Inferring FDG-PET-positivity of lymph node metastases in proven lung cancer from contrast-enhanced CT using radiomics and machine learning.
Boris GorodetskiPhilipp Hendrik BeckerAlexander Daniel Jacques BaurAlexander HartensteinJulian Manuel Michael RogaschChristian FurthHolger AmthauerBernd HammMarcus MakowskiTobias PenzkoferPublished in: European radiology experimental (2022)
Radiomics showed good discrimination power irrespective of the modeling technique in detecting LN metastases in patients with known lung cancer. The LASSO classifier was a suitable diagnostic tool and even outperformed the expert radiologists, except for high probabilities. Radiomics failed to improve clinical benefit as a prescreening tool.
Keyphrases
- contrast enhanced
- computed tomography
- diffusion weighted
- lymph node
- magnetic resonance imaging
- machine learning
- positron emission tomography
- magnetic resonance
- pet ct
- diffusion weighted imaging
- artificial intelligence
- pet imaging
- dual energy
- neoadjuvant chemotherapy
- big data
- squamous cell carcinoma
- image quality
- radiation therapy