Artificial intelligence assisted patient blood and urine droplet pattern analysis for non‑invasive and accurate diagnosis of bladder cancer

Ramiz Demir, Soner Koc, Deniz Gulfem Ozturk, Sukriye Bilir, Halil Ibrahim Ozata, Rhodri Williams, John R. E. Christy, Yanus Akkoc, Ilker Tinay, Cigdem Gunduz-Demir, Devrim Gozuacik*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract / Description of output

Bladder cancer is one of the most common cancer types in the urinary system. Yet, current bladder cancer diagnosis and follow-up techniques are time-consuming, expensive, and invasive. In the clinical practice, the gold standard for diagnosis remains invasive biopsy followed by histopathological analysis. In recent years, costly diagnostic tests involving the use of bladder cancer biomarkers have been developed, however these tests have high false-positive and false-negative rates limiting their reliability. Hence, there is an urgent need for the development of cost-effective, and non-invasive novel diagnosis methods. To address this gap, here we propose a quick, cheap, and reliable diagnostic method. Our approach relies on an artificial intelligence (AI) model to analyze droplet patterns of blood and urine samples obtained from patients and comparing them to cancer-free control subjects.
The AI-assisted model in this study uses a deep neural network, a ResNet network, pre-trained on ImageNet datasets. Recognition and classification of complex patterns formed by dried urine or blood droplets under different conditions resulted in cancer diagnosis with a high specificity and sensitivity.
Our approach can be systematically applied across droplets, enabling comparisons to reveal shared spatial behaviors and underlying morphological patterns. Our results support the fact that AI-based models have a great potential for non-invasive and accurate diagnosis of malignancies, including bladder cancer.
Original languageEnglish
Article number2488
Pages (from-to)2488
JournalScientific Reports
Issue number1
Early online date30 Jan 2024
Publication statusE-pub ahead of print - 30 Jan 2024

Keywords / Materials (for Non-textual outputs)

  • Artificial Intelligence
  • Biomarkers, Tumor/urine
  • Humans
  • Reproducibility of Results
  • Urinary Bladder Neoplasms/pathology
  • Urinary Bladder/pathology

Cite this