Comparison of Postoperative Recurrence Prediction Capability among CEST, DWI, PET/CT and Combined Indexes in Stage I Non-Small Cell Lung Cancer
Motivation: CEST has a potential to play a complementary role for prediction of postoperative recurrence and improve the prediction capability as compared with DWI, CEST and FDG-PET/CT in NSCLC patients. Goal(s): The goal was to compare the quantitative prediction capability for postoperative recurrence of FDG-PET/CT and MRI-based molecular information from CEST and DWI in stage I NSCLC patients. Approach: This clinical study examined CEST imaging, DWI and FDG-PET/CT, and all indexes and combined predictors were compared prediction capabilities in NSCLC. Results: Specificities and accuracies of MTRasym, ADC and combined predictors were significantly higher than those of SUVmax (p<0.05). Impact: MRI-based molecular information has better potential for prediction of postoperative recurrence than FDG-PET/CT in stage I NSCLC patients. Moreover, combined CEST and DWI information can improve prediction capability of CEST imaging in this setting.
Authors
- Masao Yui (ORCID: https://orcid.org/0000-0002-2562-0623)
- Daisuke Takenaka (ORCID: https://orcid.org/0000-0002-9432-7180)
- Takeshi Yoshikawa (ORCID: https://orcid.org/0000-0001-5560-5371)
- Hiroyuki Nagata (ORCID: https://orcid.org/0000-0001-7998-955X)
- Kaori Yamamoto (ORCID: https://orcid.org/0000-0003-0884-3419)
- Yoshiharu Ohno (ORCID: https://orcid.org/0000-0002-4431-1084)
- Masato Ikedo (ORCID: https://orcid.org/0000-0002-2701-1899)
- Takahiro Ueda (ORCID: https://orcid.org/0000-0003-2577-3619)
- Yoshiyuki Ozawa (ORCID: https://orcid.org/0000-0002-8252-1947)
- Masahiko Nomura
- Masanori Ozaki
Publication Details
- Journal
- Proceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition
- Published
- 2025-09-16
- DOI
- https://doi.org/10.58530/2025/1065
- Primary Topic
- Radiomics and Machine Learning in Medical Imaging
- Type
- article
- Field-Weighted Citation Impact
- 0.00