Back to all papers

Exploring the role of preprocessing combinations in hyperspectral imaging for deep learning colorectal cancer detection.

Authors

Tkachenko M,Huber B,Hamotskyi S,Jansen-Winkeln B,Gockel I,Neumuth T,Köhler H,Maktabi M

Affiliations (6)

  • Center for scalable data analytics and artificial intelligence (ScaDS.AI) Dresden/Leipzig, Leipzig, Germany. [email protected].
  • Innovation Center Computer-Assisted Surgery (ICCAS), University of Leipzig, Leipzig, 04103, Germany. [email protected].
  • Anhalt University of Applied Sciences, Köthen, 06366, Germany.
  • Department of Visceral, Transplant, Thoracic and Vascular Surgery, University Hospital of Leipzig, Leipzig, 04103, Germany.
  • Department of Gastrointestinal Surgery, IRCCS San Raffaele Scientific Institute and San Raffaele Vita-Salute University, Milan, 20132, Italy.
  • Innovation Center Computer-Assisted Surgery (ICCAS), University of Leipzig, Leipzig, 04103, Germany.

Abstract

This study compares various preprocessing techniques for hyperspectral deep learning-based cancer diagnostics. The study considers different spectrum scaling and noise reduction options across spatial and spectral axes of hyperspectral datacubes, as well varying levels of blood and light reflections removal. We also examine how the size of the patches extracted from the hyperspectral data affects the models' performance. We additionally explore various strategies to mitigate our dataset's imbalance (where cancerous tissues are underrepresented). Our results indicate that. Scaling: Standardization significantly improves both sensitivity and specificity compared to Normalization. Larger input patch sizes enhance performance by capturing more spatial context. Noise reduction unexpectedly degrades performance. Blood filtering is more effective than filtering reflected light pixels, although neither approach produces significant results. By carefully maintaining consistent testing conditions, we ensure a fair comparison across preprocessing methods and reproducibility. Our findings highlight the necessity of careful preprocessing selection to maximize deep learning performance in medical imaging applications.

Topics

Deep LearningColorectal NeoplasmsHyperspectral ImagingImage Processing, Computer-AssistedJournal Article

Ready to Sharpen Your Edge?

Join hundreds of your peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.