Construction and effectiveness evaluation of a multiparametric diagnosis prediction model for breast cancer based on Kaiser score

FU Fanxin; LU Yanhui; WANG Wanting; GAO Chao; HAN Zhiquan; LUO Chunyan; LI Jun

doi:10.19732/j.cnki.2096-6210.2026.01.010

您当前的位置：

首页 >

文章列表页 >

Construction and effectiveness evaluation of a multiparametric diagnosis prediction model for breast cancer based on Kaiser score

Article | 更新时间：2026-03-25

- Construction and effectiveness evaluation of a multiparametric diagnosis prediction model for breast cancer based on Kaiser score
- Oncoradiology Vol. 35, Issue 1, Pages: 72-83(2026)
- 作者机构：
  
  昆明医科大学第一附属医院医学影像科，云南 650032
- 作者简介：
  
  LI Jun E-mail: 6644814243@qq.com
- 基金信息：
  
  Fundamental Research Program of Yunnan Province Science and Technology Plan Project Fund (Kunming Medical University Joint Special Project, 202101AY070001-101)(202101AY070001-101)
- DOI：10.19732/j.cnki.2096-6210.2026.01.010
  CLC： R737.9;R445.2
- Received：14 April 2025，
  
  Revised：2025-06-28，
  
  Published：28 February 2026
- 稿件说明：
移动端阅览
付凡欣, 卢艳会, 王婉婷, 等. 基于Kaiser评分的乳腺癌多参数诊断预测模型的构建及效果评价［J］. 肿瘤影像学, 2026, 35(1): 72-83.

FU F X, LU Y H, WANG W TCitation:, et al. Construction and effectiveness evaluation of a multiparametric diagnosis prediction model for breast cancer based on Kaiser score［J］. Oncoradiology, 2026, 35(1): 72-83.
付凡欣, 卢艳会, 王婉婷, 等. 基于Kaiser评分的乳腺癌多参数诊断预测模型的构建及效果评价［J］. 肿瘤影像学, 2026, 35(1): 72-83. DOI： 10.19732/j.cnki.2096-6210.2026.01.010.

FU F X, LU Y H, WANG W TCitation:, et al. Construction and effectiveness evaluation of a multiparametric diagnosis prediction model for breast cancer based on Kaiser score［J］. Oncoradiology, 2026, 35(1): 72-83. DOI： 10.19732/j.cnki.2096-6210.2026.01.010.

摘要

目的

构建基于Kaiser评分的临床-影像多参数Kaiser诊断预测优化模型（简称“Kaiser

模型”）并进行验证，旨在提高对乳腺病灶恶性风险的诊断效能。

方法

收集2020年9月—2023年11月于昆明医科大学第一附属医院行乳腺X线摄影和磁共振成像（magnetic resonance imaging，MRI）检查的患者的临床及影像学资料，所有病灶均经病理学检查证实。将病灶按照7∶3的比例随机分成训练集和验证集。收集以下参数，临床因素包括患者年龄、初潮年龄、绝经情况、乳腺癌家族史、体重指数（body mass index，BMI）；乳腺X线摄影影像参数包括纤维腺体类型、微钙化；乳腺MRI影像参数包括背景实质强化、病灶类型（肿块/非肿块）、形状、边缘、瘤周水肿、病灶内部强化模式、肿瘤周围血管征、时间-信号强度曲线（time-signal intensity curve，TIC）类型、弥散加权成像（diffusion-weighted imaging，DWI）边缘征、表观弥散系数（apparent diffusion coefficient，ADC）值、乳头凹陷、皮肤增厚或回缩。依据Kaiser评分流程图对每个病灶进行评分。采用

检验和

χ²

检验单因素分析筛选预测变量，采用多因素logistic回归构建诊断预测模型，绘制列线图。采用受试者工作特征（receiver operating characteristic，ROC）曲线的曲线下面积（area under curve，AUC）比较Kaiser

模型和Kaiser评分的诊断效能；绘制校准曲线评估模型的校准能力；采用决策曲线分析（decision curve analysis，DCA）评估模型在临床决策中的效用。

结果

本研究纳入347例患者，共347个病灶，其中恶性217个，良性130个。单因素分析显示，年龄、绝经情况、乳头凹陷、皮肤回缩/增厚、微钙化、病灶类型（肿块/非肿块）、形状、周围血管征、DWI边缘征、ADC是Kaiser评分所用指标之外的有效预测因素。Kaiser

模型及Kaiser评分在训练集中的AUC分别为0.962、0.914，差异有统计学意义（

=3.363，

0.01），两者在验证集中的AUC分别为0.976、0.913，差异有统计学意义（

=2.862，

0.01）。校准曲线显示Kaiser

模型的校准度良好；DCA显示Kaiser

模型具有较高的临床应用价值。

结论

本研究设计的Kaiser

模型能在术前用于预测乳腺病变性质，其诊断效能优于经典的Kaiser评分。

Abstract

Objective

To construct and validate a clinical-imaging multiparametric Kaiser diagnostic prediction optimization model based on the Kaiser score (referred to as the Kaiser

model) for improving the efficacy of diagnosis of malignant risk in breast lesions.

Methods

Clinical and imaging data of patients who underwent mammography and breast magnetic resonance imaging (MRI) at the First Affiliated Hospital of Kunming Medical University from September 2020 to November 2023 were collected

and all lesions were confirmed pa

thologically. The lesions were randomly divided into a training set and a validation set in the ratio of 7∶3. The following parameters were collected

clinical factors: patient's age

age at menarche

menopausal status

family history of breast cancer status

body mass index (BMI); Mammography parameters: the amount of fibroglandular tissue (FGT)

microcalcification; Breast MRI parameters: background parenchymal enhancement (BPE)

lesion type (mass or non-mass)

shape

margins

peritumoral edema

internal enhancement pattern

adjacent vessel sign (AVS)

time-signal intensity curve (TIC)

diffusion-weighted imaging (DWI) rim sign

apparent diffusion coefficient (ADC) value

nipple invasion

skin thickening or retraction. Each lesion was scored according to the Kaiser score flow chart. The

test and

test were used for univariate analysis to screen predictive variables

and multivariate logistic regression was used to construct the prediction model and draw the nomogram. Area under the receiver operating characteristic curve (AUC) were used to compare the diagnostic efficacy of Kaiser

model and Kaiser score. Calibration curves were plotted to assess the calibration of the model. Decision curve analysis (DCA) was used to evaluate the clinical validity of the model.

Results

A total of 347 patients were included in this study

with 347 lesions in total

among which 217 were malignant and 130 were benign. Univariate analysis showed that age

menopausal status

nipple invasion

skin thickening or retraction

microcalcification

lesion type (mass or non-mass)

shape

AVS

DWI edge sign

and ADC value were effective predictors other than those used in Kaiser score. In the training set

the AUCs of Kaiser

model and Kaiser score were 0.962 and 0.914

with statistically significant differences (

=3.363

0.01). In the validation set

the AUCs of Kaiser

model and Kaiser score

were 0.976 and 0.913

with statistically significant differences (

=2.862

0.01). The calibration curve showed that the Kaiser

model was well calibrated. DCA indicated that the Kaiser

model had high clinical application value.

Conclusion

The Kaiser

model designed in this study can be used to predict and diagnose the nature of breast lesions before operation

and its diagnostic performance is better than the classical Kaiser score.

关键词

Keywords

references

LEI S Y , ZHENG R S , ZHANG S W , et al . Global patterns of breast cancer incidence and mortality: a population-based cancer registry data analysis from 2000 to 2020 ［J］. Cancer Commun , 2021 , 41 ( 11 ): 1183 - 1194 .

QIU H B , CAO S M , XU R H . Cancer incidence, mortality, and burden in China: a time-trend analysis and comparison with the United States and United Kingdom based on the global epidemiological data released in 2020 ［J］. Cancer Commun , 2021 , 41 ( 10 ): 1037 - 1048 .

MANN R M , CHO N , MOY L . Breast MRI: state of the art ［J］. Radiology , 2019 , 292 ( 3 ): 520 - 536 .

SUMKIN J H , BERG W A , CARTER G J , et al . Diagnostic performance of MRI, molecular breast imaging, and contrast-enhanced mammography in women with newly diagnosed breast cancer ［J］. Radiology , 2019 , 293 ( 3 ): 531 - 540 .

ⅡMA M , HONDA M , SIGMUND E E , et al . Diffusion MRI of the breast: current status and future directions ［J］. J Magn Reson Imaging , 2020 , 52 ( 1 ): 70 - 90 .

LO GULLO R , SEVILIMEDU V , BALTZER P , et al . A survey by the European Society of Breast Imaging on the implementation of breast diffusion-weighted imaging in clinical practice ［J］. Eur Radiol , 2022 , 32 ( 10 ): 6588 - 6597 .

BALTZER P A T , DIETZEL M , KAISER W A . A simple and robust classification tree for differentiation between benign and malignant lesions in MR-mammography ［J］. Eur Radiol , 2013 , 23 ( 8 ): 2051 - 2060 .

李　桢 , 李梦露 , 程流泉 . DCE-TIC曲线与DWI-ADC值联合应用对乳腺良、恶性病变的鉴别诊断价值［J］. 中国医学影像学杂志 , 2019 , 27 ( 9 ): 654 - 658 .

LI Z , LI M L , CHENG L Q . DCE-TIC combined with DWI-ADC in the differential diagnosis of benign and malignant breast lesions ［J］. Chin J Med Imag , 2019 , 27 ( 9 ): 654 - 658 .

MILOS R I , PIPAN F , KALOVIDOURI A , et al . The Kaiser score reliably excludes malignancy in benign contrast-enhancing lesions classified as BI-RADS 4 on breast MRI high-risk screening exams ［J］. Eur Radiol , 2020 , 30 ( 11 ): 6052 - 6061 .

JAJODIA A , SINDHWANI G , PASRICHA S , et al . Application of the Kaiser score to increase diagnostic accuracy in equivocal lesions on diagnostic mammograms referred for MR mammography ［J］. Eur J Radiol , 2021 , 134 : 109413 .

梁　锌 , 杨　剑 , 高　婷 , 等 . 全球女性乳腺癌发病趋势及年龄变化情况分析［J］. 中华肿瘤杂志 , 2023 , 45 ( 4 ): 313 - 321 .

LIANG X , YANG J , GAO T , et al . Analysis on the trends of incidence and age change for global female breast cancer ［J］. Chin J Oncol , 2023 , 45 ( 4 ): 313 - 321 .

KRESOVICH J K , XU Z L , O’BRIEN K M , et al . Methylation-based biological age and breast cancer risk ［J］. J Natl Cancer Inst , 2019 , 111 ( 10 ): 1051 - 1058 .

DUNNERAM Y , GREENWOOD D C , CADE J E . Diet, menopause and the risk of ovarian, endometrial and breast cancer ［J］. Proc Nutr Soc , 2019 , 78 ( 3 ): 438 - 448 .

张　吉 , 刘红胜 . 乳腺可疑钙化与乳腺癌临床病理因素的关系［J］. 中国医师杂志 , 2021 , 23 ( 12 ): 1878 - 1880 .

ZHANG J , LIU H S . Relationship between suspected calcification of breast and clinicopathological factors of breast cancer ［J］. J Chin Physician , 2021 , 23 ( 12 ): 1878 - 1880 .

MORDANG J J , GUBERN-MÉRIDA A , BRIA A , et al . The importance of early detection of calcifications associated with breast cancer in screening ［J］. Breast Cancer Res Treat , 2018 , 167 ( 2 ): 451 - 458 .

VENKATESAN A , CHU P , KERLIKOWSKE K , et al . Positive predictive value of specific mammographic findings according to reader and patient variables ［J］. Radiology , 2009 , 250 ( 3 ): 648 - 657 .

HORVAT J V , KEATING D M , RODRIGUES-DUARTE H , et al . Calcifications at digital breast tomosynthesis: imaging features and biopsy techniques ［J］. Radiographics , 2019 , 39 ( 2 ): 307 - 318 .

ÇETINKAYA E , YıLDıZ Ş , OTÇU H , et al . The value of adjacent vessel sign in malignant breast tumors ［J］. Diagn Interv Radiol , 2022 , 28 ( 5 ): 463 - 469 .

KUL S , CANSU A , ALHAN E , et al . Contrast-enhanced MR angiography of the breast: evaluation of ipsilateral increased vascularity and adjacent vessel sign in the characterization of breast lesions ［J］. AJR Am J Roentgenol , 2010 , 195 ( 5 ): 1250 - 1254 .

KANG B J , LIPSON J A , PLANEY K R , et al . Rim sign in breast lesions on diffusion-weighted magnetic resonance imaging: Diagnostic accuracy and clinical usefulness ［J］. J Magn Reson Imaging , 2015 , 41 ( 3 ): 616 - 623 .

CHOI Y , KIM S H , YOUN I K , et al . Rim sign and histogram analysis of apparent diffusion coefficient values on diffusion-weighted MRI in triple-negative breast cancer: comparison with ER-positive subtype ［J］. PLoS One , 2017 , 12 ( 5 ): e0177903 .

CHOI B B . Dynamic contrast enhanced-MRI and diffusion-weighted image as predictors of lymphovascular invasion in node-negative invasive breast cancer ［J］. World J Surg Oncol , 2021 , 19 ( 1 ): 76 .

BICKEL H , PINKER K , POLANEC S , et al . Diffusion-weighted imaging of breast lesions: region-of-interest placement and different ADC parameters influence apparent diffusion coefficient values ［J］. Eur Radiol , 2017 , 27 ( 5 ): 1883 - 1892 .

SUROV A , MEYER H J , WIENKE A . Can apparent diffusion coefficient (ADC) distinguish breast cancer from benign breast findings? A meta-analysis based on 13 847 lesions ［J］. BMC Cancer , 2019 , 19 ( 1 ): 955 .

CHEN Z W , ZHAO Y F , LIU H R , et al . Assessment of breast lesions by the Kaiser score for differential diagnosis on MRI: the added value of ADC and machine learning modeling ［J］. Eur Radiol , 2022 , 32 ( 10 ): 6608 - 6618 .

任晓梦 , 刘晓春 , 代天姿 , 等 . Kaiser评分与ADC值对乳腺BI-RADS 4类病变的诊断效能评价［J］. 磁共振成像 , 2022 , 13 ( 9 ): 25 - 29 .

REN X M , LIU X C , DAI T Z , et al . Comparative assessment of MRI BI-RADS 4 breast lesions with Kaiser score and apparent diffusion coefficient value ［J］. Chin J Magn Reson Imag , 2022 , 13 ( 9 ): 25 - 29 .

AN Y Y , MAO G Q , AO W Q , et al . Can DWI provide additional value to Kaiser score in evaluation of breast lesions ［J］. Eur Radiol , 2022 , 32 ( 9 ): 5964 - 5973 .

MENG L S , ZHAO X , GUO J X , et al . Improved differential diagnosis based on BI-RADS descriptors and apparent diffusion coefficient for breast lesions: a multiparametric MRI analysis as compared to Kaiser score ［J］. Acad Radiol , 2023 , 30 ( Suppl 2 ): S93 - S103 .

SUN S Y , DINGY Y , Z L , et al . Multiparameter MRI model with DCE-MRI, DWI, and synthetic MRI improves the Diagnostic Performance of BI-RADS 4 Lesions ［J］. Front Oncol , 2021 . Doi: 10.3389/fonc.2021.699127 http://dx.doi.org/10.3389/fonc.2021.699127 .

ZHANG M , HORVAT J V , BERNARD-DAVILA B , et al . Multiparametric MRI model with dynamic contrast-enhanced and diffusion-weighted imaging enables breast cancer diagnosis with high accuracy ［J］. J Magn Reson Imaging , 2019 , 49 ( 3 ): 864 - 874 .

Views

下载量

CNKI被引量

Alert me when the article has been cited

提交

Tools

Publicity Resources

Development of a nomogram for differentiation between pure mucinous breast carcinomas and fibroadenomas based on DCE-MRI features

Diagnostic value of ultrasonic VTIQ combined with MRI in axillary lymph node metastasis of breast cancer

Risk assessment of sentinel lymph node metastasis in breast cancer using a radiomics model based on B-mode ultrasound and color doppler ultrasound

Prediction of sentinel lymph node metastasis in breast cancer using multiparametric MRI radiomics and machine learning models

Prediction of microsatellite instability in rectal cancer using MRI radiomics models based on multiple machine learning algorithms

Related Author

QU Ning

LUO Yahongnbsp

LIU Yanchao

LIU Guokun

WANG Jia

LI Ru

ZHANG Ning

ZHANG Qiang

Related Institution

Department of Ultrasound Medicine, East District, Handan Central Hospital

Department of CT/MRI Room, Handan Central Hospital

Department of Ultrasound, Shanghai Pudong New Area People's Hospital

Department of Radiology, Ma’anshan People’s Hospital, Ma’anshan

The Graduate School, Anhui Medical University

AI脑图

AI问答

⁰