Logo-jnp
J Nephropathol. 2021;10(3): e26.
doi: 10.34172/jnp.2021.26

Scopus ID: 85108676820
  Abstract View: 1839
  PDF Download: 504

Original Article

The resolution of immunofluorescent pathological images affects diagnosis for not only artificial intelligence but also human

Kensaku Takahashi 1 ORCID logo, Shinji Kitamura 1* ORCID logo, Kazuhiko Fukushima 1, Yizhen Sang 1, Kenji Tsuji 1, Jun Wada 1

1 Department of Nephrology, Rheumatology, Endocrinology and Metabolism, Okayama University Graduate School of Medicine, Dentistry, and Pharmaceutical Sciences, Okayama-shi, Okayama, Japan
*Corresponding Author: Email: kitamura@okayama-u.ac.jp

Abstract

Introduction: For human, the resolution of images is important for diagnosis. Many clinical applications of artificial intelligence have been studied, however there are few reports on the difference in diagnosis between humans and artificial intelligence on the point of the renal pathological image resolution.

Objectives: We examined whether the resolution of renal pathological images affects diagnosis of artificial intelligence and human.

Patients and Methods: From 885 renal biopsy patients, we collected renal IgA immunofluorescent pathological images that resolution is 4, 16, 32, 64, 128, 256 and 512 pixels for each patient, and divided into training data set and validation data set, and created optimum deep learning models for each resolution. To compare with artificial intelligence nephrologist also tried to diagnose by using the same validation data set images.

Results: We inputted IgA immunofluorescent pathological images into each optimum model. Human could not identify specific staining site with four pixels images, however, each resolution optimum model showed high accuracy, average over 80%. The each accuarcy was observed higher depending on the resolution. The area under the curve (AUC) showed higher diagnosis ratio depending on the resolution, too. Nephrologist performed high diagnosis sensitivity depending on resolution images as same as artificial intelligence. However, nephrologists’ diagnosis observed large variations in specificity depending on resolution. These results suggested that the resolution might affect specificity for human not artificial intelligence

Conclusion: The resolution of images might be important for not AI but human on the point of specificity.


Implication for health policy/practice/research/medical education:

We examined how the image resolution affects the diagnosis not only artificial intelligence but also nephrologists in this study. The differences between human and artificial intelligence is specificity on diiferent resolution image diagnosis. The resolution of images might be important for not artificial intelligence but human on the point of specificity.

Please cite this paper as: Takahashi K, Kitamura S, Fukushima K, Sang Y, Tsuji K, Wada J. The resolution of immunofluorescent pathological images affects diagnosis for not only artificial intelligence but also human. J Nephropathol. 2021;10(3):e26. DOI: 10.34172/jnp.2021.26.

First Name
Last Name
Email Address
Comments
Security code


Abstract View: 1840

Your browser does not support the canvas element.


PDF Download: 504

Your browser does not support the canvas element.

Submitted: 10 Feb 2021
Accepted: 09 Mar 2021
ePublished: 02 Apr 2021
EndNote EndNote

(Enw Format - Win & Mac)

BibTeX BibTeX

(Bib Format - Win & Mac)

Bookends Bookends

(Ris Format - Mac only)

EasyBib EasyBib

(Ris Format - Win & Mac)

Medlars Medlars

(Txt Format - Win & Mac)

Mendeley Web Mendeley Web
Mendeley Mendeley

(Ris Format - Win & Mac)

Papers Papers

(Ris Format - Win & Mac)

ProCite ProCite

(Ris Format - Win & Mac)

Reference Manager Reference Manager

(Ris Format - Win only)

Refworks Refworks

(Refworks Format - Win & Mac)

Zotero Zotero

(Ris Format - Firefox Plugin)