Literature DB >> 33369008

Evaluate the performance of four artificial intelligence-aided diagnostic systems in identifying and measuring four types of pulmonary nodules.

Ming-Yue Wu1, Yong Li2, Bin-Jie Fu2, Guo-Shu Wang2, Zhi-Gang Chu2, Dan Deng1.   

Abstract

PURPOSE: This study aims to evaluate the performance of four artificial intelligence-aided diagnostic systems in identifying and measuring four types of pulmonary nodules.
METHODS: Four types of nodules were implanted in a commercial lung phantom. The phantom was scanned with multislice spiral computed tomography, after which four systems (A, B, C, D) were used to identify the nodules and measure their volumes.
RESULTS: The relative volume error (RVE) of system A was the lowest for all nodules, except for small ground glass nodules (SGGNs). System C had the smallest RVE for SGGNs, -0.13 (-0.56, 0.00). In the Bland-Altman test, only systems A and C passed the consistency test, P = 0.40. In terms of precision, the miss rate (MR) of system C was 0.00% for small solid nodules (SSNs), ground glass nodules (GGNs), and solid nodules (SNs) but 4.17% for SGGNs. The comparable system D MRs for SGGNs, SSNs, and GGNs were 71.30%, 25.93%, and 47.22%, respectively, the highest among all the systems. Receiver operating characteristic curve analysis indicated that system A had the best performance in recognizing SSNs and GGNs, with areas under the curve of 0.91 and 0.68. System C had the best performance for SGGNs (AUC = 0.91).
CONCLUSION: Among four types nodules, SGGNs are the most difficult to recognize, indicating the need to improve higher accuracy and precision of artificial systems. System A most accurately measured nodule volume. System C was most precise in recognizing all four types of nodules, especially SGGN.
© 2020 The Authors. Journal of Applied Clinical Medical Physics published by Wiley Periodicals, Inc. on behalf of American Association of Physicists in Medicine.

Entities:  

Keywords:  artificial intelligence; lung phantom; pulmonary nodules

Mesh:

Year:  2020        PMID: 33369008      PMCID: PMC7856495          DOI: 10.1002/acm2.13142

Source DB:  PubMed          Journal:  J Appl Clin Med Phys        ISSN: 1526-9914            Impact factor:   2.102


  30 in total

Review 1.  Evidence for the treatment of patients with pulmonary nodules: when is it lung cancer?: ACCP evidence-based clinical practice guidelines (2nd edition).

Authors:  Momen M Wahidi; Joseph A Govert; Ranjit K Goudar; Michael K Gould; Douglas C McCrory
Journal:  Chest       Date:  2007-09       Impact factor: 9.410

Review 2.  Noncalcified lung nodules: volumetric assessment with thoracic CT.

Authors:  Marios A Gavrielides; Lisa M Kinnard; Kyle J Myers; Nicholas Petrick
Journal:  Radiology       Date:  2009-04       Impact factor: 11.105

3.  Variability of semiautomated lung nodule volumetry on ultralow-dose CT: comparison with nodule volumetry on standard-dose CT.

Authors:  Patrick A Hein; Valentina C Romano; Patrik Rogalla; Christian Klessen; Alexander Lembcke; Lars Bornemann; Volker Dicken; Bernd Hamm; Hans-Christian Bauknecht
Journal:  J Digit Imaging       Date:  2008-09-05       Impact factor: 4.056

4.  Pulmonary nodules with ground-glass opacity can be reliably measured with low-dose techniques regardless of iterative reconstruction: results of a phantom study.

Authors:  Jenifer W Siegelman; Mark P Supanich; Marios A Gavrielides
Journal:  AJR Am J Roentgenol       Date:  2015-06       Impact factor: 3.959

5.  Recommendations for Measuring Pulmonary Nodules at CT: A Statement from the Fleischner Society.

Authors:  Alexander A Bankier; Heber MacMahon; Jin Mo Goo; Geoffrey D Rubin; Cornelia M Schaefer-Prokop; David P Naidich
Journal:  Radiology       Date:  2017-06-26       Impact factor: 11.105

6.  Variability in CT lung-nodule volumetry: Effects of dose reduction and reconstruction methods.

Authors:  Stefano Young; Hyun J Grace Kim; Moe Moe Ko; War War Ko; Carlos Flores; Michael F McNitt-Gray
Journal:  Med Phys       Date:  2015-05       Impact factor: 4.071

7.  Benefit of overlapping reconstruction for improving the quantitative assessment of CT lung nodule volume.

Authors:  Marios A Gavrielides; Rongping Zeng; Kyle J Myers; Berkman Sahiner; Nicholas Petrick
Journal:  Acad Radiol       Date:  2012-10-22       Impact factor: 3.173

8.  Accuracy of lung nodule volumetry in low-dose CT with iterative reconstruction: an anthropomorphic thoracic phantom study.

Authors:  K W Doo; E-Y Kang; H S Yong; O H Woo; K Y Lee; Y-W Oh
Journal:  Br J Radiol       Date:  2014-07-16       Impact factor: 3.039

9.  Automated system for lung nodules classification based on wavelet feature descriptor and support vector machine.

Authors:  Hiram Madero Orozco; Osslan Osiris Vergara Villegas; Vianey Guadalupe Cruz Sánchez; Humberto de Jesús Ochoa Domínguez; Manuel de Jesús Nandayapa Alfaro
Journal:  Biomed Eng Online       Date:  2015-02-12       Impact factor: 2.819

10.  [Effect of Scanning and Reconstruction Parameters on Three Dimensional Volume and CT Value Measurement of Pulmonary Nodules: A Phantom Study].

Authors:  Datong Su; Lei Feng; Yingjian Jiang; Ying Wang
Journal:  Zhongguo Fei Ai Za Zhi       Date:  2017-08-20
View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.