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

被引:8
|
作者
Purkayastha, Subhanik [1 ]
Zhao, Yijun [2 ]
Wu, Jing [2 ]
Hu, Rong [8 ]
McGirr, Aidan [4 ]
Singh, Sukhdeep [4 ]
Chang, Ken [5 ]
Huang, Raymond Y. [6 ]
Zhang, Paul J. [7 ]
Silva, Alvin [4 ]
Soulen, Michael C. [3 ]
Stavropoulos, S. William [3 ]
Zhang, Zishu [2 ]
Bai, Harrison X. [1 ]
机构
[1] Brown Univ, Rhode Isl Hosp, Dept Diagnost Imaging, Alpert Med Sch, Providence, RI 02905 USA
[2] Cent South Univ, Xiangya Hosp 2, Dept Radiol, Changsha, Peoples R China
[3] Hosp Univ Penn, Dept Radiol, Div Intervent Radiol, 3400 Spruce St, Philadelphia, PA 19104 USA
[4] Mayo Clin, Dept Radiol, Phoenix, AZ USA
[5] Massachusetts Gen Hosp, Dept Radiol, Athinoula A Martinos Ctr Biomed Imaging, Boston, MA USA
[6] Brigham & Womens Hosp, Dept Radiol, 75 Francis St, Boston, MA 02115 USA
[7] Hosp Univ Penn, Dept Pathol, Philadelphia, PA 19104 USA
[8] Cent South Univ, Sch Comp Sci & Engn, Changsha, Hunan, Peoples R China
基金
美国国家卫生研究院;
关键词
RADIOMICS; PREDICTION; MODEL; FEATURES;
D O I
10.1038/s41598-020-76132-z
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
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 (95% CI 0.49-0.68), accuracy of 0.77 (95% CI 0.68-0.84), sensitivity of 0.38 (95% CI 0.29-0.48), and specificity of 0.86 (95% CI 0.78-0.92). The best-performing TPOT pipeline achieved an external validation ROC AUC of 0.60 (95% CI 0.50-0.69), accuracy of 0.81 (95% CI 0.72-0.88), sensitivity of 0.12 (95% CI 0.14-0.30), and specificity of 0.97 (95% 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.
引用
收藏
页数:8
相关论文
共 50 条
  • [21] Comparison of Utility of Histogram Apparent Diffusion Coefficient and R2*for Differentiation of Low-Grade From High-Grade Clear Cell Renal Cell Carcinoma
    Zhang, Yu-Dong
    Wu, Chen-Jiang
    Wang, Qing
    Zhang, Jing
    Wang, Xiao-Ning
    Liu, Xi-Sheng
    Shi, Hai-Bin
    AMERICAN JOURNAL OF ROENTGENOLOGY, 2015, 205 (02) : W193 - W201
  • [22] Low-Grade Spindle Cell Proliferation in Clear Cell Renal Cell Carcinoma is Unlikely an Initial Step in Sarcomatoid Differentiation
    Isikci, Ozlem Tanas
    He, Huiying
    Grossmann, Petr
    Alaghehbandan, Reza
    Ulanec, Monika
    Petersson, Fredrik
    Montiel, Delia Perez
    Michalova, Kvetoslava
    Pivovarcikova, Kristyna
    Ondic, Ondrej
    Saskova, Bohuslava
    Rotterova, Pavla
    Hora, Milan
    Michal, Michal
    Hes, Ondrej
    MODERN PATHOLOGY, 2017, 30 : 261A - 261A
  • [23] Low-grade spindle cell proliferation in clear cell renal cell carcinoma is unlikely to be an initial step in sarcomatoid differentiation
    Isikci, Ozlem Tanas
    He, Huying
    Grossmann, Petr
    Alaghehbandan, Reza
    Ulamec, Monika
    Michalova, Kvetoslava
    Pivovarcikova, Kristyna
    Montiel, Delia Perez
    Ondic, Ondrej
    Daum, Ondrej
    Prochazkova, Kristyna
    Hora, Milan
    Michal, Michal
    Hes, Ondrej
    HISTOPATHOLOGY, 2018, 72 (05) : 804 - 813
  • [24] Low-Grade Spindle Cell Proliferation in Clear Cell Renal Cell Carcinoma Is Unlikely an Initial Step in Sarcomatoid Differentiation
    Isikci, Ozlem Tanas
    He, Huiying
    Grossmann, Petr
    Alaghehbandan, Reza
    Ulamec, Monika
    Petersson, Fredrik
    Montiel, Delia Perez
    Michalova, Kvetoslava
    Pivovarcikova, Kristyna
    Ondic, Ondrej
    Saskova, Bohuslava
    Rotterova, Pavla
    Hora, Milan
    Michal, Michal
    Hes, Ondrej
    LABORATORY INVESTIGATION, 2017, 97 : 261A - 261A
  • [25] Machine Learning-Based MRI Texture Analysis to Predict the Histologic Grade of Oral Squamous Cell Carcinoma
    Ren, Jiliang
    Qi, Meng
    Yuan, Ying
    Duan, Shaofeng
    Tao, Xiaofeng
    AMERICAN JOURNAL OF ROENTGENOLOGY, 2020, 215 (05) : 1184 - 1190
  • [26] CT-based machine learning model to predict the Fuhrman nuclear grade of clear cell renal cell carcinoma
    Lin, Fan
    Cui, En-Ming
    Lei, Yi
    Luo, Liang-ping
    ABDOMINAL RADIOLOGY, 2019, 44 (07) : 2528 - 2534
  • [27] CT-based machine learning model to predict the Fuhrman nuclear grade of clear cell renal cell carcinoma
    Fan Lin
    En-Ming Cui
    Yi Lei
    Liang-ping Luo
    Abdominal Radiology, 2019, 44 : 2528 - 2534
  • [28] Comparison of utility of tumor size and apparent diffusion coefficient for differentiation of low- and high-grade clear-cell renal cell carcinoma
    Maruyama, Mitsunari
    Yoshizako, Takeshi
    Uchida, Koji
    Araki, Hisayoshi
    Tamaki, Yukihisa
    Ishikawa, Noriyuki
    Shiina, Hiroaki
    Kitagaki, Hajime
    ACTA RADIOLOGICA, 2015, 56 (02) : 250 - 256
  • [29] Kidney scoring surveillance: predictive machine learning models for clear cell renal cell carcinoma growth using MRI
    Pouria Yazdian Anari
    Aryan Zahergivar
    Nikhil Gopal
    Aditi Chaurasia
    Nathan Lay
    Mark W. Ball
    Baris Turkbey
    Evrim Turkbey
    Elizabeth C. Jones
    W. Marston Linehan
    Ashkan A. Malayeri
    Abdominal Radiology, 2024, 49 : 1202 - 1209
  • [30] Kidney scoring surveillance: predictive machine learning models for clear cell renal cell carcinoma growth using MRI
    Anari, Pouria Yazdian
    Zahergivar, Aryan
    Gopal, Nikhil
    Chaurasia, Aditi
    Lay, Nathan
    Ball, Mark W.
    Turkbey, Baris
    Turkbey, Evrim
    Jones, Elizabeth C.
    Linehan, W. Marston
    Malayeri, Ashkan A.
    ABDOMINAL RADIOLOGY, 2024, 49 (04) : 1202 - 1209