A Deep Learning-Based Radiomics Model for Differentiating Benign and Malignant Renal Tumors
Leilei Zhou, Zuoheng Zhang, Yu-Chen Chen, Zhen-Yu Zhao, Xin-Dao Yin, Hong-Bing Jiang, Leilei Zhou, Zuoheng Zhang, Yu-Chen Chen, Zhen-Yu Zhao, Xin-Dao Yin, Hong-Bing Jiang
Abstract
Objectives: To investigate the effect of transfer learning on computed tomography (CT) images for the benign and malignant classification on renal tumors and to attempt to improve the classification accuracy by building patient-level models.
Methods: One hundred ninety-two cases of renal tumors were collected and identified by pathologic diagnosis within 15 days after enhanced CT examination (66% male, 70% malignant renal tumors, average age of 62.27 ± 12.26 years). The InceptionV3 model pretrained by the ImageNet dataset was cross-trained to perform this classification. Five image-level models were established for each of the Slice, region of interest (ROI), and rectangular box region (RBR) datasets. Then, two patient-level models were built based on the optimal image-level models. The network's performance was evaluated through analysis of the receiver operating characteristic (ROC) and five-fold cross-validation.
Results: In the image-level models, the test results of model trained on the Slice dataset [accuracy (ACC) = 0.69 and Matthews correlation coefficient (MCC) = 0.45] were the worst. The corresponding results on the ROI dataset (ACC = 0.97 and MCC = 0.93) were slightly better than those on the RBR dataset (ACC = 0.93 and MCC = 0.85) when freezing the weights before the mixed6 layer. Compared with the image-level models, both patient-level models could discriminate better (ACC increased by 2%-5%) on the RBR and Slice datasets.
Conclusions: Deep learning can be used to classify benign and malignant renal tumors from CT images. Our patient-level models could benefit from 3D data to improve the accuracy.
Copyright © 2018 The Authors. Published by Elsevier Inc. All rights reserved.
Figures
References
- Laguna MP, Algaba F, Cadeddu J, Clayman R, Gill I, Gueglio G, Hohenfellner M, Joyce A, Landman J, Lee B. Current patterns of presentation and treatment of renal masses: a clinical research office of the endourological society prospective study. J Endourol. 2014;28:861–870.
- Ljungberg B, Bensalah K, Canfield S, Dabestani S, Hofmann F, Hora M, Kuczyk MA, Lam T, Marconi L, Merseburger AS. EAU guidelines on renal cell carcinoma: 2014 update. Eur Urol. 2015;67:913–992.
- Murphy AM, Buck AM, Benson MC, Mckiernan JM. Increasing detection rate of benign renal tumors: evaluation of factors predicting for benign tumor histologic features during past two decades. Urology. 2009;73:1297–1298.
- Ball MW, Bezerra SM, Gorin MA, Cowan M, Pavlovich CP, Pierorazio PM, Netto GJ, Allaf ME. Grade heterogeneity in small renal masses: potential implications for renal mass biopsy. J Urol. 2015;193:36–40.
- Lambin P, Rios-Velazquez E, Leijenaar R, Carvalho S, van Stiphout RGPM, Granton P, Zegers CML, Gillies R, Boellard R, Dekker A. Radiomics: extracting more information from medical images using advanced feature analysis. Eur J Cancer. 2012;48:441–446.
- Hodgdon T, McInnes MDF, Schieda N, Flood TA, Lamb L, Thornhill RE. Can quantitative CT texture analysis be used to differentiate fat-poor renal angiomyolipoma from renal cell carcinoma on unenhanced CT images? Radiology. 2015;276:787–796.
- Raman SP, Chen YF, Schroeder JL, Huang P, Fishman EK. CT texture analysis of renal masses: pilot study using random forest classification for prediction of pathology. Acad Radiol. 2014;21:1587–1596.
- Feng Z, Rong P, Cao P, Zhou Q, Zhu W, Yan Z, Liu Q, Wang W. Machine learning-based quantitative texture analysis of CT images of small renal masses: differentiation of angiomyolipoma without visible fat from renal cell carcinoma. Eur Radiol. 2018;28:1625–1633.
- Aerts HJWL, Velazquez ER, Leijenaar RTH, Parmar C, Grossmann P, Carvalho S, Bussink J, Monshouwer R, Haibe-Kains B, Rietveld D. Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nat Commun. 2014:4644.
- Karpathy A, Toderici G, Shetty S, Leung T, Sukthankar R. CVPR. 2014. FF Li, Large-scale video classification with convolutional neural networks; pp. 1725–1732.
- Donahue J, Jia Y, Vinyals O, Hoffman J, Zhang N, Tzeng E, Darrell T. ICML, 32. 2013. DeCAF: a deep convolutional activation feature for generic visual recognition; pp. 647–655.
- Esteva A, Kuprel B, Novoa R, Ko J, Swetter S, Blau H, Thrun S. Corrigendum: dermatologist-level classification of skin cancer with deep neural networks. Nature. 2017;546:686.
- Arevalo J, Gonzalez FA, Ramos-Pollan R, Oliveira JL, Guevara Lopez MA. EMBC. Vol. 797. 2015. Convolutional neural networks for mammography mass lesion classification.
- Pan SJ, Yang QA. A survey on transfer learning. IEEE Trans Knowl Data Eng. 2010;22:1345–1359.
- Kim DH, MacKinnon T. Artificial intelligence in fracture detection: transfer learning from deep convolutional neural networks. Clin Radiol. 2018;73:439–445.
- Huynh BQ, Hui L, Giger ML. Digital mammographic tumor classification using transfer learning from deep convolutional neural networks. J Med Imaging. 2016;3:034501.
- Cicero M, Bilbily A, Dowdell T, Gray B, Perampaladas K, Barfett J. Training and validating a deep convolutional neural network for computer-aided detection and classification of abnormalities on frontal chest radiographs. Invest Radiol. 2017;52:281–287.
- Ciresan DC, Giusti A, Gambardella LM, Schmidhuber J. Mitosis detection in breast cancer histology images with deep neural networks. Med Image Comput Comput Assist Interv. 2013;16:411–418.
- Dou Q, Chen H, LQ Yu, Zhao L, Qin J, Wang DF, Mok VCT, Shi L, Heng PA. Automatic detection of cerebral microbleeds from mr images via 3D convolutional neural networks. IEEE Trans Med Imaging. 2016;35:1182–1195.
- Frederick LGMD, David LPMD, Irvin DFMD, Fritz C.T.R. RHIT A.G., Charles MBMD, Daniel GHMD, Monica MMD. Springer; 2010. AJCC Cancer Staging Manual.
- Fuhrman SA, Lasky LC, Limas C. Prognostic significance of morphologic parameters in renal cell carcinoma. Am J Surg Pathol. 1982;6:655–663.
- Gomes FV, Matos AP, Palas J, Mascarenhas V, Herédia V, Duarte S, Ramalho M. Renal cell carcinoma subtype differentiation using single-phase corticomedullary contrast-enhanced CT. Clin Imaging. 2015;39:273–277.
- Yan L, Liu Z, Wang G, Huang Y, Liu Y, Yu Y, Liang C. Angiomyolipoma with minimal fat: differentiation from clear cell renal cell carcinoma and papillary renal cell carcinoma by texture analysis on CT images. Acad Radiol. 2015;22:1115.
- Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z. ICVPR. 2016. Rethinking the Inception Architecture for Computer Vision; pp. 2818–2826.
- Bar Y, Diamant I, Wolf L, Lieberman S, Konen E, Greenspan H, Ieee . ISBI. 2015. Chest Pathology Detection Using Deep Learning with Non-Medical Training; pp. 294–297.
- Gao M, Bagci U, L Lu, A Wu, Buty M, Shin HC, Roth H, Papadakis GZ. CMBBE, 6. 2018. A Depeursinge, RM Summers, Holistic Classification of CT Attenuation Patterns for Interstitial Lung Diseases via Deep Convolutional Neural Networks; pp. 1–6.
- Liu J, Wang D, L Lu, Wei Z, Kim L, Turkbey EB, Sahiner B, Petrick N, Summers RM. Detection and diagnosis of colitis on computed tomography using deep convolutional neural networks. Med Phys. 2017;44
- Jozefowicz R, Zaremba W, Sutskever I. PMLR, 37. 2015. An Empirical Exploration of Recurrent Network Architectures; pp. 2342–2350.
- Ravishankar H, Sudhakar P, Venkataramani R, Thiruvenkadam S, Annangi P, Babu N, Vaidya V. Springer Int Publishing Ag; 2016. Understanding the Mechanisms of Deep Transfer Learning for Medical Images; pp. 188–196.
- Raj V, Magg S, Wermter S. Towards effective classification of imbalanced data with convolutional neural networks. Lect Notes Artif Intell. 2016;9896:150–162.
- Esteva A, Kuprel B, RA Novoa J Ko, Swetter SM, Blau HM, Thrun S. Dermatologist-level classification of skin cancer with deep neural networks. Nature. 2017;542:115–118.
- Lee H, Hong H, Kim J, Jung DC. Deep feature classification of angiomyolipoma without visible fat and renal cell carcinoma in abdominal contrast-enhanced CT images with texture image patches and hand-crafted feature concatenation. Med Phys. 2018;45:1550–1561.
- He KM, Zhang XY, Ren SQ, Sun J, Ieee . CVPR. 2016. Deep Residual Learning for Image Recognition2016 IEEE Conference on Computer Vision and Pattern Recognition; pp. 770–778.
- Shimizu A, Ohno R, Ikegami T, Kobatake H, Nawano S, Smutek D. Segmentation of multiple organs in non-contrast 3D abdominal CT images. Int J Comput Assist Radiol Surg. 2007;2:135–142.
- Chung J, Gulcehre C, Cho K, Bengio Y. Gated feedback recurrent neural networks. Comput Sci. 2015:2067–2075.
- Jia D, Krause J, Li FF. CVPR. 2013. Fine-Grained Crowdsourcing for Fine-Grained Recognition; pp. 580–587.
- Girshick R. ICCV. 2015. Fast R-CNN; pp. 1440–1448.
Source: PubMed