Hailong Li1,2, Lili He1,2,3, Jonathan A Dudley2,4, Thomas C Maloney2,4, Elanchezhian Somasundaram2,4,5, Samuel L Brady4,5, Nehal A Parikh1,3, Jonathan R Dillman6,7,8. 1. The Perinatal Institute and Section of Neonatology, Perinatal and Pulmonary Biology, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, USA. 2. Imaging Research Center, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, USA. 3. Department of Pediatrics, University of Cincinnati College of Medicine, Cincinnati, OH, USA. 4. Department of Radiology, Cincinnati Children's Hospital Medical Center, 3333 Burnet Ave., MLC 5031, Cincinnati, OH, 45229, USA. 5. Department of Radiology, University of Cincinnati College of Medicine, Cincinnati, OH, USA. 6. Imaging Research Center, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, USA. Jonathan.Dillman@cchmc.org. 7. Department of Radiology, Cincinnati Children's Hospital Medical Center, 3333 Burnet Ave., MLC 5031, Cincinnati, OH, 45229, USA. Jonathan.Dillman@cchmc.org. 8. Department of Radiology, University of Cincinnati College of Medicine, Cincinnati, OH, USA. Jonathan.Dillman@cchmc.org.
Abstract
BACKGROUND: Although MR elastography allows for quantitative evaluation of liver stiffness to assess chronic liver diseases, it has associated drawbacks related to additional scanning time, patient discomfort, and added costs. OBJECTIVE: To develop a machine learning model that can categorically classify the severity of liver stiffness using both anatomical T2-weighted MRI and clinical data for children and young adults with known or suspected pediatric chronic liver diseases. MATERIALS AND METHODS: We included 273 subjects with known or suspected chronic liver disease. We extracted data including axial T2-weighted fast spin-echo fat-suppressed images, clinical data (e.g., demographic/anthropomorphic data, particular medical diagnoses, laboratory values) and MR elastography liver stiffness measurements. We propose DeepLiverNet (a deep transfer learning model) to classify patients into one of two groups: no/mild liver stiffening (<3 kPa) or moderate/severe liver stiffening (≥3 kPa). We conducted internal cross-validation using 178 subjects, and external validation using an independent cohort of 95 subjects. We assessed diagnostic performance using accuracy, sensitivity, specificity and area under the receiver operating characteristic curve (AuROC). RESULTS: In the internal cross-validation experiment, the combination of clinical and imaging data produced the best performance (AuROC=0.86) compared to clinical (AuROC=0.83) or imaging (AuROC=0.80) data alone. Using both clinical and imaging data, the DeepLiverNet correctly classified patients with accuracy of 88.0%, sensitivity of 74.3% and specificity of 94.6%. In our external validation experiment, this same deep learning model achieved an accuracy of 80.0%, sensitivity of 61.1%, specificity of 91.5% and AuROC of 0.79. CONCLUSION: A deep learning model that incorporates clinical data and anatomical T2-weighted MR images might provide a means of risk-stratifying liver stiffness and directing the use of MR elastography.
BACKGROUND: Although MR elastography allows for quantitative evaluation of liver stiffness to assess chronic liver diseases, it has associated drawbacks related to additional scanning time, patient discomfort, and added costs. OBJECTIVE: To develop a machine learning model that can categorically classify the severity of liver stiffness using both anatomical T2-weighted MRI and clinical data for children and young adults with known or suspected pediatric chronic liver diseases. MATERIALS AND METHODS: We included 273 subjects with known or suspected chronic liver disease. We extracted data including axial T2-weighted fast spin-echo fat-suppressed images, clinical data (e.g., demographic/anthropomorphic data, particular medical diagnoses, laboratory values) and MR elastography liver stiffness measurements. We propose DeepLiverNet (a deep transfer learning model) to classify patients into one of two groups: no/mild liver stiffening (<3 kPa) or moderate/severe liver stiffening (≥3 kPa). We conducted internal cross-validation using 178 subjects, and external validation using an independent cohort of 95 subjects. We assessed diagnostic performance using accuracy, sensitivity, specificity and area under the receiver operating characteristic curve (AuROC). RESULTS: In the internal cross-validation experiment, the combination of clinical and imaging data produced the best performance (AuROC=0.86) compared to clinical (AuROC=0.83) or imaging (AuROC=0.80) data alone. Using both clinical and imaging data, the DeepLiverNet correctly classified patients with accuracy of 88.0%, sensitivity of 74.3% and specificity of 94.6%. In our external validation experiment, this same deep learning model achieved an accuracy of 80.0%, sensitivity of 61.1%, specificity of 91.5% and AuROC of 0.79. CONCLUSION: A deep learning model that incorporates clinical data and anatomical T2-weighted MR images might provide a means of risk-stratifying liver stiffness and directing the use of MR elastography.
Entities:
Keywords:
Children; Chronic liver disease; Deep learning; Liver; Liver stiffness; Magnetic resonance elastography; Magnetic resonance imaging; Risk stratification
Authors: Philipp Kickingereder; David Bonekamp; Martha Nowosielski; Annekathrin Kratz; Martin Sill; Sina Burth; Antje Wick; Oliver Eidel; Heinz-Peter Schlemmer; Alexander Radbruch; Jürgen Debus; Christel Herold-Mende; Andreas Unterberg; David Jones; Stefan Pfister; Wolfgang Wick; Andreas von Deimling; Martin Bendszus; David Capper Journal: Radiology Date: 2016-09-16 Impact factor: 11.105
Authors: Naga Chalasani; Zobair Younossi; Joel E Lavine; Michael Charlton; Kenneth Cusi; Mary Rinella; Stephen A Harrison; Elizabeth M Brunt; Arun J Sanyal Journal: Hepatology Date: 2017-09-29 Impact factor: 17.425
Authors: Andrew Dennis Smith; Kristin K Porter; Asser Abou Elkassem; Rupan Sanyal; Mark E Lockhart Journal: AJR Am J Roentgenol Date: 2019-04-11 Impact factor: 3.959
Authors: Madalsa Joshi; Jonathan R Dillman; Kamalpreet Singh; Suraj D Serai; Alexander J Towbin; Stavra Xanthakos; Bin Zhang; Weizhe Su; Andrew T Trout Journal: Abdom Radiol (NY) Date: 2018-05
Authors: Manisha Bahl; Regina Barzilay; Adam B Yedidia; Nicholas J Locascio; Lili Yu; Constance D Lehman Journal: Radiology Date: 2017-10-17 Impact factor: 11.105
Authors: Mary Catherine Sawh; Kimberly P Newton; Nidhi P Goyal; Jorge Eduardo Angeles; Kathryn Harlow; Craig Bross; Alexandra N Schlein; Jonathan C Hooker; Ethan Z Sy; Kevin J Glaser; Meng Yin; Richard L Ehman; Claude B Sirlin; Jeffrey B Schwimmer Journal: J Magn Reson Imaging Date: 2019-08-27 Impact factor: 4.813
Authors: Timothy J W Dawes; Antonio de Marvao; Wenzhe Shi; Tristan Fletcher; Geoffrey M J Watson; John Wharton; Christopher J Rhodes; Luke S G E Howard; J Simon R Gibbs; Daniel Rueckert; Stuart A Cook; Martin R Wilkins; Declan P O'Regan Journal: Radiology Date: 2017-01-16 Impact factor: 11.105
Authors: Natally Horvat; Joao Miranda; Maria El Homsi; Jacob J Peoples; Niamh M Long; Amber L Simpson; Richard K G Do Journal: Abdom Radiol (NY) Date: 2021-11-26