Feasibility Study of an Efficient Plan Pool Adaptive Radiotherapy Technology Based on Low-dose Computed Tomography for Cervical Cancer

IF 3 3区医学 Q2 ONCOLOGY

Clinical oncology Pub Date : 2025-07-09 DOI:10.1016/j.clon.2025.103903

F. Sun , Y. Xu , X. Xu , W. Gong , Z. Mo , L. Jia , S. Qin , G. Gan

{"title":"Feasibility Study of an Efficient Plan Pool Adaptive Radiotherapy Technology Based on Low-dose Computed Tomography for Cervical Cancer","authors":"F. Sun , Y. Xu , X. Xu , W. Gong , Z. Mo , L. Jia , S. Qin , G. Gan","doi":"10.1016/j.clon.2025.103903","DOIUrl":null,"url":null,"abstract":"<div><h3>Background</h3><div>Online adaptive radiotherapy (oART) involves a complex workflow across multiple departments, requiring significant resources and increasing the workload of radiation oncologists (ROs) and physicists. For cervical cancer, there is a need for a low-dose, image-guided adaptive radiotherapy solution that is both efficient and clinically effective</div></div><div><h3>Aims</h3><div>The aim is to explore the feasibility and performance of a plan-pool adaptive radiotherapy (plan-pool ART) workflow, with a focus on efficiency and dosimetric benefits for both the tumour and organs at risk (OARs).</div></div><div><h3>Materials and Methods</h3><div>A plan-pool ART framework was developed for cervical cancer radiotherapy based on the daily low-dose computed tomography (LDCT). The LDCT images were synthesised into high-quality restorative CT (RCT) images by an image-synthesis model. A total of 257 fractionated fan-beam computed tomography (FBCT) datasets from 17 cervical cancer patients treated with the oART regimen were collected (171 fractions treated with oART and 86 fractions treated with the original plan). A support vector machine (SVM) was used to train (180 cases) and evaluate (77 cases) the oART classification model, which predicts whether the fraction needs to execute oART. The oART classification model selects the daily treatment plan that best aligns with the patient's anatomical positions from the plan pool. Finally, the performance of image-guided radiotherapy (IGRT), plan-pool ART, and triggered oART (trigger-oART) techniques was compared by simulating treatments for 5 cervical cancer cases.</div></div><div><h3>Results</h3><div>The oART classification model achieved high predictive performance, with an under the curve (AUC) of 0.98, accuracy of 0.86, recall of 0.89, and specificity of 0.92. Plan-pool ART reduced the number of oART execution (1.4 vs 3.0 for trigger-oART) while optimising dosimetry. Compared to IGRT, plan-pool ART decreased mean bladder dose (3122cGy vs 3258cGy) and rectum dose (3265cGy vs 3325cGy), along with lower V<sub>4500cGy</sub> values for both organs. Target coverage remained comparable across techniques, but IGRT showed greater variability in CTV D<sub>99%</sub>, leading to potential underdosing.</div></div><div><h3>Conclusion</h3><div>The simulation results demonstrate that the plan-pool ART technology is feasible, ensuring reliable target dose coverage, reducing the dose to OARs, and lowering the number of oART implementation. This approach offers a promising new technical solution for clinical treatment.</div></div>","PeriodicalId":10403,"journal":{"name":"Clinical oncology","volume":"45 ","pages":"Article 103903"},"PeriodicalIF":3.0000,"publicationDate":"2025-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Clinical oncology","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S093665552500158X","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ONCOLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

Background

Online adaptive radiotherapy (oART) involves a complex workflow across multiple departments, requiring significant resources and increasing the workload of radiation oncologists (ROs) and physicists. For cervical cancer, there is a need for a low-dose, image-guided adaptive radiotherapy solution that is both efficient and clinically effective

Aims

The aim is to explore the feasibility and performance of a plan-pool adaptive radiotherapy (plan-pool ART) workflow, with a focus on efficiency and dosimetric benefits for both the tumour and organs at risk (OARs).

Materials and Methods

A plan-pool ART framework was developed for cervical cancer radiotherapy based on the daily low-dose computed tomography (LDCT). The LDCT images were synthesised into high-quality restorative CT (RCT) images by an image-synthesis model. A total of 257 fractionated fan-beam computed tomography (FBCT) datasets from 17 cervical cancer patients treated with the oART regimen were collected (171 fractions treated with oART and 86 fractions treated with the original plan). A support vector machine (SVM) was used to train (180 cases) and evaluate (77 cases) the oART classification model, which predicts whether the fraction needs to execute oART. The oART classification model selects the daily treatment plan that best aligns with the patient's anatomical positions from the plan pool. Finally, the performance of image-guided radiotherapy (IGRT), plan-pool ART, and triggered oART (trigger-oART) techniques was compared by simulating treatments for 5 cervical cancer cases.

Results

The oART classification model achieved high predictive performance, with an under the curve (AUC) of 0.98, accuracy of 0.86, recall of 0.89, and specificity of 0.92. Plan-pool ART reduced the number of oART execution (1.4 vs 3.0 for trigger-oART) while optimising dosimetry. Compared to IGRT, plan-pool ART decreased mean bladder dose (3122cGy vs 3258cGy) and rectum dose (3265cGy vs 3325cGy), along with lower V_4500cGy values for both organs. Target coverage remained comparable across techniques, but IGRT showed greater variability in CTV D_99%, leading to potential underdosing.

Conclusion

The simulation results demonstrate that the plan-pool ART technology is feasible, ensuring reliable target dose coverage, reducing the dose to OARs, and lowering the number of oART implementation. This approach offers a promising new technical solution for clinical treatment.

查看原文本刊更多论文

基于低剂量ct的宫颈癌高效计划池适应性放疗技术的可行性研究

在线自适应放疗（oART）涉及跨多个部门的复杂工作流程，需要大量资源并增加放射肿瘤学家（ROs）和物理学家的工作量。对于宫颈癌，需要一种低剂量，图像引导的适应性放疗解决方案，既高效又临床有效。目的是探索计划-池适应性放疗（计划-池ART）工作流程的可行性和性能，重点关注肿瘤和危险器官（OARs）的效率和剂量学益处。材料与方法建立基于每日低剂量计算机断层扫描（LDCT）的宫颈癌放疗计划池ART框架。通过图像合成模型将LDCT图像合成为高质量的恢复CT （RCT）图像。共收集了17例接受oART方案治疗的宫颈癌患者的257个扇形束计算机断层扫描（FBCT）数据集（171个部分接受oART治疗，86个部分接受原方案治疗）。使用支持向量机（SVM）训练（180例）和评估（77例）oART分类模型，预测分数是否需要执行oART。oART分类模型从方案池中选择最符合患者解剖位置的日常治疗方案。最后，通过对5例宫颈癌患者的模拟治疗，比较图像引导放疗（IGRT）、计划池ART和触发oART （trigger-oART）技术的效果。结果oART分类模型具有较好的预测效果，曲线下AUC为0.98，准确率为0.86，召回率为0.89，特异性为0.92。计划池ART减少了oART的执行次数（1.4 vs 3.0触发oART），同时优化了剂量学。与IGRT相比，计划池ART降低了膀胱平均剂量（3122cGy vs 3258cGy）和直肠平均剂量（3265cGy vs 3325cGy），两个器官的V4500cGy值也较低。不同技术的靶覆盖率保持可比性，但IGRT在CTV D99%中表现出更大的变异性，导致潜在的剂量不足。仿真结果表明，计划池ART技术是可行的，保证了可靠的靶剂量覆盖，减少了OARs的剂量，减少了oART的实施次数。这种方法为临床治疗提供了一种很有前途的新技术解决方案。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Clinical oncology 医学-肿瘤学

CiteScore

5.20

自引率

8.80%

发文量

332

审稿时长

40 days

期刊介绍： Clinical Oncology is an International cancer journal covering all aspects of the clinical management of cancer patients, reflecting a multidisciplinary approach to therapy. Papers, editorials and reviews are published on all types of malignant disease embracing, pathology, diagnosis and treatment, including radiotherapy, chemotherapy, surgery, combined modality treatment and palliative care. Research and review papers covering epidemiology, radiobiology, radiation physics, tumour biology, and immunology are also published, together with letters to the editor, case reports and book reviews.