Computer-Based Characterization of Specific Cystic Renal Masses of Bosniac Classification with Traditional Machine Learning and Modified Deep Learning Methods

Öz

Aim: This study aims to develop a novel artificial intelligencebased pre-diagnosis system for classifying cystic renal masses (CRM) according to the Bosniak classification. The objective is to distinguish between the five diagnostic stages of the Bosniak classification using traditional machine learning (ML) and deep learning (DL) techniques. Material and Method: A total of 20 contrast-enhanced CT images were collected for each of the five Bosniak stages (I, II, IIF, III, IV), verified by a uro-oncologist and radiologist. Additional image variations were generated using the Keras image processing library during the data augmentation phase, resulting in 600 images per stage. This process included operations such as brightness and contrast modification, image rotation, noise addition, and flipping. These augmented images were then used to train both ML and DL models. The k-Nearest Neighbors (kNN) algorithm was applied for the ML approach, while modified Convolutional Neural Networks (CNN) and VGG-16 models were used for the DL approach. Model performances were evaluated using receiver operating characteristic (ROC) analysis and area under the curve (AUC) metrics. Results: The kNN algorithm accurately classified the Bosniak stages with an AUC of 0.854. The VGG-16 model demonstrated superior performance, with an AUC of 0.978, achieving higher classification accuracy than the kNN model. Conclusion: The computerized Bosniak classification system based on CT images effectively differentiates between the five Bosniak stages. This system, utilizing both ML and DL models, has the potential to enhance the pre-diagnosis of CRM in clinical settings and can also effectively exclude other types of renal masses.

Anahtar Kelimeler

• Renal Mass
• Bosniak Classification
• Machine Learning
• Feature Extraction
• Deep Learning

Kaynakça

1. 1. Alrumayyan M, Raveendran L, Lawson KA, Finelli A. Cystic Renal Masses: Old and New Paradigms. Urol Clin North Am. 2023;50(2):227–238.
2. 2. McGrath TA, Bai X, Kamaya A, Park KJ, Park MY, Tse JR, et al. Proportion of malignancy in Bosniak classification of cystic renal masses version 2019(v2019) classes: systematic review and meta-analysis. Eur Radiol. 2023;33(2):1307–1317.
3. 3. Silverman SG, Pedrosa I, Ellis JH, Hindman NM, Schieda N, Smith AD, et al. Bosniak Classification of Cystic Renal Masses, Version 2019: An Update Proposal and Needs Assessment. Radiology. 2019;292(2):475–488.
4. 4. Narayanasamy S, Krishna S, Prasad Shanbhogue AK, Flood TA, Sadoughi N, Sathiadoss P, et al. Contemporary update on imaging of cystic renal masses with histopathological correlation and emphasis on patient management. Clin Radiol. 2019;74(2):83–94.
5. 5. Miskin N, Qin L, Silverman SG, Shinagare AB. Differentiating Benign From Malignant Cystic Renal Masses: A Feasibility Study of Computed Tomography Texture-Based Machine Learning Algorithms. J Comput Assist Tomogr. 2023;47(3):376–381.
6. 6. Zeng SE, Du MY, Yu Y, Huang SY, Zhang D, Cui XW, et al. Ultrasound, CT, and MR Imaging for Evaluation of Cystic Renal Masses. J Ultrasound Med. 2022;41(4):807–819.
7. 7. Warren KS, McFarlane J. The Bosniak classification of renal cystic masses. BJU Int. 2005;95(7):939–942.
8. 8. Curry NS, Cochran ST, Bissada NK. Cystic renal masses: accurate Bosniak classification requires adequate renal CT. AJR Am J Roentgenol. 2000;175(2):339–342.

9. 9. Hindman NM, Hecht EM, Bosniak MA. Follow-up for Bosniak category 2F cystic renal lesions. Radiology. 2014;272(3):757–766.
10. 10. Aronson S, Frazier HA, Baluch JD, Hartman DS, Christenson PJ. Cystic renal masses: usefulness of the Bosniak classification. Urol Radiol. 1991;13(2):83–90.
11. 11. Smith AD, Remer EM, Cox KL, Lieber ML, Allen BC, Shah SN, et al. Bosniak category IIF and III cystic renal lesions: outcomes and associations. Radiology. 2012;262(1):152–160.
12. 12. Zakaria MA, El-Toukhy N, Abou El-Ghar M, El Adalany MA. Role of multiparametric MRI in characterization of complicated cystic renal masses. Egyptian Journal of Radiology and Nuclear Medicine. 2023;54(1):1–13.
13. 13. Lin Z, Cui Y, Liu J, Sun Z, Ma S, Zhang X, et al. Automated segmentation of kidney and renal mass and automated detection of renal mass in CT urography using 3D U-Net-based deep convolutional neural network. Eur Radiol. 2021;31(7):5021–5031.
14. 14. Huang L, Ye Y, Chen J, Feng W, Peng S, Du X, et al. Cystic renal mass screening: machine-learning-based radiomics on unenhanced computed tomography. Diagn Interv Radiol. 2024;30(4):236–247.
15. 15. Zhang J, Tehrani YM, Wang L, Ishill NM, Schwartz LH, Hricak H. Renal masses: characterization with diffusion-weighted MR imaging--a preliminary experience. Radiology. 2008;247(2):458–464.
16. 16. Krishna S, Murray CA, McInnes MD, Chatelain R, Siddaiah M, Al-Dandan O, et al. CT imaging of solid renal masses: pitfalls and solutions. Clin Radiol. 2017;72(9):708–721.
17. 17. Mangayarkarasi T, Jamal DN. PNN-based analysis system to classify renal pathologies in Kidney Ultrasound Images. International Conference on Computing and Convergence Technology. 2017;123–126.
18. 18. Brandi N, Mosconi C, Giampalma E, Renzulli M. Bosniak Classification of Cystic Renal Masses: Looking Back, Looking Forward. Acad Radiol. 2024;31(8):3237–3247.
19. 19. Kang H, Xie W, Wang H, Guo H, Jiang J, Liu Z, et al. Multiparametric MRI-Based Machine Learning Models for the Characterization of Cystic Renal Masses Compared to the Bosniak Classification, Version 2019: A Multicenter Study. Acad Radiol. 2024;31(8):3223–3234.
20. 20. Bhandari M, Yogarajah P, Kavitha MS, Condell J. Exploring the Capabilities of a Lightweight CNN Model in Accurately Identifying Renal Abnormalities: Cysts, Stones, and Tumors, Using LIME and SHAP. Applied Sciences 2023, Vol. 13, Page 3125. 2023;13(5):3125.
21. 21. Zabihollahy F, Schieda N, Krishna S, Ukwatta E. Automated classification of solid renal masses on contrast-enhanced computed tomography images using convolutional neural network with decision fusion. Eur Radiol. 2020;30(9):5183–5190.