A Decision-Support Tool for Renal Mass Classification

We investigate the viability of statistical relational machine learning algorithms for the task of identifying malignancy of renal masses using radiomics-based imaging features. Features characterizing the texture, signal intensity, and other relevant metrics of the renal mass were extracted from multiphase contrast-enhanced computed tomography images. The recently developed formalism of relational functional gradient boosting (RFGB) was used to learn human-interpretable models for classification. Experimental results demonstrate that RFGB outperforms many standard machine learning approaches as well as the current diagnostic gold standard of visual qualification by radiologists.

[1]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[2]  J. Wyatt,et al.  Commentary: Prognostic models: clinically useful or quickly forgotten? , 1995 .

[3]  Gaurav Pandey,et al.  Objective risk stratification of prostate cancer using machine learning and radiomics applied to multiparametric magnetic resonance images , 2019, Scientific Reports.

[4]  Paul F. Whelan,et al.  Using filter banks in Convolutional Neural Networks for texture classification , 2016, Pattern Recognit. Lett..

[5]  Charu C. Aggarwal,et al.  Healthcare Data Analytics , 2015 .

[6]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[7]  Jaime Landman,et al.  Small renal masses: current concepts regarding the natural history and reflections on the American Urological Association guidelines , 2010, Current opinion in urology.

[8]  Kristian Kersting,et al.  Boosted Statistical Relational Learners , 2014, SpringerBriefs in Computer Science.

[9]  Badrinath R Konety,et al.  The prevalence of renal cell carcinoma diagnosed at autopsy , 2005, BJU international.

[10]  Inderbir S. Gill,et al.  Does Computed Tomography Still Have Limitations to Distinguish Benign from Malignant Renal Tumors for Radiologists? , 2017, Urologia Internationalis.

[11]  J. H. Schuenemeyer,et al.  Generalized Linear Models (2nd ed.) , 1992 .

[12]  Jason Weston,et al.  Gene Selection for Cancer Classification using Support Vector Machines , 2002, Machine Learning.

[13]  J. Friedman.  Greedy function approximation: A gradient boosting machine. , 2001 .

[14]  Ben Taskar,et al.  Introduction to statistical relational learning , 2007 .

[15]  P. N. Druzhkov,et al.  A survey of deep learning methods and software tools for image classification and object detection , 2016, Pattern Recognition and Image Analysis.

[16]  Quanzheng Li,et al.  Clinical decision support for Alzheimer's disease based on deep learning and brain network , 2016, 2016 IEEE International Conference on Communications (ICC).

[17]  Kristian Kersting,et al.  Boosted Statistical Relational Learners: From Benchmarks to Data-Driven Medicine , 2015 .

[18]  Steven Y Cen,et al.  Differentiation of Predominantly Solid Enhancing Lipid-Poor Renal Cell Masses by Use of Contrast-Enhanced CT: Evaluating the Role of Texture in Tumor Subtyping. , 2018, AJR. American journal of roentgenology.

[19]  Hendrik Blockeel,et al.  Top-Down Induction of First Order Logical Decision Trees , 1998, AI Commun..

[20]  Nello Cristianini,et al.  Kernel Methods for Pattern Analysis , 2004 .

[21]  Robert E. Schapire,et al.  A Brief Introduction to Boosting , 1999, IJCAI.

[22]  Kevin P. Murphy,et al.  Machine learning - a probabilistic perspective , 2012, Adaptive computation and machine learning series.

[23]  Gangning Liang,et al.  Fast Fourier transform-based analysis of renal masses on contrast-enhanced computed tomography images for grading of tumor , 2017, Symposium on Medical Information Processing and Analysis.

[24]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[25]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[26]  Randolph A. Miller,et al.  Review: Medical Diagnostic Decision Support Systems - Past, Present, And Future: A Threaded Bibliography and Brief Commentary , 1994, J. Am. Medical Informatics Assoc..

[27]  Gangning Liang,et al.  Quantitative Contour Analysis as an Image-based Discriminator Between Benign and Malignant Renal Tumors. , 2018, Urology.

[28]  Bram van Ginneken,et al.  A survey on deep learning in medical image analysis , 2017, Medical Image Anal..

[29]  James Wu,et al.  Foundations of Predictive Analytics (Chapman & Hall/CRC Data Mining and Knowledge Discovery Series) , 2012 .

[30]  Ricardo A Rendon,et al.  Active surveillance as the preferred management option for small renal masses. , 2010, Canadian Urological Association journal = Journal de l'Association des urologues du Canada.

[31]  Kristian Kersting,et al.  Relational learning helps in three-way classification of Alzheimer patients from structural magnetic resonance images of the brain , 2014, Int. J. Mach. Learn. Cybern..

[32]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[33]  Pedro M. Domingos,et al.  Markov Logic: An Interface Layer for Artificial Intelligence , 2009, Markov Logic: An Interface Layer for Artificial Intelligence.

[34]  G. Purcell,et al.  What makes a good clinical decision support system , 2005, BMJ : British Medical Journal.

[35]  Maria Antonietta Mazzei,et al.  CT Perfusion in the Characterisation of Renal Lesions: An Added Value to Multiphasic CT , 2014, BioMed research international.

[36]  Inderbir S. Gill,et al.  PD14-07 DIFFERENTIATION BETWEEN CLEAR CELL RENAL CELL CARCINOMAS AND ONCOCYTOMAS USING TEXTURE ANALYSIS OF CT IMAGES , 2016 .

[37]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[38]  Bino Varghese,et al.  Voxel-based whole-lesion enhancement parameters: a study of its clinical value in differentiating clear cell renal cell carcinoma from renal oncocytoma , 2017, Abdominal Radiology.

[39]  Samir S Taneja.  Small Renal Mass. , 2017, The Urologic clinics of North America.

[40]  Sriraam Natarajan,et al.  Machine Learning for Personalized Medicine: Predicting Primary Myocardial Infarction from Electronic Health Records , 2012, AI Mag..

[41]  Dapeng Hao,et al.  A CT-based radiomics nomogram for differentiation of renal angiomyolipoma without visible fat from homogeneous clear cell renal cell carcinoma , 2019, European Radiology.

[42]  Inderbir S. Gill,et al.  MP19-03 THE SHAPELY RENAL MASS: CONTOUR EVALUATION OF RENAL CELL CARCINOMA , 2016 .

[43]  Luc De Raedt,et al.  Statistical Relational Artificial Intelligence: Logic, Probability, and Computation , 2016, Statistical Relational Artificial Intelligence.

[44]  Kristian Kersting,et al.  Gradient-based boosting for statistical relational learning: The relational dependency network case , 2011, Machine Learning.

[45]  R. Wears,et al.  Computer technology and clinical work: still waiting for Godot. , 2005, JAMA.

[46]  P. McCullagh,et al.  Generalized Linear Models , 1984 .

[47]  J. Xipell,et al.  The incidence of benign renal nodules (a clinicopathologic study). , 1971, The Journal of urology.

[48]  L. Hayden,et al.  Ten Commandments for Effective Clinical Decision Support: Making the Practice of Evidence-based Medicine a Reality , 2011 .

[49]  Kristian Kersting,et al.  Learning from Imbalanced Data in Relational Domains: A Soft Margin Approach , 2014, 2014 IEEE International Conference on Data Mining.

[50]  Inderbir S Gill,et al.  A critical analysis of the actual role of minimally invasive surgery and active surveillance for kidney cancer. , 2010, European urology.

[51]  Shuo Yang,et al.  Identifying Rare Diseases from Behavioural Data: A Machine Learning Approach , 2016, 2016 IEEE First International Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE).

[52]  Hannu Huhdanpaa,et al.  Whole lesion quantitative CT evaluation of renal cell carcinoma: differentiation of clear cell from papillary renal cell carcinoma , 2015, SpringerPlus.