AUTHOR=Yue Haizhen , Li Xiaofan , You Jing , Feng Pujie , Du Yi , Wang Ruoxi , Wu Hao , Cheng Jinsheng , Ding Kuke , Jing Bin 

TITLE=Acute hematologic toxicity prediction using dosimetric and radiomics features in patients with cervical cancer: does the treatment regimen matter?

JOURNAL=Frontiers in Oncology

VOLUME=Volume 14 - 2024

YEAR=2024

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2024.1365897

DOI=10.3389/fonc.2024.1365897

ISSN=2234-943X

ABSTRACT=Acute hematologic toxicity (HT) is a prevalent adverse tissue reaction observed in cervical cancer patients undergoing chemoradiotherapy (CRT), which may lead to various negative effects such as compromised therapeutic efficacy and prolonged treatment duration.The accurate prediction of HT occurrence prior to CRT remains challenging. A discovery dataset comprising of 478 continuous cervical cancer patients (140 HT patients) and a validation dataset consisting of 205 patients (52 HT patients) were retrospectively enrolled. Both datasets were categorized into CRT and radiotherapy (RT) alone group based on the treatment regimen, i.e. whether chemotherapy was administered within the focused RT duration. Radiomics features were derived by contouring three region of interests (ROIs): bone marrow (BM), femoral head and clinical target volume on the treatment planning CT images before RT. A comprehensive model of combining the Radiomics features as well as the demographic, clinical and dosimetric features were respectively constructed to classify patients exhibiting acute HT symptoms in CRT group, RT group and their combination group. Furthermore, the time-to-event analysis of the discriminative ROI was performed on all patients with acute HT to understand the HT temporal progression. Among three ROIs, BM exhibited the best performance in classifying acute HT, which was verified across all patient groups in both discovery and validation datasets. Among different patient groups in discovery dataset, acute HT was more precisely predicted in CRT group (AUC = 0.779, 95% CI: 0.657-0.874) than that in the RT alone (AUC = 0.686, 95% CI: 0.529-0.817) or the combination groups (AUC = 0.748, 95% CI: 0.655-0.827). The predictive results in the validation dataset were similarly coincided with the discovery dataset: CRT group (AUC = 0.802, 95% CI: 0.669-0.914), RT alone group (AUC = 0.737, 95% CI: 0.612-0.862) and combination group (AUC = 0.793, 95% CI: 0.713-0.874). In addition, distinct feature sets were adopted for different patient group. Moreover, the predicted HT risk of BM was also indicative for the HT temporal progression. HT prediction in cervical patients is both dependent on the treatment regimen and ROI selection, and BM is closely related to the occurrence and progression of HT, especially for the CRT patients.