CT形态特征、性别联合放射组学鉴别腮腺多形性腺瘤与腺淋巴瘤

doi:10.7518/gjkq.2023090

摘要/Abstract

摘要：

目的探讨基于CT平扫的形态特征、性别联合放射组学模型对腮腺多形性腺瘤（PA）与腺淋巴瘤（AL）的鉴别应用。方法回顾性分析经病理证实的56例PA与49例AL的形态特征，观察分析其形状、边界、囊变、多发以及部位，提取并分析CT平扫图像中肿瘤的6种放射组学特征，包括灰度直方图（HA）、绝对梯度（AG）、灰度共生矩阵（GLCM）、自回归模型（AR）、灰度游程矩阵（GLRLM）和小波变换（WT），对两组间有统计学意义的放射组学特征参数进行筛选，分别以径向基函数核（RBFK）、多项式核（PK）和线性核（LK）对筛选后的放射组学特征建立支持向量机（SVM）分类模型并联合性别及形态特征建立联合模型，运用受试者工作特征曲线（ROC）评价诊断效能。结果最终从287个放射组学特征参数中筛出12个特征建立分类模型，以RBFK为核的分类模型诊断效能最高，对应的灵敏度、特异度、准确率及曲线下面积（AUC）分别为90.2%、82.5%、89.6%及0.883；PA以女性多见，AL以男性多见；与PA相比，AL更易多发及囊变（P<0.05）；而2组间边界是否清楚、形状是否规则以及肿瘤的部位无明显差异（P>0.05）。放射组学特征联合性别及形态特征（多发与囊变）建立以 RBFK为核的联合模型的灵敏度、特异度、准确率及 AUC 分别为 95.1%、87.6%、92.8%及 0.963。结论基于性别及CT形态特征联合放射组学特征建立的联合模型能够在术前对PA与AL进行有效鉴别。

关键词: 腮腺, 多形性腺瘤, 腺淋巴瘤, 形态学, 放射组学, CT

Abstract:

Objective This study aimed to explore the differential application of pleomorphic adenoma (PA) and adenolymphoma (AL) in parotid gland on the basis of the morphological characteristics of CT plain scan and gender combined with radiomic model. Methods The morphological features of 56 cases of PA and 49 cases of AL confirmed by pathology were analyzed retrospectively. The morphological characteristics of shape, boundary, cystic degeneration, multiple occurrence, and location of the tumors were observed and analyzed. Six kinds of radiologic features of tumors in CT plain scan images were extracted and analyzed, including gray histogram, absolute gradient, gray-level co-occurrence matrix, autoregressive model, gray-level run length matrix, and wavelet transform. They were used to screen the statistically significant radiomic characteristic parameters between groups. The radial basis function kernel (RBFK), polynomial kernel (PK), and linear kernel (LK) of the support vector machine (SVM) classification model were established for the screened radiomic features. A joint model combined with gender and morphological features was also established. The receiver operator characteristic curve was used to evaluate the diagnostic efficiency of classification models and joint model. Results A total of 12 features were screened out from 287 radiomic feature parameters to establish classification models. The classification model with RBFK as core had the highest diagnostic efficiency, and the corresponding sensitivity, specificity, accuracy, and area under the curve (AUC) were 90.2%, 82.5%, 89.6%, and 0.883, respectively. PA was more common in women, whereas AL was more common in men. AL was more prone to multiple and cystic degeneration than PA (P<0.05). No significant difference was observed between the two groups in terms of boundary, shape, and the location of the tumor (P>0.05). The sensitivity, specificity, accuracy, and AUC of the combined model based on the radiomic characteristics of RBFK, gender, and morphological characteristics (multiple and cystic changes) were 95.1%, 87.6%, 92.8%, and 0.963, respectively. Conclusion The combination of morphological characteristics based on radiomics characteristics, gender and morphological characteristics could effectively distinguish PA and AL before operation.

Key words: parotid gland, pleomorphic adenoma, adenolymphoma, morphology, radiomics, CT

中图分类号:

R 782

于冬洋,李绍东,韩雷,单奔,柳勇,赵正宇. CT形态特征、性别联合放射组学鉴别腮腺多形性腺瘤与腺淋巴瘤[J]. 国际口腔医学杂志, 2023, 50(5): 506-513.

Yu Dongyang,Li Shaodong,Han Lei,Shan Ben,Liu Yong,Zhao Zhengyu. Differentiation of pleomorphic adenoma and adenolymphoma of parotid gland by CT morphological features, gender and radiomics[J]. Int J Stomatol, 2023, 50(5): 506-513.

图/表 7

表 1

图1

表 2

图2

图3

表 3

图4

参考文献 40

1	Assili S, Fathi Kazerooni A, Aghaghazvini L, et al. Dynamic contrast magnetic resonance imaging (DCE-MRI) and diffusion weighted MR imaging (DWI) for differentiation between benign and malignant salivary gland tumors[J]. J Biomed Phys Eng, 2015, 5(4): 157-168.
2	Maahs GS, Oppermann Pde O, Maahs LG, et al. Parotid gland tumors: a retrospective study of 154 patients[J]. Braz J Otorhinolaryngol, 2015, 81(3): 301-306.
3	Ziółkowska M, Bień S, Okła S, et al. Epidemiological and clinical characteristics of 705 salivary glands neoplasms[J]. Otolaryngol Pol, 2013, 67(3): 154-163.
4	Comoglu S, Ozturk E, Celik M, et al. Comprehensive analysis of parotid mass: a retrospective study of 369 cases[J]. Auris Nasus Larynx, 2018, 45(2): 320-327.
5	Noel L, Medford S, Islam S, et al. Epidemiology of salivary gland tumours in an Eastern Caribbean nation: a retrospective study[J]. Ann Med Surg, 2018, 36: 148-151.
6	雷晓雯, 程敬亮, 冉云彩. ADC全域直方图分析对腮腺多形性腺瘤和腺淋巴瘤的鉴别诊断价值[J]. 放射学实践, 2020, 35(8): 1005-1008.
	Lei XW, Cheng JL, Ran YC. The value of ADC global histogram analysis in the differential diagnosis of pleomorphic adenoma and lymphoma of the parotid gland[J]. Pract Radiol, 2020, 35 (8): 1005-1008.
7	Qian W, Xu XQ, Zhu LN, et al. Preliminary study of using diffusion kurtosis imaging for characteri-zing parotid gland tumors[J]. Acta Radiol, 2019, 60(7): 887-894.
8	Valstar MH, Mast H, Ten Hove I, et al. Malignant transformation of salivary gland pleomorphic adenoma: proof of principle[J]. J Pathol Clin Res, 2021, 7(5): 432-437.
9	Rooker SA, van Abel KM, Yin LX, et al. Risk factors for subsequent recurrence after surgical treatment of recurrent pleomorphic adenoma of the parotid gland[J]. Head Neck, 2021, 43(4): 1088-1096.
10	Gao M, Hao Y, Huang MX, et al. Salivary gland tumours in a northern Chinese population: a 50-year retrospective study of 7 190 cases[J]. Int J Oral Ma-xillofac Surg, 2017, 46(3): 343-349.
11	李炳雨, 唐祖南, 胡耒豪, 等. 腮腺微小肿瘤的临床病理研究[J]. 北京大学学报(医学版), 2022, 54(2): 335-339.
	Li BY, Tang ZN, Hu LH, et al. Clinicopathological study of parotid gland small tumors[J] J Peking Uni (Med Ed), 2022, 54(2): 335-339.
12	金朋, 蒋翠萍, 陈松旺, 等. 腮腺多形性腺瘤和沃辛瘤的超声特征对比分析[J]. 肿瘤影像学, 2022, 31(2): 174-180.
	Jin P, Jiang CP, Chen SW, et al. Comparative analysis of ultrasound features between pleomorphic adenoma of the parotid gland and Vosin’s tumor[J]. Tumor Imag, 2022, 31(2): 174-180.
13	于冬洋, 单奔, 柳勇, 等. 3.0T磁共振DWI及动态增强扫描在腮腺常见肿瘤中的诊断价值[J]. 中华全科医师杂志, 2018(4): 303-306.
	Yu DY, Shan B, Liu Y, et al. The diagnostic value of 3.0T magnetic resonance DWI and dynamic contrast-enhanced scanning in common parotid gland tumors[J]. Chin J General Pract, 2018(4): 303-306.
14	夏飞飞, 秦文娟, 冯佳, 等. 超声灰度直方图对多形性腺瘤与腺淋巴瘤鉴别诊断效能的初步研究[J]. 国际口腔医学杂志, 2022, 49(1): 60-65.
	Xia FF, Qin WJ, Feng J, et al. Preliminary study on the differential diagnostic efficacy of ultrasound grayscale histogram in pleomorphic adenoma and adenolymphoma[J]. Int J Stomatol, 2022, 49(1): 60-65.
15	Psychogios G. Ultrasonography techniques in the preoperative diagnosis of parotid gland tumors-an updated review of the literature[J]. Med Ultrason, 2021, 23(1): 122-123.
16	张丹丹, 尤超, 顾雅佳. 基于动态增强 MRI 影像组学参数的观察者一致性研究[J]. 肿瘤影像学, 2021, 30(4): 252-256.
	Zhang DD, You C, Gu YJ. Observer consistency study based on dynamic enhanced MRI imaging omics parameters[J]. Tumor Imag, 2021, 30(4): 252-256.
17	余先超, 孙宇凤, 李鹏, 等. 影像组学在腮腺多形性腺瘤与腺淋巴瘤鉴别诊断中的应用[J]. 现代肿瘤医学, 2021, 29(5): 837-840.
	Yu XC, Sun YF, Li P, et al. The application of ima-ging omics in the differential diagnosis of pleomorphic adenoma and lymphoma of the parotid gland[J]. Modern Oncol Med, 2021, 29(5): 837-840.
18	Geistlinger L, Oh S, Ramos M, et al. Multiomic analysis of subtype evolution and heterogeneity in high-grade serous ovarian carcinoma[J]. Cancer Res, 2020, 80(20): 4335-4345.
19	Castellano G, Bonilha L, Li LM, et al. Texture analysis of medical images[J]. Clin Radiol, 2004, 59(12): 1061-1069.
20	Pressney I, Khoo M, Endozo R, et al. Pilot study to differentiate lipoma from atypical lipomatous tumour/well-differentiated liposarcoma using MR radiomics-based texture analysis[J]. Skeletal Radiol, 2020, 49(11): 1719-1729.
21	Yuan R, Shi SY, Chen JH, et al. Radiomics in Ra_yPlus: a web-based tool for texture analysis in medical images[J]. J Digit Imaging, 2019, 32(2): 269-275.
22	Wang S, Meng M, Zhang X, et al. Texture analysis of diffusion weighted imaging for the evaluation of glioma heterogeneity based on different regions of interest[J]. Oncol Lett, 2018, 15(5): 7297-7304.
23	Suh HB, Choi YS, Bae S, et al. Primary central nervous system lymphoma and atypical glioblastoma: differentiation using radiomics approach[J]. Eur Radiol, 2018, 28(9): 3832-3839.
24	Jung YJ, Han MR, Ha EJ, et al. Differentiation of salivary gland tumors through tumor heterogeneity: a comparison between pleomorphic adenoma and Warthin tumor using CT texture analysis[J]. Neuroradiology, 2020, 62(11): 1451-1458.
25	Goyal A, Razik A, Kandasamy D, et al. Role of MR texture analysis in histological subtyping and gra-ding of renal cell carcinoma: a preliminary study[J]. Abdom Radiol (NY), 2019, 44(10): 3336-3349.
26	Huang SY, Franc BL, Harnish RJ, et al. Exploration of PET and MRI radiomic features for decoding breast cancer phenotypes and prognosis[J]. NPJ Breast Cancer, 2018, 4: 24.
27	Guo Y, Kong QC, Zhu YQ, et al. Whole-lesion histogram analysis of the apparent diffusion coefficient: evaluation of the correlation with subtypes of mucinous breast carcinoma[J]. J Magn Reson Ima-ging, 2018, 47(2): 391-400.
28	王友红, 柳勇, 韩婷婷, 等. 基于MR对比增强T1WI纹理分析鉴别泪腺淋巴瘤与泪腺炎性假瘤[J]. 中国医学影像技术, 2022, 38(6): 837-841.
	Wang YH, Liu Y, Han TT, et al. Differentiation of lacrimal gland lymphoma and lacrimal gland inflammatory pseudotumor based on contrast-enhanced T1WI texture analysis using MR imaging[J]. Chin Med Imag Technol, 2022, 38(6): 837-841.
29	Park M, Kim J, Choi YS, et al. Application of dynamic contrast-enhanced MRI parameters for diffe-rentiating squamous cell carcinoma and malignant lymphoma of the oropharynx[J]. AJR Am J Roentgenol, 2016, 206(2): 401-407.
30	王安然. 基于CT影像组学的腮腺良恶性肿瘤分类方法研究[D]. 重庆: 重庆医科大学, 2021.
	Wang AR. Research on the classification method of benign and malignant parotid gland tumors based on CT imaging omics[D]. Chongqing: Chongqing Me-dical University, 2021.
31	Mahato S, Goyal N, Ram D, et al. Detection of depression and scaling of severity using six channel EEG data[J]. J Med Syst, 2020, 44(7): 118.
32	Cai J, Liu H, Yuan H, et al. A radiomics study to predict invasive pulmonary adenocarcinoma appearing as pure ground-glass nodules[J]. Clin Radiol, 2021, 76(2): 143-151.
33	Gabelloni M, Faggioni L, Attanasio S, et al. Can magnetic resonance radiomics analysis discriminate parotid gland tumors? A pilot study[J]. Diagnostics (Basel), 2020, 10(11): 900.
34	Hussain L, Awan IA, Aziz W, et al. Detecting congestive heart failure by extracting multimodal features and employing machine learning techniques[J]. Biomed Res Int, 2020, 2020: 4281243.
35	Shao S, Mao N, Liu WJ, et al. Epithelial salivary gland tumors: utility of radiomics analysis based on diffusion-weighted imaging for differentiation of benign from malignant tumors[J]. J Xray Sci Technol, 2020, 28(4): 799-808.
36	吴梦苇, 魏培英, 邵畅, 等. MRI多参数联合对腮腺腺淋巴瘤与多形性腺瘤的鉴别诊断价值[J]. 中国临床医学影像杂志, 2022, 33(3): 162-165, 171.
	Wu MW, Wei PY, Shao C, et al. The value of MRI multi parameter combination in the differential diagnosis of parotid gland lymphoma and pleomorphic adenoma[J]. Chin J Clin Med Imag, 2022, 33(3): 162-165, 171.
37	王琴, 黄东琼, 于冬洋, 等. 放射组学模型鉴别腮腺多形性腺瘤与沃辛瘤[J]. 肿瘤影像学, 2021, 30(6): 499-503.
	Wang Q, Huang DQ, Yu DY, et al. Radioomics mo-del for distinguishing pleomorphic adenoma of the parotid gland from Vosin’s tumor[J]. Tumor Imag, 2021, 30(6): 499-503.
38	林杨, 吴丽芳, 陈懿. 腮腺混合瘤与腺淋巴瘤的磁共振成像表现对比分析[J]. 肿瘤影像学, 2020, 29(3): 319-323.
	Lin Y, Wu LF, Chen Y. Comparative analysis of magnetic resonance imaging manifestations between parotid mixed tumor and adenolymphoma[J]. Tumor Imag, 2020, 29(3): 319-323.
39	史灵雪. 多参数MR影像组学特征对腮腺多形性腺瘤及腺淋巴瘤诊断价值的研究[D]. 吉林: 吉林大学, 2021.
	Shi LX. Study on the diagnostic value of multi parameter MR imaging omics features for parotid pleomorphic adenoma and adenolymphoma[D]. Jilin: Jilin University, 2021.
40	郭作梁, 陈晓华, 马兴灿, 等. 腮腺多形性腺瘤与腺淋巴瘤的CT影像特征及对比分析[J]. 心电图杂志(电子版), 2019, 8(1): 28-29.
	Guo ZL, Chen XH, Ma XC, et al. CT imaging characteristics and comparative analysis of pleomorphic adenoma and lymphoma of the parotid gland[J]. J Electrocardiogram (Electro Ed), 2019, 8(1): 28-29.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

患者及病灶特征	PA组（n=56）	AL组（n=49）	t值或χ²值	P值
年龄	47.8±15.1	53.6±15.7	-1.914	0.058
性别（男/女）	14/42	38/11	28.871	0.000
多发（有/无）	12/44	21/28	5.568	0.018
病灶数（个）	66	75
囊变（有/无）	16/50	31/44	4.615	0.032
边界（清晰/不清晰）	59/7	71/4	1.357	0.244
部位（浅叶/非浅叶）	52/14	64/11	1.031	0.310
形状（规则/不规则）	48/18	61/14	1.482	0.223

组学特征参数	PA组（n=66）	AL组（n=75）	P值
S（2，0）Correlat	18.36（12.62，36.00）	29.00（22.30，41.02）	0.022
Pere.90%	119.00（89.56，137.90）	59.07（47.90，76.80）	<0.001
45dgr_Fraction	0.72（0.51，0.81）	0.57（0.49，0.73）	0.009
Horzl_GLevNonU	1767.81（956.55，1987.81）	1250.73（951.09，1681.70）	0.037
S（4，4）SumVarnc	597.76（509.49，821.29）	326.08（299.70，422.50）	0.028
GrSkewness	6.92（5.41，7.35）	5.38（4.02，5.99）	0.006
Teta4	1.81（1.02，2.52）	0.93（0.79，1.05）	<0.001
135dr_GLevNonU	0.76（0.60，0.85）	0.62（0.52，0.69）	0.015
S（5，5）SumOfSqs	0.41（0.35，0.49）	0.33（0.29，0.40）	0.019
Horzl_ShrtREmp	0.66（0.52，0.71）	0.58（0.51，0.67）	0.024
Sigma	0.05（0.02，0.09）	0.11（0.06，0.18）	<0.001
Pere.10%	47.67（37.84，54.29）	59.81（40.35，67.66）	0.032

[1]	王罗丹,范红. 蝶鞍的形态学特点及其与错畸形的关系[J]. 国际口腔医学杂志, 2023, 50(6): 653-660.
[2]	杨雨楠,刘鹏,王虎,游梦. 上颌窦黏膜增厚的锥形束CT影像分析[J]. 国际口腔医学杂志, 2023, 50(3): 302-307.
[3]	延泽宁,孙睿,李菲,张建森. 双能量CT在颈部淋巴结病变评估中的研究进展[J]. 国际口腔医学杂志, 2023, 50(3): 335-340.
[4]	吴文智,冯达兴,陈垂壮,周丽鹃. 海口地区下颌第一恒磨牙近中中央根管发生率及相关因素[J]. 国际口腔医学杂志, 2022, 49(4): 420-425.
[5]	翟晓静,曹石,辛文龙,曹珊,张皓. 伴有广泛角化囊肿的多形性腺瘤1例[J]. 国际口腔医学杂志, 2022, 49(3): 328-331.
[6]	叶泽林,刘璐,龙虎,游梦. 弯曲前牙的影像评价及治疗的研究进展[J]. 国际口腔医学杂志, 2022, 49(2): 173-181.
[7]	夏飞飞,秦文娟,冯佳,周旭阳,孙二灿,黎昌学. 超声灰度直方图对多形性腺瘤与腺淋巴瘤鉴别诊断效能的初步研究[J]. 国际口腔医学杂志, 2022, 49(1): 60-65.
[8]	田浩楠,林敏,谢丛蔓,任嫒姝. 上颌腭侧阻生尖牙与寰椎后桥相关性的锥形束CT研究[J]. 国际口腔医学杂志, 2021, 48(5): 536-540.
[9]	施丹妮,杨鑫,吴建勇. 锥形束CT三维头影测量参考坐标系的研究进展[J]. 国际口腔医学杂志, 2021, 48(4): 398-404.
[10]	丁张帆,郭陟永,苗诚,李春洁,宣鸣,王晓毅,张壮. 基于锥形束CT的三维可视化技术在颌骨囊性病变手术中的应用[J]. 国际口腔医学杂志, 2021, 48(2): 180-186.
[11]	王奔,许喆桢,韦曦. 数字化微创技术在牙髓根尖周病学中的应用与进展[J]. 国际口腔医学杂志, 2021, 48(1): 110-118.
[12]	唐蓓,赵文俊,王虎,郑广宁,游梦. 根管超填导致下牙槽神经损伤2例[J]. 国际口腔医学杂志, 2020, 47(3): 293-296.
[13]	章婷婷,胡常红,彭燕,周文翘,张慧聪,刘蝶. 300例不同年龄段有牙颌人群上唇软组织侧貌的锥形束CT三维测量分析[J]. 国际口腔医学杂志, 2020, 47(2): 182-188.
[14]	王春林,刘从华,宋思吟,周丽淑,林丽佳. 运用锥形束CT诊断上下颌横向发育不调的研究进展[J]. 国际口腔医学杂志, 2020, 47(1): 121-124.
[15]	黎祺, 黄少宏. 岭南地区广府民系人群下颌第二恒磨牙牙根和根管形态的锥形束CT研究[J]. 国际口腔医学杂志, 2019, 46(6): 640-649.