Enhanced detection of ovarian cancer using AI-optimized 3D CNNs for PET/CT scan analysis.

Journal: Physical and engineering sciences in medicine
Published Date: Aug 4, 2025

Abstract

This study investigates how deep learning (DL) can enhance ovarian cancer diagnosis and staging using large imaging datasets. Specifically, we compare six conventional convolutional neural network (CNN) architectures-ResNet, DenseNet, GoogLeNet, U-Net, VGG, and AlexNet-with OCDA-Net, an enhanced model designed for [F]FDG PET image analysis. The OCDA-Net, an advancement on the ResNet architecture, was thoroughly compared using randomly split datasets of training (80%), validation (10%), and test (10%) images. Trained over 100 epochs, OCDA-Net achieved superior diagnostic classification with an accuracy of 92%, and staging results of 94%, supported by robust precision, recall, and F-measure metrics. Grad-CAM ++ heat-maps confirmed that the network attends to hyper-metabolic lesions, supporting clinical interpretability. Our findings show that OCDA-Net outperforms existing CNN models and has strong potential to transform ovarian cancer diagnosis and staging. The study suggests that implementing these DL models in clinical practice could ultimately improve patient prognoses. Future research should expand datasets, enhance model interpretability, and validate these models in clinical settings.

Authors

  • Mohammad Hossein Sadeghi
    Nuclear Engineering Department, School of Mechanical Engineering, Shiraz University, Shiraz, Iran.
  • Sedigheh Sina
    Department of Ray-Medical Engineering, Shiraz University, Shiraz, Iran.
  • Reza Faghihi
    Nuclear Engineering Department, School of Mechanical Engineering, Shiraz University, Shiraz, Iran.
  • Mehrosadat Alavi
    Department of Nuclear Medicine, Shiraz University of Medical Sciences, Shiraz, Iran.
  • Francesco Giammarile
    Nuclear Medicine and Diagnostic Imaging Section, Division of Human Health, Department of Nuclear Sciences and Applications, International Atomic Energy Agency, Vienna, Austria. Electronic address: francesco.giammarile@gmail.com.
  • Hamid Omidi
    Nuclear Engineering Department, School of Mechanical Engineering, Shiraz University, Shiraz, Iran.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals