An Tang1,2,3,4, François Destrempes5, Siavash Kazemirad6, Julian Garcia-Duitama7,5, Bich N Nguyen8,9, Guy Cloutier10,7,5. 1. Department of Radiology, Centre hospitalier de l'Université de Montréal (CHUM), Montréal, Québec, Canada. an.tang@umontreal.ca. 2. Department of Radiology, Radio-oncology and Nuclear Medicine, Université de Montréal and CRCHUM, 1000 rue Saint-Denis, Montréal, Québec, H2X 0C2, Canada. an.tang@umontreal.ca. 3. Laboratory of Medical Image Analysis, Centre de recherche du Centre hospitalier de l'Université de Montréal (CRCHUM), Montréal, Québec, Canada. an.tang@umontreal.ca. 4. Université de Montréal, Institute of Biomedical Engineering, Montréal, Québec, Canada. an.tang@umontreal.ca. 5. Laboratory of Biorheology and Medical Ultrasonics (LBUM), Centre de recherche du Centre hospitalier de l'Université de Montréal (CRCHUM), Montréal, Québec, Canada. 6. School of Mechanical Engineering, Iran University of Science and Technology, Tehran, Iran. 7. Université de Montréal, Institute of Biomedical Engineering, Montréal, Québec, Canada. 8. Department of Pathology, Centre hospitalier de l'Université de Montréal (CHUM), Montréal, Québec, Canada. 9. Department of Pathology and Cellular Biology, Université de Montréal, Montréal, Québec, Canada. 10. Department of Radiology, Radio-oncology and Nuclear Medicine, Université de Montréal and CRCHUM, 1000 rue Saint-Denis, Montréal, Québec, H2X 0C2, Canada.
Abstract
OBJECTIVES: To develop a machine learning model based on quantitative ultrasound (QUS) parameters to improve classification of steatohepatitis with shear wave elastography in rats by using histopathology scoring as the reference standard. METHODS: This study received approval from the institutional animal care committee. Sixty male Sprague-Dawley rats were either fed a standard chow or a methionine- and choline-deficient diet. Ultrasound-based radiofrequency images were recorded in vivo to generate QUS and elastography maps. Random forests classification models and a bootstrap method were used to identify the QUS parameters that improved the classification accuracy of elastography. Receiver-operating characteristic analyses were performed. RESULTS: For classification of not steatohepatitis vs borderline or steatohepatitis, the area under the receiver-operating characteristic curve (AUC) increased from 0.63 for elastography alone to 0.72 for a model that combined elastography and QUS techniques (p < 0.001). For detection of liver steatosis grades 0 vs ≥ 1, ≤ 1 vs ≥ 2, ≤ 2 vs 3, respectively, the AUCs increased from 0.70, 0.65, and 0.69 to 0.78, 0.78, and 0.75 (p < 0.001). For detection of liver inflammation grades 0 vs ≥ 1, ≤ 1 vs ≥ 2, ≤ 2 vs 3, respectively, the AUCs increased from 0.58, 0.77, and 0.78 to 0.66, 0.84, and 0.87 (p < 0.001). For staging of liver fibrosis grades 0 vs ≥ 1, ≤ 1 vs ≥ 2, and ≤ 2 vs ≥ 3, respectively, the AUCs increased from 0.79, 0.92, and 0.91 to 0.85, 0.98, and 0.97 (p < 0.001). CONCLUSION: QUS parameters improved the classification accuracy of steatohepatitis, liver steatosis, inflammation, and fibrosis compared to shear wave elastography alone. KEY POINTS: • Quantitative ultrasound and shear wave elastography improved classification accuracy of liver steatohepatitis and its histological features (liver steatosis, inflammation, and fibrosis) compared to elastography alone. • A machine learning approach based on random forest models and incorporating local attenuation and homodyned-K tissue modeling shows promise for classification of nonalcoholic steatohepatitis. • Further research should be performed to demonstrate the applicability of this multi-parametric QUS approach in a human cohort and to validate the combinations of parameters providing the highest classification accuracy.
OBJECTIVES: To develop a machine learning model based on quantitative ultrasound (QUS) parameters to improve classification of steatohepatitis with shear wave elastography in rats by using histopathology scoring as the reference standard. METHODS: This study received approval from the institutional animal care committee. Sixty male Sprague-Dawley rats were either fed a standard chow or a methionine- and choline-deficient diet. Ultrasound-based radiofrequency images were recorded in vivo to generate QUS and elastography maps. Random forests classification models and a bootstrap method were used to identify the QUS parameters that improved the classification accuracy of elastography. Receiver-operating characteristic analyses were performed. RESULTS: For classification of not steatohepatitis vs borderline or steatohepatitis, the area under the receiver-operating characteristic curve (AUC) increased from 0.63 for elastography alone to 0.72 for a model that combined elastography and QUS techniques (p < 0.001). For detection of liver steatosis grades 0 vs ≥ 1, ≤ 1 vs ≥ 2, ≤ 2 vs 3, respectively, the AUCs increased from 0.70, 0.65, and 0.69 to 0.78, 0.78, and 0.75 (p < 0.001). For detection of liver inflammation grades 0 vs ≥ 1, ≤ 1 vs ≥ 2, ≤ 2 vs 3, respectively, the AUCs increased from 0.58, 0.77, and 0.78 to 0.66, 0.84, and 0.87 (p < 0.001). For staging of liver fibrosis grades 0 vs ≥ 1, ≤ 1 vs ≥ 2, and ≤ 2 vs ≥ 3, respectively, the AUCs increased from 0.79, 0.92, and 0.91 to 0.85, 0.98, and 0.97 (p < 0.001). CONCLUSION: QUS parameters improved the classification accuracy of steatohepatitis, liver steatosis, inflammation, and fibrosis compared to shear wave elastography alone. KEY POINTS: • Quantitative ultrasound and shear wave elastography improved classification accuracy of liver steatohepatitis and its histological features (liver steatosis, inflammation, and fibrosis) compared to elastography alone. • A machine learning approach based on random forest models and incorporating local attenuation and homodyned-K tissue modeling shows promise for classification of nonalcoholic steatohepatitis. • Further research should be performed to demonstrate the applicability of this multi-parametric QUS approach in a human cohort and to validate the combinations of parameters providing the highest classification accuracy.
Authors: François Destrempes; Emilie Franceschini; François T H Yu; Guy Cloutier Journal: IEEE Trans Med Imaging Date: 2015-09-22 Impact factor: 10.048
Authors: Jeremy S Paige; Gregory S Bernstein; Elhamy Heba; Eduardo A C Costa; Marilia Fereirra; Tanya Wolfson; Anthony C Gamst; Mark A Valasek; Grace Y Lin; Aiguo Han; John W Erdman; William D O'Brien; Michael P Andre; Rohit Loomba; Claude B Sirlin Journal: AJR Am J Roentgenol Date: 2017-03-07 Impact factor: 3.959
Authors: François Destrempes; Jean Meunier; Marie-France Giroux; Gilles Soulez; Guy Cloutier Journal: IEEE Trans Biomed Eng Date: 2011-03-14 Impact factor: 4.538
Authors: Meng Yin; Kevin J Glaser; Armando Manduca; Taofic Mounajjed; Harmeet Malhi; Douglas A Simonetto; Ruisi Wang; Liu Yang; Shennen A Mao; Jaime M Glorioso; Faysal M Elgilani; Christopher J Ward; Peter C Harris; Scott L Nyberg; Vijay H Shah; Richard L Ehman Journal: Radiology Date: 2017-01-27 Impact factor: 11.105
Authors: Andrea Coppola; Giada Zorzetto; Filippo Piacentino; Valeria Bettoni; Ida Pastore; Paolo Marra; Laura Perani; Antonio Esposito; Francesco De Cobelli; Giulio Carcano; Federico Fontana; Paolo Fiorina; Massimo Venturini Journal: Acta Diabetol Date: 2021-11-15 Impact factor: 4.280
Authors: François Destrempes; Marc Gesnik; Boris Chayer; Marie-Hélène Roy-Cardinal; Damien Olivié; Jeanne-Marie Giard; Giada Sebastiani; Bich N Nguyen; Guy Cloutier; An Tang Journal: PLoS One Date: 2022-01-27 Impact factor: 3.240
Authors: Antonio Carlos Soares Pantaleão; Marcio Pinto de Castro; Krishynan Shanty Fernandes Meirelles Araujo; Carlos Frederico Ferreira Campos; André Luiz Alves da Silva; José Eduardo Ferreira Manso; João Carlos Machado Journal: Ultrasonography Date: 2022-03-24