# Correlation Between Dosimetric Parameters and Hematologic Toxicity in Cervical Cancer Patients Undergoing Intensity-Modulated Pelvic Radiotherapy

## TL;DR

This study finds that chemotherapy, rather than radiation dose to bone marrow, is the main cause of severe blood-related side effects in cervical cancer patients.

## Contribution

The study introduces AI-based bone marrow delineation to assess dosimetric parameters and identifies chemotherapy as a stronger predictor of hematologic toxicity than radiation dose.

## Key findings

- 75.8% of patients developed grade ≥ 2 hematologic toxicity, and 23.4% developed grade ≥ 3 toxicity.
- Chemotherapy, especially when combined with neoadjuvant and concurrent treatment, is a stronger predictor of severe toxicity than most bone marrow radiation doses.
- Femoral head radiation doses were identified as independent predictors of severe hematologic toxicity.

## Abstract

This study investigated the relationship between radiation dose to the pelvic bone marrow and the development of hematologic toxicity (HT) in 141 patients with cervical cancer undergoing radiotherapy and chemotherapy. Using artificial intelligence to precisely delineate bone marrow regions, the researchers analyzed dose-volume parameters and clinical factors associated with HT. The results showed that 75.8% of patients developed grade ≥ 2 HT, and 23.4% developed grade ≥ 3 HT. Notably, patients receiving both neoadjuvant and concurrent chemotherapy had a threefold higher risk of severe HT compared to those receiving radiotherapy alone or with concurrent chemotherapy alone, making chemotherapy a stronger predictor of HT than most bone marrow radiation doses. Femoral head dose was also identified as an independent predictor. These findings highlight that the systemic effects of chemotherapy, rather than localized bone marrow irradiation, predominantly drive severe hematologic toxicity. This knowledge is valuable for clinical practice as it identifies a particularly high-risk patient population requiring close hematologic monitoring and suggests that modifying systemic therapy may be more effective than bone marrow dose constraints alone in mitigating treatment-related toxicity.

Objective: This study aimed to elucidate the association between hematologic toxicity (HT) and pelvic bone marrow (PBM) dosimetric parameters in patients with cervical cancer (CC) undergoing radiotherapy (RT) combined with artificial intelligence (AI)-assisted organ at risk (OAR) delineation (Software Copyright Registration Number 2023SR0150365). Accurate delineation of bone marrow (BM) regions and analysis of radiation doses may provide a theoretical foundation for the application of AI in predicting HT. Methods: This retrospective study included 141 patients with CC who received chemotherapy (sequential or concurrent) and/or pelvic volumetric modulated arc therapy (VMAT) at the Department of Gynecology, Cancer Hospital of the Chinese Academy of Medical Sciences, between March 2019 and December 2019. PBM and its subregions (ilium, lower pelvis, lumbosacral spine, and femoral heads) were delineated using AI-based automatic segmentation of CT images. The volumes receiving 10–40 Gy (V10, V20, V30, V40) were calculated, and baseline clinical characteristics were assessed. HT endpoints included grade ≥ 2 (HT2+) and grade ≥ 3 (HT3+) leukopenia, neutropenia, anemia, or thrombocytopenia. Associations between dosimetric parameters and HT were evaluated using logistic regression models. Results: Of the 141 patients, 107 (75.8%) developed HT2+ and 33 (23.4%) developed HT3+. Univariate analysis showed that chemotherapy and age were correlated with HT2+. Multivariate analysis identified femoral head V30, femoral head V40, and chemotherapy as independent predictors of HT3+. Conclusions: This study highlights the potential of AI-based OAR delineation for assessing PBM dosimetric parameters in patients with CC. Optimizing RT to minimize BM dose and volume may mitigate HT and enhance treatment tolerance. In our cohort, receipt of combined neoadjuvant and concurrent chemotherapy (NACT+CCRT) was a stronger predictor of HT than most BM dosimetric parameters, suggesting that the systemic effect of chemotherapy may dominate the hematologic toxicity profile in this setting. Consequently, patients receiving this combined modality treatment are at particularly high risk for HT and warrant close hematologic monitoring.