Modelling and Optimisation of Treatment Parameters in High-Dose-Rate Mono Brachytherapy for Localised Prostate Carcinoma using a Multilayer Artificial Neural Network and a Genetic Algorithm: Pilot study,Computers in Biology and Medicine

当前位置： X-MOL 学术 › Comput. Biol. Med. › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

Modelling and Optimisation of Treatment Parameters in High-Dose-Rate Mono Brachytherapy for Localised Prostate Carcinoma using a Multilayer Artificial Neural Network and a Genetic Algorithm: Pilot study
Computers in Biology and Medicine ( IF 7.0 ) Pub Date : 2020-10-13 , DOI: 10.1016/j.compbiomed.2020.104045
Katarina M Rajković ₁ , Kata Dabić-Stanković ₂ , Jovan Stanković ₂ , Miodrag Aćimović ₃ , Nina Đukanović ₄ , Borislava Nikolin ₅

Affiliation

Background

High-dose-rate mono brachytherapy (HDR-MB) is employed in the treatment of prostate carcinoma (CaP). As an ideal plan of CaP brachytherapy cannot be created, it is necessary to identify a reliable tool to optimise the parameters of HDR-MB. This paper applies a multilayer artificial neural network (MANN) and a genetic algorithm (GA) to optimise brachytherapy parameters based on an individual dose-volumetric analysis.

Methods

Patients with localised CaP of various risks were treated with HDR–MB. Consecutive levels of the biochemical control parameter (prostate specific antigen (PSA) nadir) have been collected after completion of HDR-MB in the range 2–9 years. The Kaplan–Meier regression analysis of biochemical-free survival (BFS) was applied. The clinical risk of recurrent CaP (RCaP), the therapy dose (TD), TD coverage index (CI_100%) and PSA nadir were modelled using the MANN and GA.

Results

In the low-risk group, BFS was achieved in 100% of treated patients, while in the group of patients with high risk, BFS was achieved in 95.8% of treated patients. The MANN-GA model optimises a TD of 47.3 Gy and CI_100% of 1.14 as well as a TD of 50.4 Gy and CI_100% of 1.6 for the low-risk group and high-risk group, respectively, of localised CaP. The optimised PSA nadir was 0.047 and 0.25 ng·cm^-3 for low-risk group and high-risk group, respectively.

Conclusions

The developed MANN-GA model presents a method for optimising the treatment parameters in radiation therapy, which could be a valuable tool in planning of the HDR-MB.

中文翻译：

多层人工神经网络和遗传算法对局部前列腺癌大剂量率近距离放射治疗的建模和优化：先导研究

背景

高剂量率单程近距离放射疗法（HDR-MB）用于治疗前列腺癌（CaP）。由于无法制定理想的CaP近距离放射治疗计划，因此有必要找到可靠的工具来优化HDR-MB的参数。本文应用多层人工神经网络（MANN）和遗传算法（GA）来基于个体剂量-体积分析优化近距离放射治疗参数。

方法

患有各种风险的局部CaP的患者接受HDR–MB治疗。在2-9年内完成HDR-MB后，已连续收集了生化控制参数（前列腺特异抗原（PSA）最低点）水平。应用了无生化存活率（BFS）的Kaplan-Meier回归分析。使用MANN和GA对复发性CaP（RCaP），治疗剂量（TD），TD覆盖指数（CI _100％）和PSA最低点的临床风险进行建模。

结果

在低风险组中，接受治疗的患者中100％达到了BFS，而在高危患者中，接受治疗的患者中95.8％达到了BFS。对于局部CaP的低风险组和高风险组，MANN-GA模型分别优化了TD的47.3 Gy和CI _100％的1.14以及TD的50.4 Gy和CI _100％的TD。低风险组和高风险组的最佳PSA最低值分别为0.047和0.25 ng·cm ^-3。