Differential diagnosis of renal eosinophilic adenoma and renal clear cell carcinoma based on enhanced CT image omics model
Song Xin1, Yin Manxin2, Su Qiaona2, Ma Xinyu1, Zhao Haifeng1, Zhang Jianxin1,3
1School of Public Health,Shanxi Medical University,Taiyuan 030001, China; 2Department of Medical imaging, Shanxi medical University, Taiyuan 030000, China; 3Department of Radiology, Cancer Hospital Affiliated to Shanxi Medical University/ Shanxi Hospital Affiliated to Cancer Hospital, Chinese Academy of Medical Sciences/ Shanxi Province Cancer Hospital, Taiyuan 030000, China
Abstract:Objective This study aimed to explore the value of enhanced CT imaging model combined with machine learning in the differential diagnosis of renal clear cell carcinoma (ccRCC) and renal eosinophilic adenoma (RO). Methods Retropective cohort study was conduted. A total of 100 patients with renal cancer diagnosed pathologically admitted to Shanxi Cancer Hospital from June 2013 to July 2022 were included, including 63 males and 37 females, aged 42-81 (60.8±8.7) years. Of the 100 patients, 75 were pathologically confirmed as ccRCC patients, including 52 males and 23 females, aged 42-79 (59.9±8.5) years. There were 25 RO patients in the RO group, including 11 males and 14 females, aged 46-81 (63.5±8.8) years. The patients were classified into test cohort (30%) and training cohort (70%) with a random method, and all of them underwent enhanced CT examination. Then, 1 409 imaging features were extracted from portal venous CT images, and variance threshold, SelectKBest, and least absolute shrinkage and selection operator algorithms were used in feature extraction. We constructed an image omics model and drew the receiver operating characteristic curve. Sensitivity, specificity, accuracy, and F1-score were used in evaluating the performance of different imaging models. Results No statistically significant difference in age was found between the groups (t=-1.82, P=0.072). The gender showed statistically significant difference between the groups (χ2=5.16, P=0.023). The 12 most relevant features were selected from 1 409 image omics features, and five models were established to differentiate between ccRCC and RO: support vector machine, logistic regression (LR) model, decision tree model, K-nearest neighbor model, and random forest model. Results showed that the AUC values of the five models in the training and test cohorts were 0.905 (95% confidence interval [CI] 0.826-0.984), 0.870 (95% CI 0.742-0.996), 0.910 (95% CI 0.717-0.989), 0.853 (95% CI 0.717-0.989), 0.885 (95% CI 0.787-0.983), 0.628 (95% CI 0.353-0.903), 0.925 (95% CI 0.873-0.977), 0.638 (95% CI 0.416-0.861), 0.980 (95% CI 0.954-1.000), and 0.821 (95% CI 0.673-0.968). In summary, the LR model showed the best performance and had ideal diagnostic performance. Conclusion Enhanced CT-based image omics features can improve the accuracy of the differential diagnosis of ccRCC and RO.
宋鑫, 殷满心, 苏巧娜, 马欣雨, 赵海峰, 张建新. 基于增强CT的影像组学模型对肾嗜酸细胞腺瘤与肾透明细胞癌的鉴别诊断[J]. 中华解剖与临床杂志, 2024, 29(2): 105-110.
Song Xin, Yin Manxin, Su Qiaona, Ma Xinyu, Zhao Haifeng, Zhang Jianxin. Differential diagnosis of renal eosinophilic adenoma and renal clear cell carcinoma based on enhanced CT image omics model. Chinese Journal of Anatomy and Clinics, 2024, 29(2): 105-110.
Capitanio U, Bensalah K, Bex A, et al.Epidemiology of renal cell carcinoma[J]. Eur Urol, 2019, 75(1): 74-84. DOI: 10.1016/j.eururo.2018.08.036.
[2]
Makhov P, Joshi S, Ghatalia P, et al.Resistance to systemic therapies in clear cell renal cell carcinoma: mechanisms and management strategies[J]. Mol Cancer Ther, 2018,17(7):1355-1364. DOI: 10.1158/1535-7163.MCT-17-1299.
[3]
Giambelluca D, Pellegrino S, Midiri M, et al.The "central stellate scar" sign in renal oncocytoma[J]. Abdom Radiol (NY), 2019,44(5):1942-1943. DOI: 10.1007/s00261-019-01899-3.
[4]
韩金花,丁霞,赵霞,等.肾透明细胞癌与肾嗜酸细胞腺瘤的CT鉴别诊断[J].医学影像学杂志,2022,32(1):107-110.Han JH, Ding X, Zhao X, et al.The CT features of clear cell renal cell carcinoma and its differentiation with renal oncocytoma[J]. J Med Imaging, 2022, 32(1):107-110.
[5]
Kay FU, Pedrosa I.Imaging of solid renal masses[J]. Urol Clin North Am, 2018,45(3):311-330. DOI: 10.1016/j.ucl.2018.03.013.
[6]
Motzer RJ, Bacik J, Murphy BA, et al.Interferon-alfa as a comparative treatment for clinical trials of new therapies against advanced renal cell carcinoma[J]. J Clin Oncol, 2002,20(1):289-296. DOI: 10.1200/JCO.2002.20.1.289.
[7]
Ljungberg B, Albiges L, Abu-Ghanem Y, et al.European association of urology guidelines on renal cell carcinoma: the 2022 update[J]. Eur Urol, 2022,82(4):399-410. DOI: 10.1016/j.eururo.2022.03.006.
[8]
邢会武, 王军, 孟中勤, 等. 肾嗜酸细胞腺瘤的诊疗(附35例报告)[J].临床泌尿外科杂志,2019,34(8):598-601. DOI: 10.13201/j.issn.1001-1420.2019.08.003.Xing HW, Wang J, Meng ZQ, et al.Clinical analysis of renal oncocytoma ( Report of 35 cases)[J]. J Clin Urology, 2019, 34(8): 598-601. DOI: 10.13201/j.issn.1001-1420.2019.08.003.
[9]
Li Y, Huang X, Xia Y, et al.Value of radiomics in differential diagnosis of chromophobe renal cell carcinoma and renal oncocytoma[J]. Abdom Radiol (NY), 2020,45(10):3193-3201. DOI: 10.1007/s00261-019-02269-9.
Escudier B, Porta C, Schmidinger M, et al.Renal cell carcinoma: ESMO Clinical Practice Guidelines for diagnosis, treatment and follow-up[J]. Ann Oncol, 2016,27(suppl 5):v58-v68. DOI: 10.1093/annonc/mdw328.
马丽娅,胡道予,李佳丽,等.小肾嗜酸细胞腺瘤的CT增强表现及与小肾透明细胞癌的鉴别[J].放射学实践,2018,33(7):731-736. DOI:10.13609/j.cnki.1000-0313.2018.07.016.Ma LY, Hu DY, Li JL, et al.The enhanced CT features of small renal oncocytoma and its differentiation with small clear cell renal cell carcinoma[J]. Radiol Practic, 2018, 33(7): 731-736. DOI:10.13609/j.cnki.1000-0313.2018.07.016.
[14]
Bhandari A, Ibrahim M, Sharma C, et al.CT-based radiomics for differentiating renal tumours: a systematic review[J]. Abdom Radiol (NY), 2021,46(5):2052-2063. DOI: 10.1007/s00261-020-02832-9.
[15]
Cho A, Lee J E, Kwon G Y, et al.Post-operative acute kidney injury in patients with renal cell carcinoma is a potent risk factor for new-onset chronic kidney disease after radical nephrectomy[J]. Nephrol Dial Transplant, 2011, 26(11): 3496-3501. DOI: 10.1111/bju.13538.
[16]
Rossi SH, Klatte T, Usher-Smith J, et al.Epidemiology and screening for renal cancer[J]. World J Urol, 2018,36(9):1341-1353. DOI: 10.1007/s00345-018-2286-7.
[17]
Visvikis D, Cheze Le Rest C, Jaouen V, et al. Artificial intelligence, machine (deep) learning and radio(geno)mics: definitions and nuclear medicine imaging applications[J]. Eur J Nucl Med Mol Imaging, 2019,46(13):2630-2637. DOI: 10.1007/s00259-019-04373-w.
[18]
Gillies RJ, Kinahan PE, Hricak H.Radiomics: images are more than pictures, they are data[J]. Radiology, 2016,278(2):563-577. DOI: 10.1148/radiol.2015151169.
[19]
Suarez-Ibarrola R, Basulto-Martinez M, Heinze A, et al.Radiomics applications in renal tumor assessment: a comprehensive review of the literature[J]. Cancers (Basel), 2020,12(6): 1387. DOI: 10.3390/cancers12061387.
[20]
Gurbani S, Morgan D, Jog V, et al.Evaluation of radiomics and machine learning in identification of aggressive tumor features in renal cell carcinoma (RCC)[J]. Abdom Radiol (NY), 2021,46(9):4278-4288. DOI: 10.1007/s00261-021-03083-y.