AI-Enhanced Comprehensive Liver Tumor Prediction using Convolutional Autoencoder and Genomic Signatures

Liver tumor prediction plays a pivotal role in optimizing treatment strategies and improving patient outcomes. In our proposed work, we present an innovative AI-driven framework for liver tumor prediction, uniting cutting-edge techniques to enhance precision and depth of analysis. The framework integrates a Histological Convolutional Autoencoder (HistoCovAE) for meticulous tumor segmentation in medical imaging, and Genomic Feature Extraction (MIRSLiC) for a nuanced understanding of molecular markers. Additionally, a Multidimensional Feature Extraction module amalgamates videomics, radiomics, acoustics, and clinical data, creating a comprehensive dataset. These dimensions synergize in a unified model, offering detailed predictions encompassing tumor characteristics, subtypes, and prognosis. Model evaluation and continuous improvement, guided by real-world outcomes, underscore reliability. This integrative approach transcends conventional boundaries, providing clinicians’ actionable insights for personalized treatment strategies and heralding a new era in liver tumor prediction. Our model undergoes rigorous evaluation against diverse datasets, and the performance metrics underscore its reliability and accuracy. With precision exceeding 87%, recall rates above 92%, and a Dice coefficient surpassing 0.89 in tumor segmentation, our model showcases exceptional accuracy and robustness. In prognostic modeling, survival prediction accuracy consistently surpasses 84%, highlighting the model's ability to provide valuable insights into the future trajectory of liver cancer.

@article{Prabaharan2024,
  title     = {AI-Enhanced Comprehensive Liver Tumor Prediction using Convolutional Autoencoder and Genomic Signatures},
  journal   = {International Journal of Advanced Computer Science and Applications},
  volume    = {15},
  number    = {2},
  year      = {2024},
  publisher = {The Science and Information Organization},
  author    = {G. Prabaharan and D. Dhinakaran and P. Raghavan and S. Gopalakrishnan and G. Elumalai},
  doi       = {10.14569/IJACSA.2024.0150227},
  url       = {https://doi.org/10.14569/IJACSA.2024.0150227}
}