Dosimetry-guided morphomic modeling using daily FBCT for automated all-in-one radiotherapy eligibility assessment in postoperative cervical cancer
Abstract
ObjectiveThis study aimed to develop an automated decision-making model based on daily fan-beam CT (FBCT) morphomic features to determine whether a treatment fraction is suitable for AIO-RT initiation.MethodsA total of 48 postoperative cervical cancer patients with 313 FBCT fractions were retrospectively analyzed. Morphomic features were extracted from bladder, rectum, intrarectal gas, bilateral femoral head, and inter-organ spatial relationships. Feature selection was performed using least absolute shrinkage and selection operator (LASSO), and predictive models were built using Random Forest (RF) and Gradient Boosting Machine (GBM) under leave-one-patient-out cross-validation.ResultsBoth models achieved consistent discriminative performance (AUC = 0.958 for RF and 0.952 for GBM). Bladder-related morphological features were the dominant predictors, particularly bladder volume and shape-derived descriptors. Spatial features also contributed to classification performance, while rectal gas showed limited but complementary predictive value.ConclusionThe proposed FBCT-based morphomic framework can accurately identify unsuitable fractions for AIO-RT before workflow initiation, providing a practical and interpretable decision-support tool for adaptive radiotherapy workflow optimization.
Related
- Association between radiotherapy laterality and cardiovascular disease mortality in male breast cancer patients receiving postoperative radiotherapy: a competing risks analysis and standardized mortality ratio assessment using SEER data.
- Functional Recovery After Severe Postoperative Decline in Glioblastoma: The Importance of Reassessing Treatment Eligibility
- Machine learning predictors of post-radiotherapy cardiotoxicity in a Latin American breast cancer cohort: Clinical risk factors outperform cardiac dosimetry.
- Safety of concurrent immune checkpoint inhibitor therapy during postoperative radiotherapy for triple-negative breast cancer: A preliminary retrospective analysis
- Postoperative radiotherapy after tracheal reconstruction with cryopreserved aortic allograft for adenoid cystic carcinoma
BibTeX
@article{xu2026dosimetryguided,
title = {{Dosimetry-guided morphomic modeling using daily FBCT for automated all-in-one radiotherapy eligibility assessment in postoperative cervical cancer}},
author = {Yueliang Xu and Hao Chen and Xiaoting Xu and Songbing Qin and Guanghui Gan and Yuan Xu},
journal = {Frontiers in Oncology},
year = {2026},
month = nov,
doi = {10.3389/fonc.2026.1913463},
url = {https://www.frontiersin.org/articles/10.3389/fonc.2026.1913463},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Dosimetry-guided morphomic modeling using daily FBCT for automated all-in-one radiotherapy eligibility assessment in postoperative cervical cancer
AU - Yueliang Xu
AU - Hao Chen
AU - Xiaoting Xu
AU - Songbing Qin
AU - Guanghui Gan
AU - Yuan Xu
PY - 2026
DA - 2026/11/03
JO - Frontiers in Oncology
DO - 10.3389/fonc.2026.1913463
UR - https://www.frontiersin.org/articles/10.3389/fonc.2026.1913463
AB - ObjectiveThis study aimed to develop an automated decision-making model based on daily fan-beam CT (FBCT) morphomic features to determine whether a treatment fraction is suitable for AIO-RT initiation.MethodsA total of 48 postoperative cervical cancer patients with 313 FBCT fractions were retrospectively analyzed. Morphomic features were extracted from bladder, rectum, intrarectal gas, bilateral femoral head, and inter-organ spatial relationships. Feature selection was performed using least absolute shrinkage and selection operator (LASSO), and predictive models were built using Random Forest (RF) and Gradient Boosting Machine (GBM) under leave-one-patient-out cross-validation.ResultsBoth models achieved consistent discriminative performance (AUC = 0.958 for RF and 0.952 for GBM). Bladder-related morphological features were the dominant predictors, particularly bladder volume and shape-derived descriptors. Spatial features also contributed to classification performance, while rectal gas showed limited but complementary predictive value.ConclusionThe proposed FBCT-based morphomic framework can accurately identify unsuitable fractions for AIO-RT before workflow initiation, providing a practical and interpretable decision-support tool for adaptive radiotherapy workflow optimization.
SN - 2234-943X
ER -