WJCR World Journal of Cancer Research 2164-9049 Scientific Research Publishing 10.12677/WJCR.2024.141007 WJCR-79767 WJCR20240100000_58946220.pdf 医药卫生 影像组学在预测乳腺癌分子分型的应用进展 Advances in the Application of Radiomics in Predicting Molecular Typing of Breast Cancer 学波 1 * 鲜霞 3 2 青海大学研究生院,青海 西宁 青海省人民医院超声科,青海 西宁 null 09 01 2024 14 01 41 47 © Copyright 2014 by authors and Scientific Research Publishing Inc. 2014 This work is licensed under the Creative Commons Attribution International License (CC BY). http://creativecommons.org/licenses/by/4.0/

乳腺癌分子亚型的准确诊断对于指导医生制定个体化治疗方案具有重要意义。目前临床主要通过病理组织进行免疫组化分析获取乳腺癌分子分型,然而取样和分析可能存在一定的局限性。影像组学技术由于其将医学图像转换为用于定量研究的高维数据的能力而成为替代方案,提供了对肿瘤的非侵入性和全面评估。本文就影像组学在预测乳腺癌分子分型中的应用进展予以综述。 Accurate diagnosis of molecular subtypes of breast cancer is of great significance to guide doctors to make individualized treatment plan. At present, the molecular classification of breast cancer is mainly obtained through immunohistochemical analysis of pathological tissues, but there may be some limitations in sampling and analysis. Radiomics technology has emerged as an alternative due to its ability to convert medical images into high-dimensional data for quantitative studies, providing a non-invasive and comprehensive assessment of tumors. This article reviews the application of radiomics in predicting molecular typing of breast cancer.

影像组学,机器学习,乳腺癌,分子分型, Radiomics Machine Learning Breast Cancer Molecular Typing
摘要

乳腺癌分子亚型的准确诊断对于指导医生制定个体化治疗方案具有重要意义。目前临床主要通过病理组织进行免疫组化分析获取乳腺癌分子分型,然而取样和分析可能存在一定的局限性。影像组学技术由于其将医学图像转换为用于定量研究的高维数据的能力而成为替代方案,提供了对肿瘤的非侵入性和全面评估。本文就影像组学在预测乳腺癌分子分型中的应用进展予以综述。

关键词

影像组学,机器学习,乳腺癌,分子分型

Advances in the Application of Radiomics in Predicting Molecular Typing of Breast Cancer<sup> </sup>

Xuebo Zhao1, Xianxia Chen2*

1Graduate School of Qinghai University, Xining Qinghai

2Department of Ultrasound, Qinghai Provincial People’s Hospital, Xining Qinghai

Received: Dec. 16th, 2023; accepted: Jan. 16th, 2024; published: Jan. 24th, 2024

ABSTRACT

Accurate diagnosis of molecular subtypes of breast cancer is of great significance to guide doctors to make individualized treatment plan. At present, the molecular classification of breast cancer is mainly obtained through immunohistochemical analysis of pathological tissues, but there may be some limitations in sampling and analysis. Radiomics technology has emerged as an alternative due to its ability to convert medical images into high-dimensional data for quantitative studies, providing a non-invasive and comprehensive assessment of tumors. This article reviews the application of radiomics in predicting molecular typing of breast cancer.

Keywords:Radiomics, Machine Learning, Breast Cancer, Molecular Typing

Copyright © 2024 by author(s) and beplay安卓登录

This work is licensed under the Creative Commons Attribution International License (CC BY 4.0).

http://creativecommons.org/licenses/by/4.0/

1. 引言

在女性中,乳腺癌仍然是最常诊断的恶性肿瘤,也是癌症相关死亡的主要原因之一,全球估计有多达208万新发病例和63万例死亡 [ 1 ] [ 2 ] 。2013年,第13届Gallen国际乳腺癌会议发布了乳腺癌分子亚型的新定义:Luminal A型、Luminal B型、HER-2过表达型、TNBC和其他特殊亚型 [ 3 ] 。不同亚型患者的治疗方案和预后不同 [ 4 ] [ 5 ] 。因此,乳腺癌分子亚型的准确诊断对于指导医生制定个体化治疗方案具有重要意义。目前组织病理学检查仍然是乳腺癌明确诊断的金标准 [ 6 ] 。然而,活检取样具有侵入性且费用昂贵。此外,仅选取部分肿瘤样本组织可能会忽略肿瘤存在的异质性 [ 7 ] [ 8 ] 。为了解决这一限制,影像组学(radiomics)技术由于其将医学图像转换为用于定量研究的高维数据的能力而成为替代方案 [ 9 ] [ 10 ] ,提供了对肿瘤的非侵入性和全面评估。因此,影像组学在预测乳腺癌分子分型中的研究应用成为近年的热点。

2. 影像组学概述

荷兰学者Lambin等 [ 11 ] 于2012年首次提出“影像组学”这一概念,其采用自动化的方式将传统医学影像学转化为高维可发掘的特征空间,并对其进分析,筛选出最有价值的影像组学特征,构建模型,用于疾病的精准诊断、疗效评估和预后预测等,在辅助临床决策方面具有重要作用。

影像组学流程 [ 12 ] 主要包括5个步骤:(1) 高质量、标准化医学影像数据的获取:影像数据来源广泛,最常见的有超声、X线、CT、MRI、PET等;(2) 肿瘤感兴趣区(ROI)的分割:标定出影像数据中的目标区域。勾画方法分人工勾划、半自动勾划、全自动勾划3类,其中半自动及自动分割方法速度快,但缺乏精度,易受到病灶周围因素影响;(3) 高通量影像组学特征提取:目前常用的影像组学特征包括一阶灰度直方图特征、二阶纹理特征、高阶纹理特征和变换特征四大类。特征值取决于图像预处理和图像重建;(4) 特征筛选:从特征集中选择区分度好、可靠性高的特征模型训练,提高模型的泛化能力;(5) 模型建立与验证。

3. 影像组学预测乳腺癌分子分型的应用现状 3.1. 超声影像组学

常规超声检查因其可重复性及无创等原因成为诊断及筛查BC的最常用方法 [ 13 ] 。最近,许荣等 [ 14 ] 基于术前超声图像提取1314个病灶影像组学特征,采用最小绝对收缩和选择算子(LASSO)算法筛选出37个最佳影像组学特征,构建的影像组学模型预测训练集和测试集ER及PR双阴乳腺癌的AUC分别为0.872和0.867 [ 14 ] 。Ferre等 [ 15 ] 基于灰度超声图像提取影像组学特征评估对TNBC与非TNBC和HER-2阳性与HER-2阴性乳腺癌进行分类表现出的诊断性能,Logistic模型显示AUC、灵敏度、特异度分别为0.824、0.818,0.742。另外,Wu等 [ 16 ] 通过从788个影像组学特征中选择11个特征构成影像组学评分,用于预测Luminal型和非Luminal型乳腺癌,结果显示影像组学评分的AUC在训练集为0.828,在测试集为0.786。与常规超声相比,超声造影(CEUS)不仅可以反映肿瘤的形态特征,而且可以连续和动态地显示肿瘤微循环的灌注,这可以提供更多的额外信息 [ 17 ] 。研究表明,CEUS在乳腺癌中的表现与其预后因素具有一定的相关性,肿瘤微循环的可视化结构为预测乳腺癌的分子分型提供了有价值的信息 [ 18 ] 。Gong等 [ 19 ] 利用影像组学工具包和最大相关最小冗余算法提取和选择特征,构建US、CEUS和US与CEUS影像组学结合的多元Logistic回归模型,并通过五重交叉验证进行评价,结果显示US结合CEUS模型的准确性优于US模型(85.4% vs 81.3%, P < 0.01);在预测Luminal A、HER-2过表达、HR+和HER-2+的乳腺癌中,CEUS影像组学模型改善了US模型的预测性能。综上所述,超声影像组学能够较好地预测乳腺癌分子分型。

3.2. 乳腺X线摄影影像组学

乳腺X线摄影技术作为对乳腺病变早期诊断及筛查的手段之一。目前,乳腺X线摄影影像组学模型在区分乳腺肿块的良恶性研究较多 [ 20 ] [ 21 ] 。然而,某些学者进一步通过乳腺X线摄影影像组学来预测乳腺癌分子分型。Ge等 [ 22 ] 采用MaZda软件提取TNBC和非TNBC (总共343例)的X射线图像的定量特征,应用Fisher系数、分类错误概率组合平均相关(POE + ACC)和相对信息测量方法(MI)三种特征选择方法来筛选用于预测TNBC的提取的定量特征,进一步利用非线性判别分析方法对三个特征进行分析,从结果中观察到通过Fisher、(POE + ACC)和MI方法选择的三个特征用于预测TNBC的准确性分别为84.52%、88.39%和81.94%。Son等 [ 23 ] 基于数字乳腺断层合成(DBT)重建的乳房X线摄影图像中总共提取了129个影像组学特征,使用弹性网络法构建影像组学特征模型,在训练组中,头尾位和内外斜位组合模型(CC + MLO)得出TNBC的AUC为0.834,HER2为0.842,Luminal型为0.941;在验证组中,CC + MLO模型得出TNBC、HER-2型和Luminal型的AUC分别为0.838、0.556、0.645。研究表明 [ 24 ] ,与单独使用CC和MLO两个视图相比,两个视图图像的组合模型实现了最佳性能,TNBC与非TNBC的AUC分别为0.865和0.796,HER-2富集型与非HER-2富集型的AUC分别为0.784和0.748,Luminal型和非Luminal型的AUC分别为0.752和0.788。另也有研究 [ 25 ] 通过提取380例基于数字乳腺断层摄影(DBT)的病灶全瘤组学特征,经降维、筛选后,将保留的特征分别放入逻辑回归(LR)、支持向量机(SVM)及随机森林(RF) 3个不同的机器学习模型,以ROC曲线评价3种模型对乳腺癌4种分子分型的预测效能,结果显示在测试集中通过二分法预测Luminal A型、Luminal B型、HER2过表达型和TNBC的AUC分别为0.82、0.71、0.70和0.71。对比度增强能谱乳腺X射线摄影(CESM)是最近引入的乳腺X射线摄影方法,其特征特别适合于乳腺癌影像组学分析 [ 26 ] 。Zhang等 [ 27 ] 在367例经病理证实的乳腺癌患者的CESM图像中,分别从CC、MLO和组合模型的减影图像提取影像组学特征,通过DeLong检验比较AUC,显示出CC和MLO组合模型的AUC (0.90)高于单独CC和MLO的AUC (0.87和0.88),且CC和MLO组合模型灵敏度(0.97)也高于单独CC和MLO的灵敏度(0.93和0.93)。Forgia等 [ 26 ] 从52例患者被组织学证实的68个病灶中,从低能量(LE)和重组(RC) CESM图像中选择的ROI进行影像组学分析,结果表明影像组学在CESM预测乳腺癌的分子亚型方面具有重要的作用。由上述研究可知,基于DBT和CESM影像组学在预测乳腺癌分子分型具有更广阔的研究前景。

3.3. CT影像组学

尽管目前大多数指南不推荐将胸部CT作为乳腺癌诊断或早期筛查的常规检查 [ 28 ] ,但在实际诊疗活动中,由于乳腺癌患者肺、骨转移的发生率较高,尤其是临床分期较晚的患者,胸部CT仍是大多数患者的常规检查之一。张文等 [ 29 ] 对481例肿块型乳腺浸润性癌患者基于病灶三维图像提取影像组学特征,并采用LASSO Logistic回归模型进行特征降维及筛选,以建立影像组学标签,结果显示对于鉴别TNBC具有较好的预测效能,其在训练组和验证组的AUC分别为0.766和0.758,表明术前分期CT建立的影像组学标签有助于TNBC与非TNBC的鉴别。Wang等 [ 30 ] 结合6种特征筛选方法和7种机器学习分类器,建立了42个预测乳腺癌Luminal类型的模型,选择LASSO和SVM组合作为最终模型(其包括9个放射组学特征),结果显示区分Luminal型和非Luminal型的模型的AUC、准确度、灵敏度和特异性为0.842、0.773、0.818和0.773。Feng等 [ 31 ] 将100例TNBC和200例非TNBC随机分为训练组180例和验证组120例,自动提取182个影像组学特征建立模型,模型显示训练组和验证组AUC为0.881和0.851,结果表明基于术前CT的放射组学特征能够区分TNBC和非TNBC的患者(P < 0.001)。研究表明基于术前CT的影像组学在预测乳腺癌分子分型的研究报道较少,还需要进一步更多、更大规模的研究进行验证。

3.4. MRI影像组学

近年来,扩散加权成像(DWI)和动态对比增强(DCE)已被用来提供乳腺病变的功能特征,以评估准确的诊断。Li等 [ 32 ] 使用影像组学的方法来分析53名年轻女性乳腺癌的MR图像,并将放射组学数据与分子亚型相关联,结果表明TNBC型和非TNBC型的年轻女性乳腺癌的放射组学特征的T2加权成像上存在显著差异。Wang等 [ 33 ] 在DWI图像上提取了76个影像学特征,其中12个放射组学特征在TNBC和非TNBC患者之间具有统计学意义(P < 0.05)。Baysal等 [ 34 ] 基于磁共振成像表观扩散系数(ADC)影像组学的神经网络预测乳腺癌分子亚型,对221例乳腺癌患者的ADC图像进行分割,神经网络可以以高准确度预测超过1 cm3的乳腺癌的分子亚型。Xu等 [ 35 ] 通过LASSO的扩展逻辑回归算法最终确定了8个最佳对比增强磁共振成像(DCE-MRI)影像组学特征和4个临床特征(年龄、肿瘤位置、组织学分级、Ki-67和淋巴结转移),考虑单模态特征和多模态特征的融合,构建了临床模型、影像组学模型和组合模型三种多分类模型,组合模型区分乳腺癌分子亚型的ROC分析显示组合模型(训练集的AUC为0.84,测试集的AUC为0.84)优于影像组学模型(训练集的AUC为0.81,测试集的AUC为0.81)和临床模型(训练集的AUC为0.71,测试集的AUC为0.73)。Huang等 [ 36 ] 从活检前多参数MRI (包括动态对比增强T1加权图像、脂肪抑制T2加权图像和表观扩散系数图)中提取总共4198个放射组学特征建立了120个诊断模型,使用不同的分类算法和特征集划分的MRI序列和选择策略进一步预测乳腺癌的分子亚型,在TNBC和非TNBC之间、HER-2+和HER-2-之间、HR+/HER-2-和其他亚型之间的预测准确率分别为92.6%、79.0%、82.1%,说明基于多参数MRI的影像组学提供了一种有前途的方法来非侵入性地预测乳腺癌的分子亚型。Zhang等 [ 37 ] 通过95例术前行DCE-MRI检查的浸润性导管乳腺癌(IDBC)患者中,从两个中心的DCE-MRI上的瘤内区域和四个瘤周区域提取影像组学特征,构建5个影像组学模型,临床–放射学和放射组学组合模型获得了最佳性能,在训练队列中HR+和其他亚型之间、HER-2富集型和其他亚型之间、TNBC和其他亚型之间的AUC分别为0.838、0.848和0.930,说明DCE-MRI上IDBC瘤内和瘤周区域的放射组学特征有可能在术前预测HR+、HER-2富集型和TNBC分子亚型。Kovacevic等 [ 38 ] 在DCE-MRI序列中从手动分割的乳腺癌中提取总共1781个放射组学特征,模型区分Luminal型和其他亚型、Luminal B型(HER-2-)和其他亚型、Luminal B型(HER-2+)和其他亚型、HER-2+和其他亚型、TNBC和其他亚型的AUC分别为0.78、0.57、0.60、0.81、0.83,说明从DCE-MRI中提取的影像组学特征有希望用于区分乳腺癌亚型。总之,基于MRI影像组学在预测乳腺癌分子分型的研究较为成熟,在预测乳腺癌分子分型具有较好的应用价值。

3.5. PET影像组学

研究表明PET/MR能提供可靠的,与PET/CT相似的半定量诊断信息。Krajnc等 [ 39 ] 基于18F-FDG PET/CT图像的乳腺肿瘤定性的可行性,使用ML方法结合数据再处理技术,交叉验证证明了三阴性肿瘤识别模型的AUC、灵敏度、特异度和准确性分别为0.82、85%、78%和82%,说明18F-FDG PET/CT图像的预测模型结合ML有助于区分TNBC和其他亚型。Romeo等 [ 40 ] 应用于18F-FDG PET/MRI的基于ML的影像组学模型预测乳腺癌分子亚型,特别是在区分TNBC与其他亚型,基于定量参数和/或影像组学特征的不同组合建立了8个影像组学模型,其中最好模型性能的AUC、准确性、灵敏度和特异性分别为0.887、82.8%、79.7%和86%,表明应用于18F-FDG PET/MRI的基于ML的影像组学模型能够以高准确度非侵入性地区分TNBC与其他亚型。目前基于PET的影像组学主要在预测TNBC和其他亚型有一定研究,在进一步区分各个亚型之间还有待更多的研究验证。

4. 影像组学的挑战及未来发展

在精准治疗时代,乳腺癌早期分子分型对疾病管理和预后具有临床意义。影像组学是医学成像的一种定量方法,旨在通过使用人工智能进行先进的数据分析,增强临床医生可用的现有数据。来自乳腺影像学的各种已发表的研究都显示出影像组学高精度区分分子亚型,预测化疗的反应,预测生存结果。由于对整个肿瘤重复测量的可行性和基于深度学习的算法的适用性,成像生物标志物可能有助于实现更好的精准医学。此外,大多数影像组学研究大多是初步的,采用回顾性设计,样本量相对较小,重复性评估往往有问题或存在不确定型。因此,需要更大规模、高质量的前瞻性研究来验证这些初步结果。

基金项目

青海省“昆仑英才·高原名医”计划(青人才字[ 2023 ] 5号)。

文章引用

赵学波,陈鲜霞. 影像组学在预测乳腺癌分子分型的应用进展Advances in the Application of Radiomics in Predicting Molecular Typing of Breast Cancer[J]. 世界肿瘤研究, 2024, 14(01): 41-47. https://doi.org/10.12677/WJCR.2024.141007

参考文献 References Bray, F., Ferlay, J., Soerjomataram, I., et al. (2018) Global Cancer Statistics 2018: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries. CA: A Cancer Journal for Clinicians, 68, 394-424.
https://doi.org/10.3322/caac.21492
Siegel, R.L., Miller, K.D. and Jemal, A. (2019) Cancer Statistics, 2019. CA: A Cancer Journal for Clinicians, 69, 7-34.
https://doi.org/10.3322/caac.21551
Goldhirsch, A., Winer, E.P., Coates, A.S., et al. (2013) Personalizing the Treatment of Women with Early Breast Cancer: Highlights of the St Gallen International Expert Consensus on the Pri-mary Therapy of Early Breast Cancer 2013. Annals of Oncology, 24, 2206-2223.
https://doi.org/10.1093/annonc/mdt303
Britt, K.L., Cuzick, J. and Phillips, K.A. (2020) Key Steps for Effective Breast Cancer Prevention. Nature Reviews Cancer, 20, 417-436.
https://doi.org/10.1038/s41568-020-0266-x
Phung, M.T., Tin Tin, S. and Elwood, J.M. (2019) Prognostic Models for Breast Cancer: A Systematic Review. BMC Cancer, 19, Article No. 230.
https://doi.org/10.1186/s12885-019-5442-6
Conti, A., Duggento, A., Indovina, I., et al. (2021) Radiomics in Breast Cancer Classification and Prediction. Seminars in Cancer Biology, 72, 238-250.
https://doi.org/10.1016/j.semcancer.2020.04.002
Xie, T., Wang, Z., Zhao, Q., et al. (2019) Machine Learn-ing-Based Analysis of MR Multiparametric Radiomics for the Subtype Classification of Breast Cancer. Frontiers in On-cology, 9, Article No. 505.
https://doi.org/10.3389/fonc.2019.00505
Davey, M.G., Davey, M.S., Boland, M.R., et al. (2021) Radiomic Differentiation of Breast Cancer Molecular Subtypes Using Pre-Operative Breast Imaging—A Systematic Review and Meta-Analysis. European Journal of Radiology, 144, Article ID: 109996.
https://doi.org/10.1016/j.ejrad.2021.109996
Rizzo, S., Botta, F., Raimondi, S., et al. (2018) Radiomics: The Facts and the Challenges of Image Analysis. European Radiology Experimental, 2, Article No. 36.
https://doi.org/10.1186/s41747-018-0068-z
Pesapane, F., Suter, M.B., Rotili, A., et al. (2020) Will Traditional Biopsy Be Substituted by Radiomics and Liquid Biopsy for Breast Cancer Diagnosis and Characterisation? Medical On-cology, 37, Article No. 29.
https://doi.org/10.1007/s12032-020-01353-1
Lambin, P., Rios-Velazquez, E., Leijenaar, R., et al. (2012) Ra-diomics: Extracting More Information from Medical Images Using Advanced Feature Analysis. European Journal of Cancer, 48, 441-446.
https://doi.org/10.1016/j.ejca.2011.11.036
Gillies, R.J., Kinahan, P.E. and Hricak, H. (2016) Radiomics: Im-ages Are More than Pictures, They Are Data. Radiology, 278, 563-577.
https://doi.org/10.1148/radiol.2015151169
Cui, Q., Dai, L., Li, J., et al. (2020) Accuracy of CEUS-Guided Sentinel Lymph Node Biopsy in Early-Stage Breast Cancer: A Study Review and Meta-Analysis. World Journal of Sur-gical Oncology, 18, Article No. 112.
https://doi.org/10.1186/s12957-020-01890-z
许荣, 欧阳秋芳, 林晴, 等. 超声影像组学预测雌激素及孕激素受体双阴性乳腺癌[J]. 中国医学影像技术, 2023, 39(9): 1346-1349. Ferre, R., Elst, J., Senthilnathan, S., et al. (2023) Machine Learning Analysis of Breast Ultrasound to Classify Triple Negative and HER2+ Breast Cancer Sub-types. Breast Disease, 42, 59-66.
https://doi.org/10.3233/BD-220018
Wu, J., Ge, L., Jin, Y., et al. (2022) Development and Validation of an Ultrasound-Based Radiomics Nomogram for Predicting the Luminal from Non-Luminal Type in Patients with Breast Carcinoma. Frontiers in Oncology, 12, Article ID: 993466.
https://doi.org/10.3389/fonc.2022.993466
Wan, C.F., Liu, X.S., Wang, L., et al. (2018) Quantitative Con-trast-Enhanced Ultrasound Evaluation of Pathological Complete Response in Patients with Locally Advanced Breast Cancer Receiving Neoadjuvant Chemotherapy. European Journal of Radiology, 103, 118-123.
https://doi.org/10.1016/j.ejrad.2018.04.005
Zhao, Y.X., Liu, S., Hu, Y.B., et al. (2017) Diagnostic and Prog-nostic Values of Contrast-Enhanced Ultrasound in Breast Cancer: A Retrospective Study. OncoTargets and Therapy, 10, 1123-1129.
https://doi.org/10.2147/OTT.S124134
Gong, X., Li, Q., Gu, L., et al. (2023) Conventional Ultrasound and Contrast-Enhanced Ultrasound Radiomics in Breast Cancer and Molecular Subtype Diagnosis. Frontiers in Oncology, 13, Article ID: 1158736.
https://doi.org/10.3389/fonc.2023.1158736
Chen, S., Guan, X., Shu, Z., et al. (2019) A New Application of Multimodality Radiomics Improves Diagnostic Accuracy of Nonpalpable Breast Lesions in Patients with Microcalcifica-tions-Only in Mammography. Medical Science Monitor, 25, 9786-9793.
https://doi.org/10.12659/MSM.918721
万宏燕, 徐井旭, 杨瑜, 等. 基于X线摄影影像组学特征鉴别乳腺良恶性肿块的价值[J]. 医学影像学杂志, 2023, 33(5): 773-776. Ge, S., Yixing, Y., Jia, D., et al. (2022) Application of Mammography-Based Radiomics Signature for Preoperative Prediction of Triple-Negative Breast Cancer. BMC Medical Imaging, 22, Article No. 166.
https://doi.org/10.1186/s12880-022-00875-6
Son, J., Lee, S.E., Kim, E.K., et al. (2020) Prediction of Breast Cancer Molecular Subtypes Using Radiomics Signatures of Synthetic Mammography from Digital Breast Tomosynthesis. Scientific Reports, 10, Article No. 21566.
https://doi.org/10.1038/s41598-020-78681-9
Ma, W., Zhao, Y., Ji, Y., et al. (2019) Breast Cancer Molecular Subtype Prediction by Mammographic Radiomic Features. Academic Radiology, 26, 196-201.
https://doi.org/10.1016/j.acra.2018.01.023
李佳蔚, 姜婷婷, 汤振伟, 等. 数字乳腺断层摄影的影像组学对乳腺癌分子分型预测研究[J]. 肿瘤影像学, 2023, 32(1): 12-19. La Forgia, D., Fanizzi, A., Campobasso, F., et al. (2020) Radiomic Analysis in Contrast-Enhanced Spectral Mammography for Predicting Breast Cancer Histological Outcome. Diagnostics (Basel), 10, Article No. 708.
https://doi.org/10.3390/diagnostics10090708
Zhang, Y., Liu, F., Zhang, H., et al. (2021) Diagnostic Value of Radiomics Analysis in Contrast-Enhanced Spectral Mammography for Identifying Triple-Negative Breast Cancer. Fron-tiers in Oncology, 11, Article ID: 773196.
https://doi.org/10.3389/fonc.2021.773196
Cardoso, F., Kyriakides, S., Ohno, S., et al. (2019) Early Breast Cancer: ESMO Clinical Practice Guidelines for Diagnosis, Treatment and Follow-Updagger. Annals of Oncology, 30, 1194-1220.
https://doi.org/10.1093/annonc/mdz173
张文, 何兰, 范志豪, 等. 基于术前分期CT的影像组学标签预测三阴性乳腺癌[J]. 放射学实践, 2019, 34(9): 947-951. Wang, F., Wang, D., Xu, Y., et al. (2022) Potential of the Non-Contrast-Enhanced Chest CT Radiomics to Distinguish Molecular Subtypes of Breast Cancer: A Retrospective Study. Frontiers in Oncology, 12, Article ID: 848726.
https://doi.org/10.3389/fonc.2022.848726
Feng, Q., Hu, Q., Liu, Y., et al. (2020) Diagnosis of Triple Nega-tive Breast Cancer Based on Radiomics Signatures Extracted from Preoperative Contrast-Enhanced Chest Computed Tomography. BMC Cancer, 20, Article No. 579.
https://doi.org/10.1186/s12885-020-07053-3
Li, Q., Dormer, J., Daryani, P., et al. (2019) Radiomics Analysis of MRI for Predicting Molecular Subtypes of Breast Cancer in Young Women. Proceedings of SPIE—The International Society for Optical Engineering, Vol. 10950, 1095044.
https://doi.org/10.1117/12.2512056
Wang, Q., Mao, N., Liu, M., et al. (2021) Radiomic Analysis on Magnetic Resonance Diffusion Weighted Image in Distinguishing Triple-Negative Breast Cancer from Other Subtypes: A Feasibil-ity Study. Clinical Imaging, 72, 136-141.
https://doi.org/10.1016/j.clinimag.2020.11.024
Baysal, B., Baysal, H., Eser, M.B., et al. (2022) Radiomics Features Based on MRI-ADC Maps of Patients with Breast Cancer: Relationship with Lesion Size, Features Stability, and Model Accuracy. Medeniyet Medical Journal, 37, 277-288.
https://doi.org/10.4274/MMJ.galenos.2022.70094
Xu, A., Chu, X., Zhang, S., et al. (2022) Prediction Breast Molecular Typing of Invasive Ductal Carcinoma Based on Dynamic Contrast Enhancement Magnetic Resonance Imaging Radiomics Characteristics: A Feasibility Study. Frontiers in Oncology, 12, Article ID: 799232.
https://doi.org/10.3389/fonc.2022.799232
Huang, Y., Wei, L., Hu, Y., et al. (2021) Multi-Parametric MRI-Based Radiomics Models for Predicting Molecular Subtype and Androgen Receptor Expression in Breast Cancer. Frontiers in Oncology, 11, Article ID: 706733.
https://doi.org/10.3389/fonc.2021.706733
Zhang, S., Wang, X., Yang, Z., et al. (2022) Intra- and Peritumoral Radiomics Model Based on Early DCE-MRI for Preoperative Prediction of Molecular Subtypes in Invasive Ductal Breast Carcinoma: A Multitask Machine Learning Study. Frontiers in Oncology, 12, Article ID: 905551.
https://doi.org/10.3389/fonc.2022.905551
Kovacevic, L., Stajduhar, A., Stemberger, K., et al. (2023) Breast Cancer Surrogate Subtype Classification Using Pretreatment Multi-Phase Dynamic Contrast-Enhanced Magnetic Reso-nance Imaging Radiomics: A Retrospective Single-Center Study. Journal of Personalized Medicine, 13, Article No. 1150.
https://doi.org/10.3390/jpm13071150
Krajnc, D., Papp, L., Nakuz, T.S., et al. (2021) Breast Tumor Charac-terization Using [(18)F]FDG-PET/CT Imaging Combined with Data Preprocessing and Radiomics. Cancers (Basel), 13, Article No. 1249.
https://doi.org/10.3390/cancers13061249
Romeo, V., Kapetas, P., Clauser, P., et al. (2022) A Simultaneous Multiparametric (18)F-FDG PET/MRI Radiomics Model for the Diagnosis of Triple Negative Breast Cancer. Cancers (Basel), 14, Article No. 3944.
https://doi.org/10.3390/cancers14163944
Baidu
map