Top

Insights into Imaging

Published in:

Open Access 01-12-2023 | Computed Tomography | Original Article

Deep learning and radiomic feature-based blending ensemble classifier for malignancy risk prediction in cystic renal lesions

Authors: Quan-Hao He, Jia-Jun Feng, Fa-Jin Lv, Qing Jiang, Ming-Zhao Xiao

Published in: Insights into Imaging | Issue 1/2023

Abstract

Background

The rising prevalence of cystic renal lesions (CRLs) detected by computed tomography necessitates better identification of the malignant cystic renal neoplasms since a significant majority of CRLs are benign renal cysts. Using arterial phase CT scans combined with pathology diagnosis results, a fusion feature-based blending ensemble machine learning model was created to identify malignant renal neoplasms from cystic renal lesions (CRLs). Histopathology results were adopted as diagnosis standard. Pretrained 3D-ResNet50 network was selected for non-handcrafted features extraction and pyradiomics toolbox was selected for handcrafted features extraction. Tenfold cross validated least absolute shrinkage and selection operator regression methods were selected to identify the most discriminative candidate features in the development cohort. Feature’s reproducibility was evaluated by intra-class correlation coefficients and inter-class correlation coefficients. Pearson correlation coefficients for normal distribution and Spearman's rank correlation coefficients for non-normal distribution were utilized to remove redundant features. After that, a blending ensemble machine learning model were developed in training cohort. Area under the receiver operator characteristic curve (AUC), accuracy score (ACC), and decision curve analysis (DCA) were employed to evaluate the performance of the final model in testing cohort.

Results

The fusion feature-based machine learning algorithm demonstrated excellent diagnostic performance in external validation dataset (AUC = 0.934, ACC = 0.905). Net benefits presented by DCA are higher than Bosniak-2019 version classification for stratifying patients with CRL to the appropriate surgery procedure.

Conclusions

Fusion feature-based classifier accurately distinguished malignant and benign CRLs which outperformed the Bosniak-2019 version classification and illustrated improved clinical decision-making utility.

Available only for authorised users

Moch H, Cubilla AL, Humphrey PA, Reuter VE, Ulbright TM (2016) The 2016 WHO classification of tumours of the urinary system and male genital organs-part A: renal, penile, and testicular tumours. Eur Urol 70:93–105CrossRef

Hu EM, Zhang A, Silverman SG, et al. (2018) Multi-institutional analysis of CT and MRI reports evaluating indeterminate renal masses: comparison to a national survey investigating desired report elements. Abdom Radiol (NY) 43:3493–3502CrossRef

Smith AD, Allen BC, Sanyal R, et al. (2015) Outcomes and complications related to the management of Bosniak cystic renal lesions. AJR Am J Roentgenol 204:W550-556CrossRef

Agnello F, Albano D, Micci G, et al. (2020) CT and MR imaging of cystic renal lesions. Insights Imaging 11:5CrossRef

Yang B, Qiu C, Wan S, et al. (2020) Long-term follow-up study of the malignant transformation potential of the simple renal cysts. Transl Androl Urol 9:684–689CrossRef

Soputro NA, Kapoor J, Zargar H, Dias BH (2021) Malignant ascites following radical nephrectomy for cystic renal cell carcinoma. BMJ Case Rep 14:e243103CrossRef

Park MY, Park KJ, Kim MH, Kim JK (2021) Bosniak classification of cystic renal masses version 2019: comparison with version 2005 for class distribution, diagnostic performance, and interreader agreement using CT and MRI. AJR Am J Roentgenol 217:1367–1376CrossRef

Shampain KL, Shankar PR, Troost JP, et al. (2022) Interrater agreement of Bosniak classification version 2019 and version 2005 for cystic renal masses at CT and MRI. Radiology 302:357–366CrossRef

Dana J, Gauvin S, Zhang M, et al. (2022) CT-based Bosniak classification of cystic renal lesions: is version 2019 an improvement on version 2005? Eur Radiol 23:1–10

10.

Schoots IG, Zaccai K, Hunink MG, Verhagen P (2017) Bosniak classification for complex renal cysts reevaluated: a systematic review. J Urol 198:12–21CrossRef

11.

Yan JH, Chan J, Osman H, et al. (2021) Bosniak Classification version 2019: validation and comparison to original classification in pathologically confirmed cystic masses. Eur Radiol 31:9579–9587CrossRef

12.

Spiesecke P, Reinhold T, Wehrenberg Y, et al. (2021) Cost-effectiveness analysis of multiple imaging modalities in diagnosis and follow-up of intermediate complex cystic renal lesions. BJU Int 128:575–585CrossRef

13.

Corrias G, Micheletti G, Barberini L, Suri JS, Saba L (2022) Texture analysis imaging “what a clinical radiologist needs to know.” Eur J Radiol 146:110055CrossRef

14.

Xv Y, Lv F, Guo H, et al. (2021) Machine learning-based CT radiomics approach for predicting WHO/ISUP nuclear grade of clear cell renal cell carcinoma: an exploratory and comparative study. Insights Imaging 12:170CrossRef

15.

Hu Y, Xie C, Yang H, et al. (2021) Computed tomography-based deep-learning prediction of neoadjuvant chemoradiotherapy treatment response in esophageal squamous cell carcinoma. Radiother Oncol J Eur Soc Ther Radiol Oncol 154:6–13CrossRef

16.

Orlhac F, Frouin F, Nioche C, Ayache N, Buvat I (2019) Validation of a method to compensate multicenter effects affecting CT radiomics. Radiology 291:53–59CrossRef

17.

Ligero M, Jordi-Ollero O, Bernatowicz K, et al. (2021) Minimizing acquisition-related radiomics variability by image resampling and batch effect correction to allow for large-scale data analysis. Eur Radiol 31:1460–1470CrossRef

18.

Pleil JD, Wallace MAG, Stiegel MA, Funk WE (2018) Human biomarker interpretation: the importance of intra-class correlation coefficients (ICC) and their calculations based on mixed models, ANOVA, and variance estimates. J Toxicol Environ Health B Crit Rev 21:161–180CrossRef

19.

Zwanenburg A, Vallières M, Abdalah MA, et al. (2020) The image biomarker standardization initiative: standardized quantitative radiomics for high-throughput image-based phenotyping. Radiology 295:328–338CrossRef

20.

Lambin P, Leijenaar RTH, Deist TM, et al. (2017) Radiomics: the bridge between medical imaging and personalized medicine. Nat Rev Clin Oncol 14:749–762CrossRef

21.

Perez-Ortiz M, Gutierrez PA, Tino P, Hervas-Martinez C (2016) Oversampling the minority class in the feature space. IEEE Trans Neural Netw Learn Syst 27:1947–1961CrossRef

22.

Vasquez MM, Hu C, Roe DJ, Chen Z, Halonen M, Guerra S (2016) Least absolute shrinkage and selection operator type methods for the identification of serum biomarkers of overweight and obesity: simulation and application. BMC Med Res Methodol 16:154CrossRef

23.

Campbell SC, Clark PE, Chang SS, Karam JA, Souter L, Uzzo RG (2021) Renal mass and localized renal cancer: evaluation, management, and follow-up: AUA guideline: part I. J Urol 206:199–208CrossRef

24.

Campbell SC, Uzzo RG, Karam JA, Chang SS, Clark PE, Souter L (2021) Renal mass and localized renal cancer: evaluation, management, and follow-up: AUA guideline: part II. J Urol 206:209–218CrossRef

25.

Boissier R, Ouzaid I, Nouhaud FX, et al. (2019) Long-term oncological outcomes of cystic renal cell carcinoma according to the Bosniak classification. Int Urol Nephrol 51:951–958CrossRef

26.

Huang Z, Wang H, Ji Z (2022) Giant polycystic papillary renal cell carcinoma: a case report and literature review. Front Oncol 12:876217CrossRef

27.

Xv Y, Lv F, Guo H, et al. (2021) A CT-based radiomics nomogram integrated with clinic-radiological features for preoperatively predicting WHO/ISUP grade of clear cell renal cell carcinoma. Front Oncol 11:712554CrossRef

28.

Pacheco EO, Torres US, Alves AMA, Bekhor D, D’Ippolito G (2020) Bosniak classification of cystic renal masses version 2019 does not increase the interobserver agreement or the proportion of masses categorized into lower Bosniak classes for non-subspecialized readers on CT or MR. Eur J Radiol 131:109270CrossRef

29.

McGrath TA, Bai X, Kamaya A et al (2022) Proportion of malignancy in Bosniak classification of cystic renal masses version 2019 (v2019) classes: systematic review and meta-analysis. Eur Radiol

30.

Gillingham N, Chandarana H, Kamath A, Shaish H, Hindman N (2019) Bosniak IIF and III renal cysts: can apparent diffusion coefficient-derived texture features discriminate between malignant and benign IIF and III cysts? J Comput Assist Tomogr 43:485–492CrossRef

31.

Lee Y, Kim N, Cho KS, et al. (2009) Bayesian classifier for predicting malignant renal cysts on MDCT: early clinical experience. AJR Am J Roentgenol 193:W106-111CrossRef

32.

Miskin N, Qin L, Matalon SA, et al. (2021) Stratification of cystic renal masses into benign and potentially malignant: applying machine learning to the bosniak classification. Abdom Radiol (NY) 46:311–318CrossRef

33.

Li Y, Dai C, Bian T, et al. (2019) Development and prospective validation of a novel weighted quantitative scoring system aimed at predicting the pathological features of cystic renal masses. Eur Radiol 29:1809–1819CrossRef

34.

Dana J, Lefebvre TL, Savadjiev P, et al. (2022) Malignancy risk stratification of cystic renal lesions based on a contrast-enhanced CT-based machine learning model and a clinical decision algorithm. Eur Radiol 32:4116–4127CrossRef

35.

Kim Y, Tao C, Kim H, Oh GY, Ko J, Bae KT (2022) A deep learning approach for automated segmentation of kidneys and exophytic cysts in individuals with autosomal dominant polycystic kidney disease. J Am Soc Nephrol 33:1581–1589CrossRef

36.

Han K, Wang Y, Chen H et al (2022) A survey on vision transformer. IEEE Trans Pattern Anal Mach Intell

37.

Gao R, Zhao S, Aishanjiang K, et al. (2021) Deep learning for differential diagnosis of malignant hepatic tumors based on multi-phase contrast-enhanced CT and clinical data. J Hematol Oncol 14:154CrossRef

38.

Ferreira AM, Reis RB, Kajiwara PP, Silva GEB, Elias J, Muglia VF (2016) MRI evaluation of complex renal cysts using the Bosniak classification: a comparison to CT. Abdom Radiol (NY) 41:2011–2019CrossRef

39.

Krishna S, Schieda N, Pedrosa I, et al. (2021) Update on MRI of cystic renal masses including Bosniak version 2019. J Magn Reson Imaging 54:341–356CrossRef

40.

Davenport MS, Hu EM, Smith AD, et al. (2017) Reporting standards for the imaging-based diagnosis of renal masses on CT and MRI: a national survey of academic abdominal radiologists and urologists. Abdom Radiol (NY) 42:1229–1240CrossRef

Title: Deep learning and radiomic feature-based blending ensemble classifier for malignancy risk prediction in cystic renal lesions
Authors: Quan-Hao He
Jia-Jun Feng
Fa-Jin Lv
Qing Jiang
Ming-Zhao Xiao
Publication date: 01-12-2023
Publisher: Springer Vienna
Keywords: Computed Tomography
Kidney Cancer
Kidney Cancer
Computed Tomography
Kidney Cancer
Published in: Insights into Imaging / Issue 1/2023
Electronic ISSN: 1869-4101
DOI: https://doi.org/10.1186/s13244-022-01349-7

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Deep learning and radiomic feature-based blending ensemble classifier for malignancy risk prediction in cystic renal lesions

Abstract

Background

Results

Conclusions

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Abstract

Background

Results

Conclusions

Please log in to get access to this content

Other articles of this Issue 1/2023

Evaluation of preventive tract embolization with standardized gelatin sponge slurry on chest tube placement rate after CT-guided lung biopsy: a propensity score analysis

Retrospective batch analysis to evaluate the diagnostic accuracy of a clinically deployed AI algorithm for the detection of acute pulmonary embolism on CTPA

Diagnostic error and bias in the department of radiology: a pictorial essay

Systematic review with radiomics quality score of cholangiocarcinoma: an EuSoMII Radiomics Auditing Group Initiative

Core and penumbra estimation using deep learning-based AIF in association with clinical measures in computed tomography perfusion (CTP)

CT appearances and classification of hepatic epithelioid hemangioendothelioma