Multi-Modal Evolutionary Deep Learning Model for Ovarian Cancer Diagnosis

Ovarian cancer (OC) is a common reason for mortality among women. Deep learning has recently proven better performance in predicting OC stages and subtypes. However, most of the state-of-the-art deep models employ single modality data, which may afford low-level due to insufficient representation important characteristics. Furthermore, these still lack optimization model construction, requires high computational cost train deploy them. In this work, hybrid evolutionary model, using multi-modal proposed. The established fusion framework amalgamates gene alongside with histopathological image modality. Based on different states forms each modality, we set up feature extraction network, respectively. This includes predictive antlion-optimized long-short-term-memory process longitudinal data. Another convolutional neural network included histopathology images. topology customized automatically by antlion algorithm make it realize performance. After that output from two improved networks fused based upon weighted linear aggregation. features are finally used predict stage. A number assessment indicators was compare proposed other nine constructed distinct algorithms. conducted benchmark benchmarks breast lung cancers. results reveal more precise accurate diagnosing