Differentiation of low and high grade renal cell carcinoma on routine MRI with an externally validated automatic machine learning algorithm

Created by W.Langdon from gp-bibliography.bib Revision:1.8051

@Article{Purkayastha:2020:SR,

• author = "Subhanik Purkayastha and Yijun Zhao and Jing Wu and Rong Hu and Aidan McGirr and Sukhdeep Singh and Ken Chang and Raymond Y. Huang and Paul J. Zhang and Alvin Silva and Michael C. Soulen and S. William Stavropoulos and Zishu Zhang and Harrison X. Bai",
• title = "Differentiation of low and high grade renal cell carcinoma on routine {MRI} with an externally validated automatic machine learning algorithm",
• journal = "Scientific Reports",
• year = "2020",
• volume = "10",
• pages = "Article number: 19503",
• month = "11 " # nov,
• keywords = "genetic algorithms, genetic programming, TPOT, Diagnosis, Machine learning",
• URL = "https://rdcu.be/dabfG",
• DOI = "doi:10.1038/s41598-020-76132-z",
• abstract = "Pre-treatment determination of renal cell carcinoma aggressiveness may help guide clinical decision-making. We aimed to differentiate low-grade (Fuhrman I-II) from high-grade (Fuhrman III-IV) renal cell carcinoma using radiomics features extracted from routine MRI. 482 pathologically confirmed renal cell carcinoma lesions from 2008 to 2019 in a multicenter cohort were retrospectively identified. 439 lesions with information on Fuhrman grade from 4 institutions were divided into training and test sets with an 8:2 split for model development and internal validation. Another 43 lesions from a separate institution were set aside for independent external validation. The performance of TPOT (Tree-Based Pipeline Optimization Tool), an automatic machine learning pipeline optimizer, was compared to hand-optimized machine learning pipeline. The best-performing hand-optimized pipeline was a Bayesian classifier with Fischer Score feature selection, achieving an external validation ROC AUC of 0.59 (95percent CI 0.49-0.68), accuracy of 0.77 (95percent CI 0.68-0.84), sensitivity of 0.38 (95percent CI 0.29-0.48), and specificity of 0.86 (95percent CI 0.78-0.92). The best-performing TPOT pipeline achieved an external validation ROC AUC of 0.60 (95percent CI 0.50-0.69), accuracy of 0.81 (95percent CI 0.72-0.88), sensitivity of 0.12 (95percent CI 0.14-0.30), and specificity of 0.97 (95percent CI 0.87-0.97). Automated machine learning pipelines can perform equivalent to or better than hand-optimized pipeline on an external validation test non-invasively predicting Fuhrman grade of renal cell carcinoma using conventional MRI.",

}

Genetic Programming entries for Subhanik Purkayastha Yijun Zhao Jing Wu Rong Hu Aidan J McGirr Sukhdeep Singh Ken Chang Raymond Y Huang Paul J Zhang Alvin Silva Michael C Soulen S William Stavropoulos Zishu Zhang Harrison X Bai

Citations