Usefulness of texture features of apparent diffusion coefficient maps in predicting chemoradiotherapy response in muscle-invasive bladder cancer.
Koichiro KimuraSoichiro YoshidaJunichi TsuchiyaIchiro YamadaHajime TanakaMinato YokoyamaYoh MatsuokaRyoichi YoshimuraUkihide TateishiYasuhisa FujiiPublished in: European radiology (2021)
• Texture analysis of ADC maps and feature selection identified important texture features for classifying pathologic tumor response in patients with muscle-invasive bladder cancer. • The machine learning model incorporating the texture features set, which included first quartile ADC, GLCM correlation, and GLCM homogeneity, showed high performance in predicting chemoradiotherapy response. • Texture features could serve as imaging biomarkers that optimize eligible patient selection for chemoradiotherapy in muscle-invasive bladder cancer.
Keyphrases
- muscle invasive bladder cancer
- contrast enhanced
- diffusion weighted imaging
- machine learning
- locally advanced
- rectal cancer
- diffusion weighted
- magnetic resonance imaging
- neoadjuvant chemotherapy
- high resolution
- computed tomography
- squamous cell carcinoma
- magnetic resonance
- artificial intelligence
- resting state
- functional connectivity