A Quantum Mixed-State Self-Harnessing Physics-Guided Neural Networks with Dandelion Optimizer Model for Breast Cancer Detection Using Histopathological Image
Abstract
Breast cancer is one of the common and life-threatening disorders in the world, as it requires proper and timely diagnosis to enhance the survival of the patient. Conventional diagnostic tools tend to be unable to evaluate high-dimensional histopathological image data, and the data is misclassified, which can lead to delayed treatment. To overcome this, the Quantum Mixed-State Self-Harnessing Physics-Guided Neural Networks with Dandelion Optimizer (QM-SS-HP-GNN-DO) is suggested to provide effective breast cancer diagnosis. To begin with, the images obtained and used in histopathology are gathered and preprocessed by Trainable Self-Guided Filtering (T-SGF) to improve the features of interest included in the BreakHis dataset. QM-SS-HP-GNN model subsequently provides classification, and Dandelion Optimizer (DO) optimizes the network weights to enhance the accuracy of the network. Experimental performance is better with an accuracy of 99.43%, precision of 99.10%, sensitivity of 99.05%, specificity of 99.20%, and F1-score of 99.08%, showing the best results compared to existing models. Overall, the suggested model offers a well-constructed, stable, and extremely precise framework of breast cancer diagnosis, and can be adapted to other medical image-based disease detection problems.
Read the paper
Related studies
- Quantum dots: synthesis, bioapplications, and toxicity
- A Guide to In Silico Drug Design
- Quantum Computing for Healthcare: A Review
- Automated in Silico Design of Homogeneous Catalysts
- Identification of Novel 3-Hydroxy-pyran-4-One Derivatives as Potent HIV-1 Integrase Inhibitors Using in silico Structure-Based Combinatorial Library Design Approach
- In silico structural elucidation of RNA-dependent RNA polymerase towards the identification of potential Crimean-Congo Hemorrhagic Fever Virus inhibitors
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.