CoChat

Computer-Aided Diagnosis of Hepatic Fibrosis: Preliminary Evaluation of MRI Texture Analysis Using the Finite Difference Method and an Artificial Neural Network

Kato, Hiroki, Kanematsu, Masayuki, Zhang, Xuejun, Saio, Masanao, Kondo, Hiroshi, Goshima, Satoshi, Fujita, Hiroshi · 2007 · American Journal of Roentgenology
Cited by 79

The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.

Abstract

OBJECTIVE: The purpose of our study was to preliminarily evaluate the usefulness of a computer algorithm analysis using the finite difference method and an artificial neural network to diagnose hepatic fibrosis with MR images. MATERIALS AND METHODS: Liver parenchymal textures on the MR images of 52 patients who underwent partial hepatectomy were processed by the computer algorithm and reviewed by two radiologists. The texture features using the finite difference method were processed by an artificial neural network program containing a three-layer learning algorithm of the back propagation, composed of a seven-unit input layer, a six-unit hidden layer, and a one-unit output layer. The radiologists assigned confidence levels for the presence of hepatic fibrosis. Degrees of hepatic fibrosis were determined semiquantitatively by a pathologist. Algorithm outputs and radiologists' interpretations were correlated with degrees of fibrosis using Spearman's rank correlation analysis, and diagnostic performances were evaluated using receiver operating characteristic curve analysis. RESULTS: By the computer algorithm, the A(z) (area under the curve) value was greater for gadolinium-enhanced equilibrium phase images (A(z) = 0.801) than for T1-weighted (A(z) = 0.597) or T2-weighted (A(z) = 0.525) images (p < 0.05), and the outputs of equilibrium phase images showed a moderate correlation (r = 0.502, p = 0.001) with the pathologic grades. By the radiologists' interpretations, the A(z) value for all images combined (A(z) = 0.715) was greater than that of portal venous phase images (A(z) = 0.503) (p < 0.05), and the confidence levels of all images combined were moderately correlated (r = 0.473, p = 0.002) with pathologic grades. CONCLUSION: Computer algorithm analysis of equilibrium phase images was found to reflect the degree of fibrosis most accurately. MR image texture analysis performed using the computer algorithm was found to have a potential usefulness for the diagnosis of hepatic fibrosis.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.2214/ajr.07.2070

Cites

1 of 1 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Cited by

See all 79

Metadata

Authors
Kato, H., Kanematsu, M., Zhang, X., Saio, M., Kondo, H., Goshima, S., & Fujita, H.
Venue
American Journal of Roentgenology
Published
2007-07
Volume
189
Issue
1
Pages
117-122
ISSN
  • 0002-9580 (ISSN-L)
  • 0361-803X
  • 1546-3141
OpenAlex
W2115774529
Cited by
79
References
1
FWCI
4.10
Type
journal article
Language
en
Open access
closed

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.