|
|
Prediction of Histological Grade and Ki-67 Expression inBreast Cancer by DCE-MRI and DWI Features |
Zhao Wenrui1, Xu Maosheng2, Wang Shiwei2, Fan Ming1*, Li Lihua1 |
1.(College of Life Information Science and Instrument Engineering, Hangzhou Dianzi University, Hangzhou 310018, China) 2.(Department of Radiology, Zhejiang Hospital of Traditional Chinese Medicine, Hangzhou 310006, China) |
|
|
Abstract The purpose of this study was to predict the histological grade of breast cancer and Ki-67 expression using features extracted from dynamic contrast enhancement magnetic resonance imaging (DCE-MRI) and diffusion weighted imaging (DWI). In this study, 144 cases of breast invasive ductal carcinoma were collected, which have not experienced breast surgery or chemotherapy before MRI examination. DW and DCE-MR images were obtained from preoperative breast MRI examination using a 3T scanner, and ADC map was calculated from DWI. Breast tumor segmentation was performed on all of the image series. After that, image features of texture, statistic, and morphological features of breast tumor were extracted on both the DW and DCE-MR images. The unsupervised discriminative feature selection (UDFS) and Fisher Score algorithm were used for feature selection. The classification model was established on these images respectively, and the classifiers of single-parametric image were fused for prediction. In order to evaluate the classifier performance, the area under the receiver operating characteristic curve (AUC) were calculated in a leave-one-out cross-validation analysis. The predictive model based on the second postcontrast image series of DCE-MRI generated an AUC of 0.780 with the specificity and sensitivity of 0.647 and 0.934 respectively in histological grade task, while in Ki-67 expression task, the model based on DWI generated an AUC of 0.756 with the specificity and sensitivity of 0.806 and 0.695, respectively. After multi-classifier fusion using features both from the DWI and DCE-MRI, the classification result was increased to AUC of 0.808 with the specificity and sensitivity of 0.706 and 0.895 respectively in histological grade prediction task, and generated an AUC of 0.783 with the specificity and sensitivity of 0.778 and 0.722 respectively in Ki-67 expression prediction task. In conclusion, it was showed that compared with each single parametric image alone, the performance of the classifier could be improved by combining features of DCE-MRI and DWI.
|
Received: 22 October 2018
|
|
|
|
|
[1] Girard P, Sanchez O, Leroyer C, et al. Deep venous thrombosis in patients with acute pulmonary embolism: Prevalence, risk factors, and clinical significance [J]. Chest, 2005, 128(3): 1593-1600. [2] Ferlay J, Ervik M, Dikshit R, et al. Cancer incidence and mortality worldwide: IARC Cancer Base No.11 [J]. International Agency for Research on Cancer, 2015, 136 (5): E359-E386. [3] 刘力,刘国文,谭米多. 乳腺癌的综合治疗现状 [J]. 中国肿瘤外科杂志, 2013, 5 (1): 60-63. [4] Deepti G, Veena G, Marwah N, et al. Correlation of hormone receptor expression with histologic parameters in benign and malignant breast tumors [J]. Iranian Journal of Pathology, 2015, 10(1): 23-34. [5] 王林伟,袁静萍,李雁. 乳腺癌组织学分级系统的研究进展和发展方向 [J]. 实用肿瘤学杂志, 2014, 28(2): 160-164. [6] Bloom HJ, Richardson WW. Histological grading and prognosis in breast cancer: A study of 1409 cases of which 359 have been followed for 15 years [J]. Br J Cancer, 1957, 11(3): 359-377. [7] 张卫,苏丹柯,罗宁斌,等. MR扩散加权成像表观扩散系数与乳腺浸润性导管癌病理分级相关性研究 [J]. 磁共振成像, 2015(2): 131-135. [8] Ruibal A, Arias JI, Del Río MC, et al. Histological grade in breast cancer: Association with clinical and biological features in a series of 229 patients [J]. Int J Biol Markers, 2001, 16(1): 56-61. [9] 王林伟,袁静萍,李雁. 乳腺癌组织学分级系统的研究进展和发展方向 [J]. 实用肿瘤学杂志, 2014, 28(2): 160-164. [10] Fan Ming, Cheng Hu, Zhang Peng, et al. DCE-MRI texture analysis with tumor subregion partitioning for predicting Ki-67 status of estrogen receptor-positive breast cancers [J]. Journal of Magnetic Resonance Imaging, 2018, 48(1): 237-247. [11] Petric M, Martinez S, Acevedo F, et al. Correlation between Ki67 and histological grade in breast cancer patients treated with preoperative chemotherapy [J]. Asian Pacific Journal of Cancer Prevention Apjcp, 2014, 15(23): 10277-10280. [12] Widodo I, Dwianingsih EK, Triningsih E, et al. Clinicopathological features of indonesian breast cancers with different molecular subtypes[J]. Asian Pacific Journal of Cancer Prevention Apjcp, 2014, 15(15): 6109-6113. [13] Fan Ming, He Ting, Zhang Peng, et al. Heterogeneity of diffusion-weighted imaging in tumours and the surrounding stroma for prediction of Ki-67 proliferation status in breast cancer [J]. Scientific Reports, 2017, 7 (1): 2875. [14] Gerdes J, Schwab U, Lemke H, et al. Production of a mouse monoclonal antibody reactive with a human nuclear antigen associated with cell proliferation [J]. International Journal of Cancer, 2010, 31(1): 13-20. [15] Weiss LM, Strickler JG, Medeiros LJ, et al. Proliferative rates of non-Hodgkin′s lymphomas as assessed by Ki-67 antibody [J]. Human Pathology, 1987, 18(11): 1155-1159. [16] 刘伟娟. 全数字化乳腺钼靶X线摄影在乳腺癌诊断中的研究进展[J]. 中国中西医结合影像学杂志, 2013, 11(5): 572-574. [17] Nagashima T, Hashimoto H, Oshida K, et al. Ultrasound demonstration of mammographically detected microcalcifications in patients with ductal carcinoma in situ, of the breast [J]. Breast Cancer, 2005, 12(3): 216-220. [18] Wang Junlin, Feng Zongying, Department OR, et al. Comparative analysis of molybdenum target X-ray, CT and color doppler ultrasound in the diagnosis of early inflammatory breast cancer [J]. Journal of Medical Theory & Practice, 2017, 30(15): 2200-2201, 2207. [19] Grimm LJ. Breast MRI radiogenomics: Current status and research implications [J]. Journal of Magnetic Resonance Imaging, 2016, 43 (6): 1269-1278. [20] Woodard GA, Ray KM, Joe BN, et al. Qualitative radiogenomics: Association between Oncotype DX test recurrence score and BI-RADS mammographic and breast MR imaging features [J]. Radiology, 2017, 286 (1): 162333. [21] 张静,安宁豫,程流泉,等. 动态增强磁共振成像结合扩散加权成像诊断乳腺病变的多参数分析 [J]. 中国医学影像学杂志, 2012 (10): 745-749. [22] Fan Ming, He Ting, Zhang Peng, et al. Diffusion-weighted imaging features of breast tumours and the surrounding stroma reflect intrinsic heterogeneous characteristics of molecular subtypes in breast cancer [J]. NMR in Biomedicine, 2017, 31(2): e0189302. [23] Xing Hua, Song Changlong, Li Wenjia. Meta analysis of lymph node metastasis of breast cancer patients: Clinical value of DWI and ADC value [J]. European Journal of Radiology, 2016, 85(6): 1132-1137. [24] 张承杰,厉力华. 基于空间FCM与MRF方法的乳腺MRI序列三维病灶分割研究[J]. 中国生物医学工程学报, 2014,33(2):202-211. [25] Stone M. Cross-validatory choice and assessment of statistical predictions (with discussion) [J]. Journal of the Royal Statistical Society, 1974, 36(2):111-147. [26] Yang Yi, Shen Hengtao, Ma Zhigang, et al. L2,1-norm regularized discriminative feature selection for unsupervised learning [C] // Proceedings of the 22nd International Joint Conference on Artificial Intelligence. New York: AAAI Press, 2011: 1589-1594. [27] Giorgio R, Simone M, Umberto C, et al. Infinite latent feature selection: A probabilistic latent graph-based ranking approach [C]// IEEE International Conference on Computer Vision. Venice: IEEE, 2017: 1407-1415. [28] Shin JK, Kim JY. Dynamic contrast-enhanced and diffusion-weighted MRI of estrogen receptor-positive invasive breast cancers: Associations between quantitative MR parameters and Ki-67 proliferation status [J]. Journal of Magnetic Resonance Imaging, 2017, 45(1):94-102. |
[1] |
Xie Sudan, Fan Ming, Xu Maosheng, Wang Shiwei, Li Lihua. Prediction of Histological Grade in Invasive Breast Cancer Based on T2-Weighted MRI[J]. Chinese Journal of Biomedical Engineering, 2020, 39(3): 280-287. |
[2] |
Ma Wei, Liu Hongli, Sun Mingjian, Xu Jun, Jiang Yanni. A Novel Automated Tumor Segmentation Model for Enhanced Breast MRI[J]. Chinese Journal of Biomedical Engineering, 2019, 38(1): 28-34. |
|
|
|
|