Literature DB >> 32070870

Using a single abdominal computed tomography image to differentiate five contrast-enhancement phases: A machine-learning algorithm for radiomics-based precision medicine.

Laurent Dercle1, Jingchen Ma2, Chuanmiao Xie3, Ai-Ping Chen2, Deling Wang3, Lyndon Luk2, Paul Revel-Mouroz4, Philippe Otal4, Jean-Marie Peron5, Hervé Rousseau4, Lin Lu2, Lawrence H Schwartz2, Fatima-Zohra Mokrane6, Binsheng Zhao2.   

Abstract

PURPOSE: The clinical adoption of quantitative imaging biomarkers (radiomics) has established the need for high quality contrast-enhancement in medical images. We aimed to develop a machine-learning algorithm for Quality Control of Contrast-Enhancement on CT-scan (CECT-QC).
METHOD: Multicenter data from four independent cohorts [A, B, C, D] of patients with measurable liver lesions were analyzed retrospectively (patients:time-points; 503:3397): [A] dynamic CTs from primary liver cancer (60:2359); [B] triphasic CTs from primary liver cancer (31:93); [C] triphasic CTs from hepatocellular carcinoma (121:363); [D] portal venous phase CTs of liver metastasis from colorectal cancer (291:582). Patients from cohort A were randomized to training-set (48:1884) and test-set (12:475). A random forest classifier was trained and tested to identify five contrast-enhancement phases. The input was the mean intensity of the abdominal aorta and the portal vein measured on a single abdominal CT scan image at a single time-point. The output to be predicted was: non-contrast [NCP], early-arterial [E-AP], optimal-arterial [O-AP], optimal-portal [O-PVP], and late-portal [L-PVP]. Clinical utility was assessed in cohorts B, C, and D.
RESULTS: The CECT-QC algorithm showed performances of 98 %, 90 %, and 84 % for predicting NCP, O-AP, and O-PVP, respectively. O-PVP was reached in half of patients and was associated with a peak in liver malignancy density. Contrast-enhancement quality significantly influenced radiomics features deciphering the phenotype of liver neoplasms.
CONCLUSIONS: A single CT-image can be used to differentiate five contrast-enhancement phases for radiomics-based precision medicine in the most common liver neoplasms occurring in patients with or without liver cirrhosis.
Copyright © 2020 Elsevier B.V. All rights reserved.

Entities:  

Keywords:  Contrast media; Liver neoplasms; Machine learning; Quality control; Radiomics

Mesh:

Substances:

Year:  2020        PMID: 32070870      PMCID: PMC9345686          DOI: 10.1016/j.ejrad.2020.108850

Source DB:  PubMed          Journal:  Eur J Radiol        ISSN: 0720-048X            Impact factor:   4.531


  29 in total

Review 1.  Invasive and non-invasive diagnosis of cirrhosis and portal hypertension.

Authors:  Moon Young Kim; Woo Kyoung Jeong; Soon Koo Baik
Journal:  World J Gastroenterol       Date:  2014-04-21       Impact factor: 5.742

2.  Spleno-hepatic index to predict portal hypertension by equilibrium radionuclide ventriculography.

Authors:  Laurent Dercle; Chloé Billey; Thomas Cognet; Emmanuelle Cassol; Mathieu Sinigaglia; Pierre Pascal; Isabelle Berry; Philippe Otal; Christophe Bureau; Olivier Lairez
Journal:  Nucl Med Commun       Date:  2018-12       Impact factor: 1.690

3.  Radiomics machine-learning signature for diagnosis of hepatocellular carcinoma in cirrhotic patients with indeterminate liver nodules.

Authors:  Fatima-Zohra Mokrane; Lin Lu; Adrien Vavasseur; Philippe Otal; Jean-Marie Peron; Lyndon Luk; Hao Yang; Samy Ammari; Yvonne Saenger; Herve Rousseau; Binsheng Zhao; Lawrence H Schwartz; Laurent Dercle
Journal:  Eur Radiol       Date:  2019-08-23       Impact factor: 5.315

Review 4.  Liver cirrhosis.

Authors:  Emmanuel A Tsochatzis; Jaime Bosch; Andrew K Burroughs
Journal:  Lancet       Date:  2014-01-28       Impact factor: 79.321

Review 5.  Modified RECIST (mRECIST) assessment for hepatocellular carcinoma.

Authors:  Riccardo Lencioni; Josep M Llovet
Journal:  Semin Liver Dis       Date:  2010-02-19       Impact factor: 6.115

6.  Prognosis of hepatocellular carcinoma: the BCLC staging classification.

Authors:  J M Llovet; C Brú; J Bruix
Journal:  Semin Liver Dis       Date:  1999       Impact factor: 6.115

7.  We should desist using RECIST, at least in GIST.

Authors:  Robert S Benjamin; Haesun Choi; Homer A Macapinlac; Michael A Burgess; Shreyaskumar R Patel; Lei L Chen; Donald A Podoloff; Chuslip Charnsangavej
Journal:  J Clin Oncol       Date:  2007-05-01       Impact factor: 44.544

8.  Diagnosis of hepatic nodules 20 mm or smaller in cirrhosis: Prospective validation of the noninvasive diagnostic criteria for hepatocellular carcinoma.

Authors:  Alejandro Forner; Ramón Vilana; Carmen Ayuso; Lluís Bianchi; Manel Solé; Juan Ramón Ayuso; Loreto Boix; Margarita Sala; María Varela; Josep M Llovet; Concepció Brú; Jordi Bruix
Journal:  Hepatology       Date:  2008-01       Impact factor: 17.425

9.  Hepatocellular carcinoma in cirrhotic patients: prospective comparison of US, CT and MR imaging.

Authors:  Michele Di Martino; Gianmaria De Filippis; Adriano De Santis; Daniel Geiger; Maurizio Del Monte; Concetta Valentina Lombardo; Massimo Rossi; Stefano Ginanni Corradini; Gianluca Mennini; Carlo Catalano
Journal:  Eur Radiol       Date:  2012-11-18       Impact factor: 5.315

10.  A Response Assessment Platform for Development and Validation of Imaging Biomarkers in Oncology.

Authors:  Hao Yang; Lawrence H Schwartz; Binsheng Zhao
Journal:  Tomography       Date:  2016-12
View more
  4 in total

1.  Predicting death or recurrence of portal hypertension symptoms after TIPS procedures.

Authors:  Shawn H Sun; Thomas Eche; Chloé Dorczynski; Philippe Otal; Paul Revel-Mouroz; Charline Zadro; Ephraim Partouche; Nadim Fares; Charlotte Maulat; Christophe Bureau; Lawrence H Schwartz; Hervé Rousseau; Laurent Dercle; Fatima-Zohra Mokrane
Journal:  Eur Radiol       Date:  2022-01-11       Impact factor: 5.315

2.  Identifying Robust Radiomics Features for Lung Cancer by Using In-Vivo and Phantom Lung Lesions.

Authors:  Lin Lu; Shawn H Sun; Aaron Afran; Hao Yang; Zheng Feng Lu; James So; Lawrence H Schwartz; Binsheng Zhao
Journal:  Tomography       Date:  2021-02-09

Review 3.  Understanding Sources of Variation to Improve the Reproducibility of Radiomics.

Authors:  Binsheng Zhao
Journal:  Front Oncol       Date:  2021-03-29       Impact factor: 6.244

Review 4.  Effectiveness of Artificial Intelligence for Personalized Medicine in Neoplasms: A Systematic Review.

Authors:  Sorayya Rezayi; Sharareh R Niakan Kalhori; Soheila Saeedi
Journal:  Biomed Res Int       Date:  2022-04-07       Impact factor: 3.246

  4 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.