CN110415206A - 一种识别肺腺癌浸润分型的方法 - Google Patents

一种识别肺腺癌浸润分型的方法 Download PDF

Info

Publication number
CN110415206A
CN110415206A CN201910275152.5A CN201910275152A CN110415206A CN 110415206 A CN110415206 A CN 110415206A CN 201910275152 A CN201910275152 A CN 201910275152A CN 110415206 A CN110415206 A CN 110415206A
Authority
CN
China
Prior art keywords
tubercle
reality
type
value
major diameter
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201910275152.5A
Other languages
English (en)
Other versions
CN110415206B (zh
Inventor
杨柳
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Dunlu Biomedical Technology Co Ltd
Original Assignee
Shanghai Dunlu Biomedical Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shanghai Dunlu Biomedical Technology Co Ltd filed Critical Shanghai Dunlu Biomedical Technology Co Ltd
Priority to CN201910275152.5A priority Critical patent/CN110415206B/zh
Publication of CN110415206A publication Critical patent/CN110415206A/zh
Application granted granted Critical
Publication of CN110415206B publication Critical patent/CN110415206B/zh
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/0002Inspection of images, e.g. flaw detection
    • G06T7/0012Biomedical image inspection
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/60Analysis of geometric attributes
    • G06T7/62Analysis of geometric attributes of area, perimeter, diameter or volume
    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H30/00ICT specially adapted for the handling or processing of medical images
    • G16H30/40ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/10Image acquisition modality
    • G06T2207/10072Tomographic images
    • G06T2207/10081Computed x-ray tomography [CT]
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/30Subject of image; Context of image processing
    • G06T2207/30004Biomedical image processing
    • G06T2207/30061Lung
    • G06T2207/30064Lung nodule
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/30Subject of image; Context of image processing
    • G06T2207/30004Biomedical image processing
    • G06T2207/30096Tumor; Lesion

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Medical Informatics (AREA)
  • Radiology & Medical Imaging (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Quality & Reliability (AREA)
  • Geometry (AREA)
  • Epidemiology (AREA)
  • Primary Health Care (AREA)
  • Public Health (AREA)
  • Apparatus For Radiation Diagnosis (AREA)

Abstract

本发明公开一种识别肺腺癌浸润分型的方法。采用以下影像学特征参数汇分析:至少包括混合密度磨玻璃结节实性区域CT值、结节长径、胸膜凹陷征、边缘类型、支气管充气征、血管集束征等;优选组合包括:混合密度磨玻璃结节实性区域CT值,混合密度磨玻璃结节磨玻璃影区域CT值,结节长径,实性长径,结节类型,边缘类型,实性占比类型,结节形状,支气管充气征,胸膜凹陷征,空泡征,血管集束征,结节与肺界面清晰类型,胸膜侵犯等。加上年龄,共计15个参数的多项式组合,构成“预测因子”,“预测因子”到达阈值与否,评估肺腺癌浸润或侵袭属性,尤其预测是否为浸润性分型。

Description

一种识别肺腺癌浸润分型的方法
技术领域
本专利涉及一种肺部肿瘤分型或浸润属性的识别预测方法,尤其涉及一种通过影像学特征预测肺腺癌浸润分型的方法。
背景技术
肺癌是全世界发病率和死亡率最高的恶性肿瘤之一,肺癌亚型中,非小细胞肺癌约占85%,而非小细胞肺癌又以肺腺癌占据绝大多数。非小细胞肺癌分为原位腺癌(adenocarcinoma in situ,AIS)、微浸润腺癌(minimally invasive adenocarcinoma,MIA)及浸润性腺癌(invasive adenocarcinoma,IAC)。MIA和IAC亚型具有更高的浸润性,恶性程度更高,预后更差。因此,及早预测识别浸润性分型,有利于提早控制和治疗,挽救肿瘤扩散转移造成的生命危害。
发明内容
本发明目的在于提供一种联合多维度CT影像学特征参数,预测肺腺癌浸润亚型的方法。
为了实现上述目的,本发明采用了如下技术方案 :
采用以下参数汇总计算:混合密度磨玻璃结节实性区域CT值,混合密度磨玻璃结节磨玻璃影区域CT值,结节长径,实性长径,结节类型,边缘类型,实性占比类型,结节形状,支气管充气征,胸膜凹陷征,空泡征,血管集束征,结节与肺界面清晰类型,胸膜侵犯等。除CT特征外,加入患者年龄参数。
本专利提供一个新变量预测因子,由以上参数的多项式组成,多项式首选为一次线性多项式(可包括高次方多项式),预测因子至少包括混合密度磨玻璃结节实性区域CT值、结节长径、胸膜凹陷征、边缘类型、支气管充气征、血管集束征、年龄等7个变量,最优选为至少包含以上15个变量。其中,预测因子与混合密度磨玻璃结节实性区域CT值、混合密度磨玻璃结节磨玻璃影区域CT值、结节长径、实性长径正相关,与结节类型的混合磨玻璃密度结节、边缘类型的分页、结节形状的不规则、支气管充气征的实性区域分布、胸膜凹陷征存在、以及年龄正相关,与胸膜侵犯存在、界面的清晰和血管集束征负相关。
本专利通过“预测因子”的数值,预测肺腺癌浸润亚型,数值越高,越可能为高浸润性亚型,即MIA型或IAC型,通过受试者工作曲线(ROC)曲线下面积优化获取预测IAC型的预测因子阈值及该阈值的灵敏度和特异度。
具体实施方案
以下对本发明的优选实施例进行说明,应当理解,此处所描述的优选实施例仅用于说明和解释本发明,并不用于限定本发明。
采用薄层CT获取疑似肺腺癌结节。通过医师或由医师框定感兴趣区域后机器识别图像,获取以下14个CT特征参数:混合密度磨玻璃结节实性区域CT值,混合密度磨玻璃结节磨玻璃影区域CT值,结节长径,实性长径,结节类型,边缘类型,实性占比类型,结节形状,支气管充气征,胸膜凹陷征,空泡征,血管集束征,结节与肺界面清晰类型,胸膜侵犯。同时录入患者年龄。
进一步具体地,各关键参数数据类型及编码方式为:
混合密度磨玻璃结节实性区域CT值和混合密度磨玻璃结节磨玻璃影区域CT值为数值变量,数值为CT信号值,一般为负数。
结节长径和实性长径为数值变量,数值单位为毫米(mm)。
结节类型为分类变量:1=纯磨玻璃密度结节,2=混合磨玻璃密度结节。
边缘类型为分类变量:1=光滑边缘,2=分叶边缘,3=多毛刺边缘。
实性占比类型为分类变量:1=实性区域低于磨玻璃区域,2=实性区域高于磨玻璃区域。
结节形状为分类变量:1=近似圆形(或椭圆),2=不规则形。
支气管充气征为分类变量:1=无充气征,2=主要为磨玻璃区域充气征,3=主要为实性区域充气征。
胸膜凹陷征为分类变量:0=否,1=是。
空泡征为分类变量:0=否,1=是。
血管集束征为分类变量:0=否,1=是。
结节与肺界面清晰类型为分类变量:1=清晰,2=不清晰。
胸膜侵犯为分类变量:0=否,1=是。
此外,受试者年龄为正整数,单位为岁。
更进一步,预测算法如下:
构建预测因子,预测因子由以上诸变量的多项式构成,且结节分类、形状、实性占比、支气管充气征、空泡征、胸膜凹陷征、实性区域CT值、GGO区CT值、长径和年龄系数为正或0,胸膜侵犯、边缘类型、结节与肺界面清晰类型和血管集束征系数为负或0,优选多项式为线性1次多项式。
以下为优选计算公式:
预测因子=结节分类+形状+6*实性占比类型+支气管充气征+3*空泡征+胸膜凹陷征+0.005*实性区域CT值+0.005*GGO区CT值+0.4*长径+0.1*实性长径+0.1*年龄-胸膜侵犯-边缘类型-4*结节与肺界面清晰类型-2*血管集束征。
该计算公式特征为:
胸膜侵犯、边缘类型、结节与肺界面清晰类型和血管集束征系数为负或0,结节分类、形状、实性占比类型、支气管充气征、空泡征、胸膜凹陷征、实性区域CT值、GGO区CT值、长径和年龄系数为正或0,结节分类、形状、实性占比类型、支气管充气征等分类变量的系数(绝对值)约为实性区域CT值和GGO区CT值系数的100-2000倍,约为结节长径和实性长径的2至100倍,约为年龄的5-100倍;在分类变量中,实性占比类型、空泡征和结节与肺界面清晰类型具有相对更高的系数,为其他分类变量系数的2-10倍。
当肺腺癌浸润属性分类编码为1-3时,即:1=AIS,2= MIA,3= IAC,采用280名肺腺癌患者数据,用以上预测因子预测浸润性分类,ROC曲线下面积高达0.992(0.986-0.998),优选公式下针对IAC预测,预测因子Cutoff阈值为17.98,此时预警IAC灵敏度高达92.5%,准确度高达98.7%。更进一步,当结合胸片图像识别应用,医师框选结节所在区域后,系统自动计算以上15个指标结果,利用本优选公式,可快速输出IAC分型的预警结论。

Claims (5)

1.一种用于识别预测肺腺癌浸润属性分型的影像学特征和年龄组合算法;
其中,影像学特征至少包括:混合密度磨玻璃结节实性区域CT值、结节长径、胸膜凹陷征、边缘类型、支气管充气征、血管集束征等特征。
2.一种用于识别预测肺腺癌浸润属性分型的影像学特征和年龄组合算法;
其中,影像学特征优选组合包括:混合密度磨玻璃结节实性区域CT值,混合密度磨玻璃结节磨玻璃影区域CT值,结节长径,实性长径,结节类型,边缘类型,实性占比类型,结节形状,支气管充气征,胸膜凹陷征,空泡征,血管集束征,结节与肺界面清晰类型,胸膜侵犯等;
加上年龄,共计15个参数的多项式组合。
3.根据权利要求2所述的组合算法,多项式首选为一次线性多项式。
4.根据权利要求2所述的组合算法,算法结果(称为预测因子)与混合密度磨玻璃结节实性区域CT值、混合密度磨玻璃结节磨玻璃影区域CT值、结节长径、实性长径正相关,与结节类型的混合磨玻璃密度结节、边缘类型的分页、结节形状的不规则、支气管充气征的实性区域分布、胸膜凹陷征存在、以及年龄正相关,与胸膜侵犯存在、界面的清晰和血管集束征负相关。
5.根据权利要求4所述的组合算法,算法结果(称为预测因子),支气管充气征等分类变量的系数(绝对值)约为实性区域CT值和GGO区CT值系数的100-2000倍,约为结节长径和实性长径的2至100倍,约为年龄的5-100倍;在分类变量中,实性占比类型、空泡征和结节与肺界面清晰类型具有相对更高的系数,为其他分类变量系数的2-10倍。
CN201910275152.5A 2019-04-08 2019-04-08 一种识别肺腺癌浸润分型的方法 Active CN110415206B (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910275152.5A CN110415206B (zh) 2019-04-08 2019-04-08 一种识别肺腺癌浸润分型的方法

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910275152.5A CN110415206B (zh) 2019-04-08 2019-04-08 一种识别肺腺癌浸润分型的方法

Publications (2)

Publication Number Publication Date
CN110415206A true CN110415206A (zh) 2019-11-05
CN110415206B CN110415206B (zh) 2023-12-15

Family

ID=68357589

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910275152.5A Active CN110415206B (zh) 2019-04-08 2019-04-08 一种识别肺腺癌浸润分型的方法

Country Status (1)

Country Link
CN (1) CN110415206B (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113706533A (zh) * 2021-10-28 2021-11-26 武汉大学 图像处理方法、装置、计算机设备及存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105726052A (zh) * 2016-01-28 2016-07-06 上海市肺科医院 一种获取浸润性病灶概率的方法及系统
CN106780460A (zh) * 2016-12-13 2017-05-31 杭州健培科技有限公司 一种用于胸部ct影像的肺结节自动检测系统
CN107103187A (zh) * 2017-04-10 2017-08-29 四川省肿瘤医院 基于深度学习的肺结节检测分级与管理的方法及系统
CN107292114A (zh) * 2017-06-28 2017-10-24 中日友好医院 一种孤立性肺结节恶性概率预测模型的建立方法
CN108280826A (zh) * 2018-01-23 2018-07-13 北京易智能科技有限公司 一种ct肺亚实性结节特征提取及检测方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105726052A (zh) * 2016-01-28 2016-07-06 上海市肺科医院 一种获取浸润性病灶概率的方法及系统
CN106780460A (zh) * 2016-12-13 2017-05-31 杭州健培科技有限公司 一种用于胸部ct影像的肺结节自动检测系统
CN107103187A (zh) * 2017-04-10 2017-08-29 四川省肿瘤医院 基于深度学习的肺结节检测分级与管理的方法及系统
CN107292114A (zh) * 2017-06-28 2017-10-24 中日友好医院 一种孤立性肺结节恶性概率预测模型的建立方法
CN108280826A (zh) * 2018-01-23 2018-07-13 北京易智能科技有限公司 一种ct肺亚实性结节特征提取及检测方法

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113706533A (zh) * 2021-10-28 2021-11-26 武汉大学 图像处理方法、装置、计算机设备及存储介质
CN113706533B (zh) * 2021-10-28 2022-02-08 武汉大学 图像处理方法、装置、计算机设备及存储介质

Also Published As

Publication number Publication date
CN110415206B (zh) 2023-12-15

Similar Documents

Publication Publication Date Title
Peng et al. A radiomics nomogram for preoperative prediction of microvascular invasion risk in hepatitis B virus-related hepatocellular carcinoma
Lin et al. A Delta-radiomics model for preoperative evaluation of Neoadjuvant chemotherapy response in high-grade osteosarcoma
Liang et al. Predicting malignancy in thyroid nodules: radiomics score versus 2017 American College of Radiology Thyroid Imaging, Reporting and Data System
Liu et al. Preoperative diagnosis of malignant pulmonary nodules in lung cancer screening with a radiomics nomogram
Al-Tarawneh Lung cancer detection using image processing techniques
Xian et al. Fully automatic segmentation of breast ultrasound images based on breast characteristics in space and frequency domains
Weng et al. A radiomics model for determining the invasiveness of solitary pulmonary nodules that manifest as part-solid nodules
Adachi et al. Multi‐institutional dose‐segmented dosiomic analysis for predicting radiation pneumonitis after lung stereotactic body radiation therapy
Patil et al. Cancer cells detection using digital image processing methods
Van Engeland et al. Combining two mammographic projections in a computer aided mass detection method
Jiang et al. Assessing EGFR gene mutation status in non-small cell lung cancer with imaging features from PET/CT
Wang et al. Joint use of the radiomics method and frozen sections should be considered in the prediction of the final classification of peripheral lung adenocarcinoma manifesting as ground-glass nodules
Feng et al. Differentiating minimally invasive and invasive adenocarcinomas in patients with solitary sub-solid pulmonary nodules with a radiomics nomogram
CN110415206A (zh) 一种识别肺腺癌浸润分型的方法
Vieira et al. Multi-pathology detection and lesion localization in WCE videos by using the instance segmentation approach
Kim et al. Evaluation of semi-automatic segmentation methods for persistent ground glass nodules on thin-section CT scans
Zhu et al. Shadow removal with background difference method based on shadow position and edges attributes
Li et al. Discovery and validation of a CT‐based radiomic signature for preoperative prediction of early recurrence in hypopharyngeal carcinoma
Zheng et al. 3D gray density coding feature for benign‐malignant pulmonary nodule classification on chest CT
Meng et al. Preoperative microvascular invasion prediction to assist in surgical plan for single hepatocellular carcinoma: better together with radiomics
Wu et al. Reversible contrast enhancement for medical images with background segmentation
Qi et al. Comparison of diagnostic performance of spread through airspaces of lung adenocarcinoma based on morphological analysis and perinodular and intranodular radiomic features on chest CT images
CN114677511A (zh) 一种残差ECA通道注意力UNet结合TRW-S的肺结节分割方法
Sun et al. Computed tomography radiomics in growth prediction of pulmonary ground-glass nodules
Gao et al. Artificial-intelligence-based computed tomography histogram analysis predicting tumor invasiveness of lung adenocarcinomas manifesting as radiological part-solid nodules

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant