山东医药2026，Vol.66Issue(4)：1-5,15,6.DOI:10.3969/j.issn.1002-266X.2026.04.001
融合妇科查体信息与影像组学特征的子宫颈癌放疗靶区自动勾画模型构建与评价
Construction and evaluation of an automatic segmentation model for radiotherapy target volumes in cervical cancer based on fusion of gynecological examination information and radiomics features
摘要
Abstract
Objective To construct an automatic segmentation model for radiotherapy target volumes of cervical canc-er by integrating gynecological examination information and radiomics features,so as to provide reliable technical support for precise radiotherapy of cervical cancer.Methods A total of 288 patients with cervical cancer who received radiotherapy were enrolled.They were divided into the training set(224 cases)and validation set(64 cases)at a ratio of 7∶2 using a random number table method.Another 32 patients with cervical cancer who received radiotherapy were selected as the inde-pendent test set.Gynecological examination records within 1 week before radiotherapy were collected and converted into structured feature vectors through natural language processing(NLP).Meanwhile,computed tomography(CT)and mag-netic resonance imaging[MRI,including T2-weighted imaging(T2 WI)and diffusion-weighted imaging(DWI)]images were collected,and the radiotherapy target volumes were delineated by senior radiation oncologists as the expert reference standard.A total of 126 radiomics features were extracted using PyRadiomics software,and 68 key features were screened out by least absolute shrinkage and selection operator(LASSO)regression.A single CT-based model was constructed using the classic 3D U-Net architecture with positioning CT images as the only input.A single MRI-based model was built with the same 3D U-Net architecture,using registered T2 WI/DWI dual sequences and CT images as 3-channel input,and only adjusting the input channels to adapt to multi-sequence fusion data.A fusion model was established on the basis of the im-proved U-Net architecture with the addition of a cross-modal attention feature fusion module,taking CT images,fused MRI images,and 7-dimensional gynecological examination feature vectors as inputs.The training set was used for model train-ing,the validation set for real-time monitoring,and the independent test set for evaluating model performance from three di-mensions:segmentation accuracy[including Dice similarity coefficient(DSC),95%Hausdorff distance(HD95),and vol-ume error rate],delineation efficiency,and inter-observer consistency(inter-physician Kappa coefficient).Results The fusion model showed a significantly higher DSC,and significantly lower HD95 and volume error rate than the other two sin-gle-modality models(all P<0.05).The average time consumed by 10 radiation oncologists for manual delineation and fu-sion model-assisted delineation was(58.6±8.3)minutes and(9.2±1.5)minutes,respectively,with a statistically sig-nificant difference(P<0.05).The Kappa coefficients of manual delineation and fusion model-assisted delineation by 10 ra-diation oncologists were 0.62(95%CI:0.55-0.69)and 0.81(95%CI:0.75-0.87),respectively,and the difference was statistically significant(P<0.05).Conclusions The automatic segmentation model for cervical cancer radiotherapy target volumes integrating gynecological examination information and radiomics features is successfully constructed.This model can significantly improve the accuracy and consistency of cervical cancer radiotherapy target volume delineation,and shorten the delineation time.关键词
子宫颈癌/靶区勾画/妇科查体/影像组学/特征融合/模型构建Key words
cervical carcinoma/target volume delineation/gynecological examination/radiomics/feature fusion/model construction分类
医药卫生引用本文复制引用
常世川,蒲万利,刘强,黄小平,方志祥,牟艳红..融合妇科查体信息与影像组学特征的子宫颈癌放疗靶区自动勾画模型构建与评价[J].山东医药,2026,66(4):1-5,15,6.基金项目
重庆市科卫联合医学科研项目面上项目(2024MSXM072). （2024MSXM072）
