefore the dipterans improvement algorithmic program (FOA) is utilized to optimize the specification to additional improve the reservoir SNN performance. 3 modality datasets are accustomed verify the effectiveness of the projected technique. The results show Associate in nursing accuracy of ninety seven.44% for the BreastMNIST information. The classification accuracy is ninety eight.27% on the mini-MIAS information. And therefore the overall accuracy is ninety five.83% for the Break His information by victimization the strikingness feature extraction, entropy-based time secret writing, and network improvement.