Comparison of reduced field‐of‐view DWI with conventional DWI for machine learning‐based assessment of lymphovascular invasion in rectal cancer
Medical Physics · 2025
DOI: 10.1002/mp.70015 ↗At a glance
Vergleichsstudie in Medical Physics, 2025. Written by Weinuo Qu and 6 co-authors. Institution: Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei, P.R. China. Major MEDLINE topics: Rectal Neoplasms, Diffusion Magnetic Resonance Imaging, Machine Learning, Image Processing, Computer-Assisted. 36 references. Funded by: National Natural Science Foundation of China, Hubei Provincial Health Science and Technology Project.
Abstract (original language)
Background
Lymphovascular invasion (LVI) is an important prognostic factor of rectal cancer and influences treatment planning. MRI‐based radiomic features provide phenotypic information on tumor biological behaviors.
Purpose
We aimed to compare the performance of different models derived from reduced field‐of‐view diffusion‐weighted imaging (rDWI) for prediction of lymphovascular invasion (LVI) in comparison with conventional DWI (fDWI) and high‐resolution T2‐weighted imaging (T2WI).
Methods
Eighty‐six rectal cancer patients received rDWI, fDWI, and high‐resolution T2WI at 3T. Whole‐lesion ROI delineations were performed on above sequences for radiomic feature extractions (60 and 26 patients in training and test cohorts, respectively). A baseline logistic model was applied to all sequences to compare their diagnostic performances in predicting LVI. Different machine learning models, including eXtreme Gradient Boosting (XGBoost), Support Vector Machine (SVM), and Random Forest (RF) were further utilized on rDWI to assess LVI status. The performances of different models from these sequences and visual interpretation by radiologists were evaluated and compared for LVI prediction.
Results
Radiomic models from DWI sequences performed better than visual interpretation for diagnosing LVI ( p = 0.002–0.036). In logistics models, radiomics derived from rDWI outperformed those from T2WI ( z = 2.064, p = 0.039) in differentiating‐LVI. AUC of rDWI model was higher than that of fDWI but the difference was not statistically significant ( z = 1.006, p = 0.315). No significant differences of performance were detected between fDWI and T2WI ( p > 0.05). The best performance, with an AUC of 0.957, was achieved by the RF model derived from rDWI in the training cohort, with a significant difference noted between the RF and logistic models for LVI prediction ( z = 2.250, p = 0.032).
Conclusion
RDWI‐derived radiomics performed better than T2WI and fDWI in differentiating LVI. Radiomic models based on rDWI were promising tools for facilitating clinical assessment of LVI status in rectal cancer.
Subjects
MeSH terms (MEDLINE)
Author keywords
Authors and institutions
- Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei, P.R. China.
- Department of Pediatrics, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei, P.R. China.
Funding
- National Natural Science Foundation of China
- Hubei Provincial Health Science and Technology Project
Cite
APA
Qu, W., Wang, J., Li, J., Shen, Y., Peng, Y., Hu, D., & Li, Z. (2025). Comparison of reduced field‐of‐view DWI with conventional DWI for machine learning‐based assessment of lymphovascular invasion in rectal cancer. Medical Physics. https://doi.org/10.1002/mp.70015
Vancouver
Qu W, Wang J, Li J, Shen Y, Peng Y, Hu D, et al. Comparison of reduced field‐of‐view DWI with conventional DWI for machine learning‐based assessment of lymphovascular invasion in rectal cancer. Medical Physics. 2025. doi:10.1002/mp.70015
BibTeX
@article{Qu2025,
author = {Qu, Weinuo and Wang, Jing and Li, Jiali and Shen, Yaqi and Peng, Yang and Hu, Daoyu and Li, Zhen},
title = {Comparison of reduced field‐of‐view DWI with conventional DWI for machine learning‐based assessment of lymphovascular invasion in rectal cancer},
journal = {Medical Physics},
year = {2025},
doi = {10.1002/mp.70015}
}
EUVIMED