Ana Jimenez-Pastor1, Angel Alberich-Bayarri2, Rafael Lopez-Gonzalez2, David Marti-Aguado3, Manuela França4, Rodrigo San Martin Bachmann5, Juan Mazzucco6, Luis Marti-Bonmati7,8. 1. Quantitative Imaging Biomarkers in Medicine, QUIBIM S.L, Aragon Avenue, 30, 13th floor, Office J, 46021, Valencia, Spain. anajimenez@quibim.com. 2. Quantitative Imaging Biomarkers in Medicine, QUIBIM S.L, Aragon Avenue, 30, 13th floor, Office J, 46021, Valencia, Spain. 3. Digestive Disease Department, Clinic University Hospital, INCLIVA Health Research Institute, Valencia, Spain. 4. Radiology Department, Centro Hospitalar Universitário do Porto (CHUP), Porto, Portugal. 5. Laboratorio Clinico Diagnomed, Concepción, Chile. 6. ARGUS Diagnostico Medico, Buenos Aires, Argentina. 7. Biomedical Imaging Research Group (GIBI230-PREBI) at La Fe Health Research Institute, and Imaging La Fe node at Distributed Network for Biomedical Imaging (ReDIB) Unique Scientific and Technical Infrastructures (ICTS), Valencia, Spain. 8. Radiology Department, La Fe University and Polytechnic Hospital, Valencia, Spain.
Abstract
OBJECTIVE: To automate the segmentation of whole liver parenchyma on multi-echo chemical shift encoded (MECSE) MR examinations using convolutional neural networks (CNNs) to seamlessly quantify precise organ-related imaging biomarkers such as the fat fraction and iron load. METHODS: A retrospective multicenter collection of 183 MECSE liver MR examinations was conducted. An encoder-decoder CNN was trained (107 studies) following a 5-fold cross-validation strategy to improve the model performance and ensure lack of overfitting. Proton density fat fraction (PDFF) and R2* were quantified on both manual and CNN segmentation masks. Different metrics were used to evaluate the CNN performance over both unseen internal (46 studies) and external (29 studies) validation datasets to analyze reproducibility. RESULTS: The internal test showed excellent results for the automatic segmentation with a dice coefficient (DC) of 0.93 ± 0.03 and high correlation between the quantification done with the predicted mask and the manual segmentation (rPDFF = 1 and rR2* = 1; p values < 0.001). The external validation was also excellent with a different vendor but the same magnetic field strength, proving the generalization of the model to other manufacturers with DC of 0.94 ± 0.02. Results were lower for the 1.5-T MR same vendor scanner with DC of 0.87 ± 0.06. Both external validations showed high correlation in the quantification (rPDFF = 1 and rR2* = 1; p values < 0.001). In both internal and external validation datasets, the relative error for the PDFF and R2* quantification was below 4% and 1% respectively. CONCLUSION: Liver parenchyma can be accurately segmented with CNN in a vendor-neutral virtual approach, allowing to obtain reproducible automatic whole organ virtual biopsies. KEY POINTS: • Whole liver parenchyma can be automatically segmented using convolutional neural networks. • Deep learning allows the creation of automatic pipelines for the precise quantification of liver-related imaging biomarkers such as PDFF and R2*. • MR "virtual biopsy" can become a fast and automatic procedure for the assessment of chronic diffuse liver diseases in clinical practice.
OBJECTIVE: To automate the segmentation of whole liver parenchyma on multi-echo chemical shift encoded (MECSE) MR examinations using convolutional neural networks (CNNs) to seamlessly quantify precise organ-related imaging biomarkers such as the fat fraction and iron load. METHODS: A retrospective multicenter collection of 183 MECSE liver MR examinations was conducted. An encoder-decoder CNN was trained (107 studies) following a 5-fold cross-validation strategy to improve the model performance and ensure lack of overfitting. Proton density fat fraction (PDFF) and R2* were quantified on both manual and CNN segmentation masks. Different metrics were used to evaluate the CNN performance over both unseen internal (46 studies) and external (29 studies) validation datasets to analyze reproducibility. RESULTS: The internal test showed excellent results for the automatic segmentation with a dice coefficient (DC) of 0.93 ± 0.03 and high correlation between the quantification done with the predicted mask and the manual segmentation (rPDFF = 1 and rR2* = 1; p values < 0.001). The external validation was also excellent with a different vendor but the same magnetic field strength, proving the generalization of the model to other manufacturers with DC of 0.94 ± 0.02. Results were lower for the 1.5-T MR same vendor scanner with DC of 0.87 ± 0.06. Both external validations showed high correlation in the quantification (rPDFF = 1 and rR2* = 1; p values < 0.001). In both internal and external validation datasets, the relative error for the PDFF and R2* quantification was below 4% and 1% respectively. CONCLUSION: Liver parenchyma can be accurately segmented with CNN in a vendor-neutral virtual approach, allowing to obtain reproducible automatic whole organ virtual biopsies. KEY POINTS: • Whole liver parenchyma can be automatically segmented using convolutional neural networks. • Deep learning allows the creation of automatic pipelines for the precise quantification of liver-related imaging biomarkers such as PDFF and R2*. • MR "virtual biopsy" can become a fast and automatic procedure for the assessment of chronic diffuse liver diseases in clinical practice.
Entities:
Keywords:
Biomarkers; Iron overload; Magnetic resonance imaging; Neural network models; Non-alcoholic fatty liver disease
Authors: Nandita M deSouza; Aad van der Lugt; Christophe M Deroose; Angel Alberich-Bayarri; Luc Bidaut; Laure Fournier; Lena Costaridou; Daniela E Oprea-Lager; Elmar Kotter; Marion Smits; Marius E Mayerhoefer; Ronald Boellaard; Anna Caroli; Lioe-Fee de Geus-Oei; Wolfgang G Kunz; Edwin H Oei; Frederic Lecouvet; Manuela Franca; Christian Loewe; Egesta Lopci; Caroline Caramella; Anders Persson; Xavier Golay; Marc Dewey; James P B O'Connor; Pim deGraaf; Sergios Gatidis; Gudrun Zahlmann Journal: Insights Imaging Date: 2022-10-04
Authors: Moritz Gross; Michael Spektor; Ariel Jaffe; Ahmet S Kucukkaya; Simon Iseke; Stefan P Haider; Mario Strazzabosco; Julius Chapiro; John A Onofrey Journal: PLoS One Date: 2021-12-01 Impact factor: 3.240
Authors: Ina Vernikouskaya; Hans-Peter Müller; Dominik Felbel; Francesco Roselli; Albert C Ludolph; Jan Kassubek; Volker Rasche Journal: Sci Rep Date: 2022-04-01 Impact factor: 4.379